UTS site search

Professor Hung Nguyen

Biography

Prof Hung T. Nguyen received his BE degree with First Class Honours and University Medal in 1976 and PhD degree in 1980 from the University of Newcastle in Australia.

He is currently Assistant Deputy Vice-Chancellor (Innovation), Director of the Centre for Health Technologies, and Professor of Electrical Engineering at UTS.

He has been involved with research in the areas of biomedical engineering, artificial intelligence, neurosciences and advanced control for more than 20 years. He has developed several biomedical devices and systems for diabetes, disability, cardiovascular diseases and breast cancer.

Prof Nguyen was appointed a Member of the Order of Australia (AM) in 2002 and was a finalist for NSW Australian of the Year 2012. He was Dean of the Faculty of Engineering and Information Technology at UTS from 2010 to 2014, Founder & CEO/Managing Director of AIMedics Pty Ltd from 2001 to 2006, a recipient of UTS Teaching Award in 2000, and Engineering Manager of Power Electronics Pty Ltd from 1988 to 1990.

Professional

Prof Nguyen is a Fellow of the Institution of Engineers, Australia; the Australian Computer Society; and the British Computer Society. He is also a Senior Member of the Institute of Electrical and Electronic Engineers.

Image of Hung Nguyen
Assist DVC & VP (Innovation)/Director Health Technologies, Provost
Director, CHT - Centre for Health Technologies
Core Member, CHT - Centre for Health Technologies
Associate Member, AAI - Advanced Analytics Institute
B.E. (Ncle) Honours Class I, ME (Ncle), PhD (Ncle)
Fellow, Australian Computer Society
Fellow, British Computer Society
Fellow, Institution of Engineers, Australia
 
Phone
+61 2 9514 2996

Research Interests

Biomedical Engineering, Biomedical Devices, Artificial Intelligence, Neurosciences, Advanced Control, Robotics and Automation

Major Competitive Research Grants

2016-2018, NHMRC Project Grant (APP1102286), Non-invasive detection of hypoglycaemia in people with diabetes using brain wave activity, CI: Prof Hung Nguyen, Prof Timothy Jones, Prof Tuan Nguyen, AI: A/Prof Jerry Greenfield, $330,447

2015-2017, ARC Project Grant (DP150102493), Non-invasive prediction of averse neural events using brain wave activity, Prof Hung Nguyen, Prof Ashley Craig, $234,800.

2014-2016, NHMRC Project Grant (APP1062319), Understanding and predicting freezing of gait in Parkinson’s disease, CI: A/Prof Simon Lewis, Prof Hung Nguyen, Dr Hamish MacDougal, A/Prof Philip Ward, AI: A/Prof Sharon Naismith, $368,360

2011, ARC LIEF Grant (LE110100094), Selective laser melting – an advanced manufacturing and physical modelling technology for the digital age, Prof Timothy Sercombe, Prof Arcady Dyskin, Prof Elena Pasternak, Prof Graham Schaffer, Prof Hung Nguyen, Prof Phillip Dight, Dr Anthony Roberts, Prof Klaus Regenauer-Lieb, A/Prof Joseph Grotowski, Prof Syed Masood, $300,000

2006-2008, ARC Project Grant (DP06668541), Innovative hands-free technology to give the severely disabled greater mobility control, Prof Hung Nguyen, Prof Ashley Craig, Prof James Middleton, Dr Yvonne Tran, $245,000.

2006, ARC LIEF Grant (LE0668541), Infrastructure for design and testing of implantable and non-invasive intelligent medical devices, Prof Hung Nguyen, Prof Nigel Lovell, Prof Ashley Craig, Dr Peter Watterson, A/Prof Ananda Sanagavarapu, Dr Laura Poole-Warren, Dr Socrates Dokos, A/Prof Clive McFarland, $260,000.

2005-2007, Juvenile Diabetes Research Foundation International Regular Research Grant (1-2005-1055), Non-invasive hypoglycaemia detection using physiological responses, Prof Hung Nguyen, Prof Stephen Colagiuri, Prof Timothy Jones, $USD411,000.

2004, ARC LIEF Grant (LE0454081), Innovative assistive technology for severely disabled people, Prof Hung Nguyen, Prof Ashley Craig, Prof Glen Davis, Dr James Middleton, Mr Andrew Barriskill, $276,317.

2003-2004 NHMRC Development Grant (244905), Miniature implanted device to improve heart failure management, Prof Stephen Hunyor, Dr Peter O’Kelly, Prof Hung Nguyen, Dr Yifei Huang, $335,000.

2003-2005, ARC Project Grant (DP0346540), Microwave differential imaging of myocardium for assessment and therapeutic monitoring of transcatheter cardiac ablation, A/Prof Ananda Sanagavarapu, Prof David Ross, Prof Hung Nguyen, $259,000.

Full Patents

12. Hung T. Nguyen, "Method and System for Determining a Variation in a Metabolic Function and Managing the Variation Accordingly", Australian Patent No. 2010239138, granted 5 May 2016.

11. Hung T. Nguyen, "A Method and System for Controlling a Device", Australian Patent No. 2010239137, granted 4 February 2016.

10.   Nejhdeh Ghevondian, Hung Nguyen, Richard John Wilshire, “Patient Monitor”, US Patent US 8,945,007 B2, granted 3 February 2015.

9. Hung T. Nguyen, “Method and System for Determining a Variation in a Metabolic Function and Managing the Variation Accordingly”, US Patent US 8,880,164 B2, granted 4 November 2014.

8. Hung T. Nguyen and Nejhdeh Ghevondian, “A Non-Invasive Method and Apparatus for Determining Onset of Physiological Conditions”, Canadian Patent CA 2439276 C, granted 16 April 2013.

7. Hung T. Nguyen and Nejhdeh Ghevondian, “Non-Invasive Method and Apparatus for Determining Onset of Physiological Conditions”, European Patent (App. 02700041.3), approved 9 May 2012.

6. Nejhdeh Ghevondian, Hung Nguyen, Richard John Wilshire, “Patient Monitor”, Australian Patent No. 2004236368, granted 17 November 2011.

5. Nejhdeh Ghevondian, Hung Nguyen, Richard John Wilshire, “Patient Monitor”, New Zealand Patent No. 566149 (Divisional of 543267), granted 7 January 2010.

4. Nejhdeh Ghevondian, Hung Nguyen, Richard John Wilshire, “Patient Monitor”, European Patent EP1626657, granted 16 September 2009.

3. Hung T. Nguyen and Nejhdeh Ghevondian, “Non-Invasive Method and Apparatus for Determining Onset of Physiological Conditions”, US Patent US 7,450,986 B2, granted 11 November 2008.

2. Hung T. Nguyen and Nejhdeh Ghevondian, “Non-Invasive Method and Apparatus for Determining Onset of Physiological Conditions”, New Zealand Patent No. 527818, granted 9 June 2005.

1. Hung T. Nguyen and Nejhdeh Ghevondian, “Non-Invasive Method and Apparatus for Determining Onset of Physiological Conditions”, Australian Patent No. 2002233052, granted 23 September 2004.

Biomedical Instrumentation and Applications, Neural Networks and Fuzzy Logic

Books

Savkin, A.V., Cheng, T.M., Li, Z., Javed, F., Matveev, A.S. & Nguyen, H. 2015, Decentralized Coverage Control Problems For Mobile Robotic Sensor and Actuator Networks, John Wiley & Sons.
View/Download from: UTS OPUS
This book introduces various coverage control problems for mobile sensor networks including barrier, sweep and blanket. Unlike many existing algorithms, all of the robotic sensor and actuator motion algorithms developed in the book are fully decentralized or distributed, computationally efficient, easily implementable in engineering practice and based only on information on the closest neighbours of each mobile sensor and actuator and local information about the environment. Moreover, the mobile robotic sensors have no prior information about the environment in which they operation. These various types of coverage problems have never been covered before by a single book in a systematic way. Another topic of this book is the study of mobile robotic sensor and actuator networks. Many modern engineering applications include the use of sensor and actuator networks to provide efficient and effective monitoring and control of industrial and environmental processes. Such mobile sensor and actuator networks are able to achieve improved performance and efficient monitoring together with reduction in power consumption and production cost.
Lam, H.K., Ling, S.H. & Nguyen, H.T. 2012, Computational Intelligence and Its Applications Evolutionary Computation, Fuzzy Logic, Neural Network and Support Vector Machine Techniques, World Scientific.
This book focuses on computational intelligence techniques and their applications — fast-growing and promising research topics that have drawn a great deal of attention from researchers over the years.
Holst, H.V., Nguyen, H.T. & Wikander, J. 2010, Innovation Driven Research Education Volume I : an Introduction, KTH Royal Institute of Technology.
The Innovation Driven Research Education Handbook gives an introduction to the world of innovation and enterprise in order to facilitate the understanding of how basic research results can be transformed into new innovations for business ...

Chapters

Ting, S.R.S., Min, E.H., Cortie, M.B., Nguyen, H.T. & Hutvagner, G. 2015, 'Non-Viral Nano-Vectors for Nucleic Acid Delivery' in Bondi, M.L., Botto, C. & Amore, E. (eds), Frontiers in Nanomedicine, Bentham Science, UAE, pp. 222-255.
View/Download from: UTS OPUS or Publisher's site
The development of therapeutic nucleic acids has led to new strategies for treating various diseases. Non-viral, synthetic nano-vectors in gene therapy have attracted increasing attention due to their low immunogenicity and low toxicity compared to viral counterparts. Due to the molecular structure of nucleic acids, they are very prone to degradation in pH sensitive biological environments. Therefore, synthetic nano-vehicles for therapeutic delivery, known as 'nano-vectors', need to be cleverly designed and engineered to protect and deliver appropriate therapeutic nucleic acids to the targeted sites for action. In this chapter, a brief overview of various types of therapeutic nucleic acids is first provided, followed by analysis of the synthetic nanomaterials under development as delivery systems to carry nucleic acids. The nucleic acid-encapsulated nano-vectors discussed here open a window for a new generation of nanomedicine.
Tran, Y., Nguyen, H. & Craig, A. 2014, 'Assistive technologies using brain-computer interfaces: The problem of mental fatigue' in New Research on Assistive Technologies: Uses and Limitations, pp. 85-96.
View/Download from: UTS OPUS
© 2014 by Nova Science Publishers, Inc. All rights reserved. Assistive technology has great potential for enhancing the capabilities of individuals with disabilities. In people with a severe neurological disability like chronic spinal cord injury (SCI) one strategy to overcome functional loss involves providing access to assistive technology that allows the severely disabled person to regain some level of control over their living environment. New types of assistive technologies include brain computer interface (BCI) based assistive technology systems. These are systems that interpret and translate voluntary changes in brain electrical activity to allow users to activate and control devices in their environment with their brain signals. However, BCI based assistive technologies require a great deal of attention and concentration from the user, especially if the user exerts control over extended periods of time. Any task that requires extended concentration and attention will undoubtedly result in elevated mental fatigue. Chronic mental fatigue is a common though negative symptom of many illnesses and disabilities. In this chapter we describe a device that utilizes changes in brain activity using EEG alpha waves (8-13Hz) as a switching mechanism for an environmental control system (ECS). The device functions by detecting changes in alpha activity during the opening and closing of the eyes. A rapid and substantial increase in alpha activity is observed when eyes are closed and there is a large attenuation of the 8-13Hz activity when the eyes are open. Switching occurs when alpha activity increases above a set threshold during eye closure. Although this hands-free ECS has been shown to be effective in severely disabled participants in their homes while operating a television set, little is known about the effects of mental fatigue on the operational capacity of this device when used by people with severe disabilities for long periods of time. Recent research on stra...
Tran, T., Hoang, T.D., Ha, Q.P. & Nguyen, H.T. 2012, 'Decentralized Model Predictive Control of Time-varying Splitting Parallel Systems' in Mohammadpour, J. & Scherer, C.W. (eds), Control of Linear Parameter Varying Systems with Applications, Springer, Germany, pp. 217-251.
View/Download from: UTS OPUS or Publisher's site
This chapter is devoted to the development of a decentralised model predictive control (MPC) strategy for splitting parallel systems that have timevarying and unknown splitting ratios. The large-scale system in consideration consists of several dynamically-coupled modular subsystems. Each subsystem is regulated by a dedicated multivariable controller employing the open-loop MPC algorithms in conjunction with stability constraints. The connection topology of the large-scale systems includes serial, parallel and recirculated configurations. The solution to splitting parallel systems in this chapter is not only an alternative to the hybrid approach for duty-standby modes, but also a novel approach that accommodates the concurrent operations of splitting parallel systems. The effectiveness of this approach rests on the newly introduced asymptotically positive real constraint (APRC) which prescribes an approaching characteristic towards a positive real property of the system under control. The asymptotic attribute of APRC smooths out all significant wind-up actions in the control trajectories. The APRCs are developed into a one-time-step quadratic constraint on the local control vectors, which plays the role of a stability constraint for the decentralised MPC. The recursive feasibility is assured by characterizing the APRC with dynamicmultiplier matrices. Numerical simulations for two typical modular systems in an alumina refinery are provided to illustrate the theoretical results.
Dehestani, D., Guo, Y., Ling, S.S., Su, S.T.E.V.E.N. & Nguyen, H. 2012, 'Intelligent fault detection and isolation of HVAC system based on online support vector machine' in Lam, H.K., Ling, S.T.E.V.E. & Nguyen, H. (eds), Computational Intelligence and Its Applications: Evolutionary Computation, Fuzzy Logic, Neural Network and Support Vector Machine Techniques.
Tran, T., Tuan, H.D., Ha, Q.P. & Nguyen, H.T. 2012, 'Decentralised model predictive control of time-varying splitting parallel systems' in Control of Linear Parameter Varying Systems with Applications, pp. 217-251.
View/Download from: Publisher's site
© 2012 Springer Science+Business Media, LLC. All rights reserved. This chapter is devoted to the development of a decentralised model predictive control (MPC) strategy for splitting parallel systems that have time-varying and unknown splitting ratios. The large-scale system in consideration consists of several dynamically-coupled modular subsystems. Each subsystem is regulated by a dedicated multivariable controller employing the open-loop MPC algorithms in conjunction with stability constraints. The connection topology of the large-scale systems includes serial, parallel and recirculated configurations. The solution to splitting parallel systems in this chapter is not only an alternative to the hybrid approach for duty-standby modes, but also a novel approach that accommodates the concurrent operations of splitting parallel systems. The effectiveness of this approach rests on the newly introduced asymptotically positive real constraint (APRC) which prescribes an approaching characteristic towards a positive real property of the system under control. The asymptotic attribute of APRC smooths out all significant wind-up actions in the control trajectories. The APRCs are developed into a one-time-step quadratic constraint on the local control vectors, which plays the role of a stability constraint for the decentralised MPC. The recursive feasibility is assured by characterizing the APRC with dynamic multiplier matrices. Numerical simulations for two typical modular systems in an alumina refinery are provided to illustrate the theoretical results.
Nguyen, H.T. 2010, 'Technology Dynamics for Innovative Entrepreneurship' in Holst, H.V., Nguyen, H. & Wikander, J. (eds), Innovation Driven Research Education, Product Innovation Engineering Program, Sweden, pp. 107-117.
Usually, university spin-off companies are based on state-of-the-art developments that come from innovative research work. resulting in the generation of inrel lecruai property and involvement of leading researchers. Associated with these companies. [he risks are greater because they contain more dimensions of in novation than other business ventures. These include novelty to market, novelty (0 management, and novelty to producrion (Shepherd 2000).
Farrugia, S.P., King, L., Lubke, S. & Nguyen, H.T. 2010, 'Regulatory Approvals' in Holst, H.V., Nguyen, H. & Wikander, J. (eds), Innovation Driven Research Education, Product Innovation Engineering Program, Sweden, pp. 119-151.
The aim of this chapter is to provide an overview of the RegulatOry Approval process for medical devices intended for sa le in (he United States of America. The sale of medical devices in most countries is regu lated by law. In the United States, medical devices are regulated by the Center for Devices and Radiological Health (CDRH) of the Food and Drug Administration (FDA). The FDA mandate is to promote and protect the public health by making safe and effective medical devices available in a timely manner.
Wightley, A.C., Baxter, J. & Nguyen, H.T. 2010, 'Design Of A Business Plan For Innovation' in Holst, H.V., Nguyen, H. & Wikander, J. (eds), Innovation Driven Research Education, Product Innovation Engineering Program, Sweden, pp. 153-166.
Holst, H.V., Nguyen, H.T. & Wikander, J. 2010, 'Introduction' in Holst, H.V., Nguyen, H. & Wikander, J. (eds), Innovation Driven Research Education, Product Innovation Engineering Program, Sweden, pp. 15-17.
Khushaba, R.N., Al-Ani, A., Al-Jumaily, A. & Nguyen, H.T. 2008, 'A Hybrid Nonlinear-Discriminant Analysis Feature Projection Technique' in Wobcke, W. & Zhang, M. (eds), Lecture Notes In Computer Science Vol 5360: AI 2008 Advances in Artificial Intelligence, Springer, Germany, pp. 544-550.
View/Download from: UTS OPUS or Publisher's site
Feature set dimensionality reduction via Discriminant Analysis (DA) is one of the most sought after approaches in many applications. In this paper, a novel nonlinear DA technique is presented based on a hybrid of Artificial Neural Networks (ANN) and the Uncorrelated Linear Discriminant Analysis (ULDA). Although dimensionality reduction via ULDA can present a set of statistically uncorrelated features, but similar to the existing DAs it assumes that the original data set is linearly separable, which is not the case with most real world problems. In order to overcome this problem, a one layer feed-forward ANN trained with a Differential Evolution (DE) optimization technique is combined with ULDA to implement a nonlinear feature projection technique. This combination acts as nonlinear discriminant analysis. The proposed approach is validated on a Brain Computer Interface (BCI) problem and compared with other techniques.
Kulatunga, A.K., Skinner, B., Liu, D. & Nguyen, H.T. 2007, 'Distributed simultaneous task allocation and motion coordination of autonomous vehicles using a parallel computing cluster' in Tarn, T.J., Chen, S.B. & Zhou, C. (eds), Robotic Welding, Intelligence and Automation, Springer, Heidelberg, pp. 409-420.
View/Download from: UTS OPUS or Publisher's site
Task allocation and motion coordination are the main factors that should be consi-dered in the coordination of multiple autonomous vehicles in material handling systems. Presently, these factors are handled in different stages, leading to a reduction in optimality and efficiency of the overall coordination. However, if these issues are solved simultaneously we can gain near optimal results. But, the simultaneous approach contains additional algorithmic complexities which increase computation time in the simulation environment. This work aims to reduce the computation time by adopting a parallel and distributed computation strategy for Simultaneous Task Allocation and Motion Coordination (STAMC). In the simulation experiments, each cluster node executes the motion coordination algorithm for each autonomous vehicle. This arrangement enables parallel computation of the expensive STAMC algorithm. Parallel and distributed computation is performed directly within the interpretive MATLAB environment. Results show the parallel and distributed approach provides sub-linear speedup compared to a single centralised computing node.

Conferences

Ting, S.S., Min, E.H., Nguyen, H.T., Stenzel, M.H. & Hutvagner, G. 2015, 'Targeted delivery of siRNA using glycopolymer', 35th Australasian Polymer Symposium, Gold Coast, Australia.
View/Download from: UTS OPUS
Liver is an essential part of the human biological system as it serves to detoxify, synthesize protein and produce biochemicals necessary for digestion. However, there have been common liver diseases namely, hepatitis (A, B, C, and E), fatty liver, cirrhosis and ultimately liver cancer. RNA interference (RNAi) mediated through double-stranded small interfering RNA (siRNA) pave the way to knockdown disease causing gene.1 Nevertheless, effective delivery of siRNA is an arduous task as they are very prone to degradation and are difficult to target specific cells. Glycopolymers are carbohydrates based polymers that recognise biological receptors on cells.2 This project focuses on the design of synthetic glycopolymer architectures using reversible addition-fragmentation transfer (RAFT) polymerization of sugar containing monomers for conjugations of siRNA. Galactose based monomer are selected here, as liver cancer cells over-expressed asialoglycoproteins, which are galactose recognising receptors. Moreover, synthetic delivery system has been reported to protect enzymatic degradation of therapeutics during delivery in the biological enviroment.3 Figure 1 shows the synthetic approach towards glycopolymers for the conjugation of siRNA by using a 4-Cyano-4-[(dodecylsulfanylthiocarbonyl)sulfanyl] pentanoic acid (CPDT) RAFT agent, 4,4-Azobis(4-cyanovaleric acid) (ACVA) initiator polymerized in dioxane. Figure 2 display the increased in molecular weights of polymers with increasing monomer conversions.
Argha, A., Li, L.I., Su, S. & Nguyen 2015, 'Discrete-Time Sliding Mode Control for Networked Systems With Random Communication Delays', Proceedings of the 2015 American Control Conference (ACC), The 2015 American Control Conference, IEEE, Chicago, IL, USA, pp. 6016-6021.
View/Download from: UTS OPUS or Publisher's site
This paper aims to design a robust discretetime sliding mode control (DSMC) for the uncertain discretetime networked systems involving time-varying Communication delays. To this end, the so-called Bernoulli random binary distribution is utilized to model the random time-varying delays. Then, by exploiting a specific sliding surface, a discrete-time sliding mode controller is designed such that the derived closed-loop system state and sliding function remain bounded in the presence of uncertainties and exogenous disturbances. Since the system state and sliding function are involved timevarying delays, the notion of exponentially mean square stability will be used to guarantee the stability/boundedness of the derived closed-loop system. The proposed robust DSMC can also overcome the conservatism of the existing methods in the literature. An illustrative example is presented to show the effectiveness of the proposed approach.
Candra, H., Yuwono, M., Chai, R., Handojoseno, A., Elamvazuthi, I., Nguyen, H.T. & Su, S. 2015, 'Investigation of Window Size in Classification of EEG Emotion Signal with Wavelet Entropy and Support Vector Machine', Proceeding in Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE, 2015, pp. 7250-7253., 37TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE Engineering in Medicine and Biology Society 2015, EMBC 2015, Milano, Italy, pp. 7250-7253.
View/Download from: UTS OPUS or Publisher's site
When dealing with patients with psychological or emotional symptoms, medical practitioners are often faced with the problem of objectively recognizing their patients' emotional state. In this paper, we approach this problem using a computer program that automatically extracts emotions from EEG signals. We extend the finding of Koelstra et. al [IEEE trans. affective comput., vol. 3, no. 1, pp. 18–31, 2012] using the same dataset (i.e. the DEAP: dataset for emotion analysis using electroencephalogram, physiological and video signals), where we observed that the accuracy can be further improved using wavelet features extracted from shorter time segments. More precisely, we achieved accuracy of 65% for both valence and arousal using the wavelet entropy of 3 to 12 seconds signal segments. This improvement in accuracy entails an important discovery that information on emotions contained in the EEG signal may be better described in term of wavelets and in shorter time segments.
Candra, H., Yuwono, M., Handojoseno, A., Chai, R., Su, S. & Nguyen, H.T. 2015, 'Recognizing emotions from EEG subbands using wavelet analysis', Proceeding in Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE, 2015, pp. 6030-6033., 37TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE Engineering in Medicine and Biology Society 2015, Milano, Italy, pp. 6030-6033.
View/Download from: UTS OPUS or Publisher's site
Objectively recognizing emotions is a particularly important task to ensure that patients with emotional symptoms are given the appropriate treatments. The aim of this study was to develop an emotion recognition system using Electroencephalogram (EEG) signals to identify four emotions including happy, sad, angry, and relaxed. We approached this objective by firstly investigating the relevant EEG frequency band followed by deciding the appropriate feature extraction method. Two features were considered namely: 1. Wavelet Energy, and 2. Wavelet Entropy. EEG Channels reduction was then implemented to reduce the complexity of the features. The ground truth emotional states of each subject were inferred using Russel's circumplex model of emotion, that is, by mapping the subjectively reported degrees of valence (pleasure) and arousal to the appropriate emotions — for example, an emotion with high valence and high arousal is equivalent to a 'happy' emotional state, while low valence and low arousal is equivalent to a 'sad' emotional state. The Support Vector Machine (SVM) classifier was then used for mapping each feature vector into corresponding discrete emotions. The results presented in this study indicated thatWavelet features extracted from alpha, beta and gamma bands seem to provide the necessary information for describing the aforementioned emotions. Using the DEAP (Dataset for Emotion Analysis using electroencephalogram, Physiological and Video Signals), our proposed method achieved an average sensitivity and specificity of 77.4% +/ 14.1% and 69.1% +/ 12.8%, respectively.
Handojoseno, A.M.A., Gilat, M., Ly, Q.T., Chamtie, H., Shine, J.M., Nguyen, T.N., Tran, Y., Lewis, S.J.G. & Nguyen, H.T. 2015, 'An EEG Study of Turning Freeze in Parkinson's Disease Patients:The Alteration of Brain Dynamic on the Motor and Visual Cortex', Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Milano, Italy, pp. 6618-6621.
View/Download from: UTS OPUS
Freezing of gait is a very debilitating symptom affecting many patients with Parkinson's disease, leading to a reduced mobility and increased risk for falls. Turning is known to be the most provocative trigger for freezing of gait. However, the underlying brain dynamic changes associated with a turning freeze remain unknown. This study therefore used ambulatory EEG to investigate the brain dynamic changes associated with freezing of gait during turning. In addition, this study aimed to determine the most suitable EEG sensor location to detect freezing of gait during turning using our classification system. Data from four Parkinson's disease patients with freezing of gait was analysed using power spectral density and brain effective connectivity, comparing periods of successful turning with freezing of gait during turning. Results showed that freezing of gait during turning is associated with significant alterations in the high beta and theta power spectral densities across the occipital and parietal areas. Furthermore, brain effective connectivity showed that freezing during turning was associated with increased connectivity towards the visual area, which also had the highest accuracy to detect freezing episodes in the O1 regions by using power spectral density in our classification analyses. This is the first study to show cortical dynamic changes associated with freezing of gait during turning, providing valuable information to enhance the performance of future freezing of gait detection systems.
Ha, V.K.L., Nguyen, T.N. & Nguyen, H.T. 2015, 'Real-time Transmission of Panoramic Images for aTelepresence Wheelchair', 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Milan, Italy, pp. 3565-3568.
View/Download from: UTS OPUS
This paper proposes an approach to transmit panoramic images in real-time for a telepresence wheelchair. The system can provide remote monitoring and assistive assistance for people with disabilities. This study exploits technological advancement in image processing, wireless communication networks, and healthcare systems. High resolution panoramic images are extracted from the camera which is mounted on the wheelchair. The panoramic images are streamed in real-time via a wireless network. The experimental results show that streaming speed is up to 250 KBps. The subjective quality assessments show that the received images are smooth during the streaming period. In addition, in terms of the objective image quality evaluation the average peak signalto- noise ratio of the reconstructed images is measured to be 39.19 dB which reveals high quality of images.
Nguyen, H.H., Nguyen, T.N., Clout, R. & Nguyen, H.T. 2015, 'A novel target following solution for the electric powered hospital bed', 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Engineering in Medicine and Biology Society (EMBC), IEEE, Milano, Italy, pp. 3569-3572.
View/Download from: UTS OPUS or Publisher's site
The paper proposes a novel target following solution for an electric powered hospital bed. First, an improved real-time decoupling multivariable control strategy is introduced to stabilize the overall system during its operation. Environment laser-based data are then collected and pre-processed before engaging a neural network classifier for target detection. Finally, a high-level control algorithm is implemented to guarantee safety condition while the hospital bed tracks its target. The proposed solution is successfully validated through real-time experiments.
Roxby, D.N., Tran, N., Yu, P.L. & Nguyen, H.T. 2015, 'Experimenting with Microbial Fuel Cells for Powering Implanted Biomedical Devices', Engineering in Medicine and Biology Conference 2015, IEEE, Milan, Italy, pp. 2685-2688.
View/Download from: UTS OPUS or Publisher's site
Microbial Fuel Cell (MFC) technology has the ability to directly convert sugar into electricity by using bacteria. Such a technology could be useful for powering implanted biomedical devices that require a surgery to replace their batteries every couple of years. In steps towards this, parameters such as electrode configuration, inoculation size, stirring of the MFC and single versus dual chamber reactor configuration were tested for their effect on MFC power output. Results indicate that a Top-Bottom electrode configuration, stirring and larger amounts of bacteria in single chamber MFCs, and smaller amounts of bacteria in dual chamber MFCs give increased power outputs. Finally, overall dual chamber MFCs give several fold larger MFC power outputs.
Nguyen, T. & Nguyen, H. 2015, 'Neural Network Decoupling technique and its application to a powered wheelchair system', Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, The 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Milano, Italy, pp. 4586-4589.
View/Download from: UTS OPUS or Publisher's site
This paper proposes a neural network decoupling technique for an uncertain multivariable system. Based on a linear diagonalization technique, a reference model is designed using nominal parameters to provide training signals for a neural network decoupler. A neural network model is designed to learn the dynamics of the uncertain multivariable system in order to avoid required calculations of the plant Jacobian. To avoid overfitting problem, both neural networks are trained by the Lavenberg-Marquardt with Bayesian regulation algorithm that uses a real-time recurrent learning algorithm to obtain gradient information. Three experimental results in the powered wheelchair control application confirm that the proposed technique effectively minimises the coupling effects caused by input-output interactions even under the condition of system uncertainties.
Chai, R., Naik, G., Tran, Y., Ling, S., Craig, A. & Nguyen, H.T. 2015, 'Classification of Driver Fatigue in an Electroencephalography-Based Countermeasure System with Source Separation Module', Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2015 (EMBC 2015), The 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2015 (EMBC 2015), IEEE, Milano, Italy, pp. 514-517.
View/Download from: UTS OPUS or Publisher's site
An electroencephalography (EEG)-based counter measure device could be used for fatigue detection during driving. This paper explores the classification of fatigue and alert states using power spectral density (PSD) as a feature extractor and fuzzy swarm based-artificial neural network (ANN) as a classifier. An independent component analysis of entropy rate bound minimization (ICA-ERBM) is investigated as a novel source separation technique for fatigue classification using EEG analysis. A comparison of the classification accuracy of source separator versus no source separator is presented. Classification performance based on 43 participants without the inclusion of the source separator resulted in an overall sensitivity of 71.67%, a specificity of 75.63% and an accuracy of 73.65%. However, these results were improved after the inclusion of a source separator module, resulting in an overall sensitivity of 78.16%, a specificity of 79.60% and an accuracy of 78.88% (p < 0.05).
Chai, R., Smith, M.R., Nguyen, T.N., Ling, S.H., Coutts, A.J. & Nguyen, H.T. 2015, 'Comparing Features Extractors in EEG-Based Cognitive Fatigue Detection of Demanding Computer Tasks', Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2015 (EMBC 2015), The 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2015 (EMBC 2015), IEEE, Milano, Italy, pp. 7594-7597.
View/Download from: UTS OPUS or Publisher's site
An electroencephalography (EEG)-based classification system could be used as a tool for detecting cognitive fatigue from demanding computer tasks. The most widely used feature extractor in EEG-based fatigue classification is power spectral density (PSD). This paper investigates PSD and three alternative feature extraction methods, in order to find the best feature extractor for the classification of cognitive fatigue during cognitively demanding tasks. These compared methods are power spectral entropy (PSE), wavelet, and autoregressive (AR). Bayesian neural network was selected as the classifier in this study. The results showed that the use of PSD and PSE methods provide an average accuracy of 60% for each computer task. This finding is slightly improved using the wavelet method which has an average accuracy of 61%. The AR method is the best feature extractor compared with the PSD, PSE and wavelet in this study with accuracy of 75.95% in AX continuous performance test (AX-CPT), 75.23% in psychomotor vigilance test (PVT) and 76.02% in Stroop task (p-value < 0.05).
Truong, B.A.O., Hoang, T.U.A.N., Fitzgerald, A.J., Wallace, V.P., Nguyen, T. & Nguyen, H.U.N.G. 2015, 'Breast Cancer Classification Using Extracted Parameters from a Terahertz Dielectric Model of Human Breast Tissue', Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2015 (EMBC 2015), The 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2015 (EMBC 2015), IEEE, Milano, Italy, pp. 2804-2807.
View/Download from: UTS OPUS or Publisher's site
Our previous study proposed a dielectric model for human breast tissue and provided initial analysis of classification potential of the eight model parameters and their multiparameter combinations with the support vector machine (SVM). A combination of three model parameters could achieve a leave-one-out cross validation accuracy of 93.2%. However, the SVM approach fails to exploit the combinations of more than three model parameters for classification improvement. Thus, the Bayesian neural network (BNN) method is employed to overcome this problem based on its advantages of handling our small data and high complexity of the multiparamter combinations. The BNN successfully classifies the data using the combinations of four model parameters with an accuracy, estimated by leave-one-out cross validation, of 97.3%. Overall performance assessed by leaveone-out and repeated random-subsampling cross validations for all examined combinations is also remarkably improved by BNN. The results indicate the advance of BNN as compared to SVM in utilising the model parameters for detecting tumour from normal breast tissue.
Ho-Le, T.P., Center, J.R., Eisman, J.A., Nguyen, H.T. & Nguyen, T.V. 2015, 'POLYGENIC RISK SCORE IMPROVES FRACTURE RISK PREDICTION: THE DUBBO OSTEOPROROSIS EPIDEMIOLOGY STUDY', 25th Annual Scientific Meeting of the Australian New Zealand Bone and Mineral Society, Tasmania.
Many genes for bone mineral density (BMD) have been identified in genomewide association studies. However, the contribution of these genes for fracture prediction is still unclear. This study sought to develop clinico-genetic models for predicting fracture risk in the elderly. The study was part of the Dubbo Osteoporosis Epidemiology Study, in which bone health of participants aged from 60 years had been monitored continuously since 1990. Fragility fracture was ascertained from X-ray reports. Femoral neck BMD was measured by dual-energy X-ray absorptiometry. Seventy-one BMD-associated genetic variants were genotyped. A weighted polygenic risk score (GRS) was derived from the variants. Three fracture risk models were constructed: (1) clinical factors only, (2) clinical factors and GRS, or (3) clinical factors and 71 variants. During the follow-up period, 230 fracture cases (36.4%) were observed. Each score increase in GRS was associated with an odds ratio of 1.47 (95%CI, 1.28 to 1.69) of fracture. The area under the curve (AUC) of model 1 (with age, sex, BMD, prior fracture, and fall) was 0.71 (95%CI, 0.67 to 0.75); when GRS was added to the model (P<0.001), the AUC was increased to 0.74 (95%CI, 0.70 to 0.78). When all 71 variants were considered together with the clinical risk factors, the AUC was increased to 0.78 (95%CI, 0.74 to 0.82), and net reclassification index was improved by 22%. These results indicate that BMD-associated genes could improve the performance of fracture prediction over and above that of clinical risk factors alone, and help stratify individuals by fracture status.
Pendharkar, G., Naik, G.R., Acharyya, A. & Nguyen, H.T. 2015, 'Multiscale PCA to distinguish regular and irregular surfaces using tri axial head and trunk acceleration signals', Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE, Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE, IEEE, Milan, Italy, pp. 4122-4125.
View/Download from: UTS OPUS or Publisher's site
This study uses multiscale principal component analysis (MSPCA) signal processing technique in order to distinguish the two different surfaces, tiled (regular) and cobbled (irregular) using accelerometry data (recorded from MTx sensors). Two MTx sensors were placed on the head and trunk of the subject while the subject walked freely over the regular and irregular surfaces during a free walk. 3D acceleration signals, vertical, medio lateral (ML) and anterior-posterior (AP) were recorded for the head and trunk segments and compared for the free walk on a defined route. The magnitude of the ML and AP acceleration obtained from the MTx sensors (for both head & trunk) was higher when walking over the irregular (cobbled) surface as compared to the regular (tiled) surface. The accelerometry data was initially analysed using MSPCA and was later classified using naive Bayesian classifier with >86% accuracy. This research study demonstrates that MSPCA can be used to distinguish the regular and irregular surfaces. The proposed method could be very useful as an automated method for classification of the two surfaces.
Argha, A., Li, L., Su, S. & Nguyen, H. 2015, 'Robust Output-feedback Discrete-Time Sliding Mode Control Utilizing Disturbance Observer', Proceedings of the 2015 54th IEEE Conference on Decision and Control (CDC), 54th IEEE Conference on Decision and Control, IEEE, Osaka, Japan, pp. 5671-5676.
View/Download from: UTS OPUS or Publisher's site
This paper is devoted to the problem of designing a robust dynamic output-feedback discrete-time sliding mode controller (ODSMC) for uncertain discrete-time systems. The basic idea behind this scheme comes from the fact that output feedback discrete-time sliding mode control (ODSMC), unlike its continuous-time counterpart, does not require to exploit a discontinuous term including the sliding function. Therefore, it is not a vital requirement that the sliding function is expressed in terms of the system outputs only. Furthermore, our observerbased discrete-time sliding mode controller (DSMC) leads to a considerably larger region of applicability. Besides, with the assumption of dealing with slow exogenous disturbances, a methodology is developed which aims to reduce the thickness of the boundary layer around the sliding surface. Moreover, the boundedness of the obtained closed-loop system is analyzed and the bound on the underlying system state is derived.
Argha, A., Su, S.W., Nguyen, H. & Celler, B.G. 2015, 'Designing adaptive integral sliding mode control for heart rate regulation during cycle-ergometer exercise using bio-feedback', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 6688-6691.
View/Download from: UTS OPUS or Publisher's site
&copy; 2015 IEEE. This paper considers our developed control system which aims to regulate the exercising subjects' heart rate (HR) to a predefined profile. The controller would be an adaptive integral sliding mode controller. Here it is assumed that the controller commands are interpreted as biofeedback auditory commands. These commands can be heard and implemented by the exercising subject as a part of the control-loop. However, transmitting a feedback signal while the pedals are not in the appropriate position to efficiently exert force may lead to a cognitive disengagement of the user from the feedback controller. To address this problem this paper will employ a different form of control system regarding as 'actuator-based event-driven control system'. This paper will claim that the developed event-driven controller makes it possible to effectively regulate HR to a predetermined HR profile.
Argha, A., Su, S.W., Nguyen, H. & Celler, B.G. 2015, 'Heart Rate Regulation During Cycle-Ergometer Exercise via Bio-Feedback', Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, Milan Italy, pp. 4639-4642.
View/Download from: UTS OPUS or Publisher's site
This paper explains our developed control system which regulates the heart rate (HR) to track a desired trajectory. The controller is indeed a non-conventional non-model-based proportional, integral and derivative (PID) controller. The controller commands are interpreted as biofeedback auditory commands. These commands can be heard and implemented by the exercising subject as a part of the control-loop. However, transmitting a feedback signal while the pedals are not in the appropriate position to efficiently exert force may lead to a cognitive disengagement of the user from the feedback controller. This note explains a novel form of control system regarding as 'actuator-based event-driven control system, designed specifically for the purpose of this project. We conclude that the developed event-driven controller makes it possible to precisely regulate HR to a predetermined HR profile.
Su, S.W., Tuan, H.D., Chen, W., Nguyen, H.T. & Celler, B.G. 2016, 'Conditions for simultaneous decentralized integral controllability', Proceedings of the 2015 Australian Control Conference, Australian Control Conference (AUCC), IEEE, Gold Coast, Australia, pp. 144-147.
&copy; 2015 Engineers Australia. This paper explores the designing of a decentralized integral controller to simultaneously ensure closed loop decentralized unconditional stability for a set of multi-variable models. If such a controller exists, then the set of models is considered as Simultaneously Decentralized Integral Controllable (SDIC). We provide an sufficient SDIC condition under which an approach is given to simultaneously achieve closed loop decentralized unconditional stability.
Handojoseno, A.M., Shine, J.M., Nguyen, T.N., Gilat, M., Tran, Y.H., Lewis, S. & Nguyen, H.T. 2014, 'Prediction of Freezing of Gait Using Analysis of Brain Effective Connectivity', Proceeding of the 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Chicago, Illinois, USA, pp. 4119-4122.
View/Download from: UTS OPUS
Freezing of gait (FOG) is a debilitating symptom of Parkinsons disease (PD), in which patients experience sudden difficulties in starting or continuing locomotion. It is described by patients as the sensation that their feet are suddenly glued to the ground. This, disturbs their balance, and hence often leads to falls. In this study, directed transfer function (DTF) and partial directed coherence (PDC) were used to calculate the effective connectivity of neural networks, as the input features for systems that can detect FOG based on a Multilayer Perceptron Neural Network, as well as means for assessing the causal relationships in neurophysiological neural networks during FOG episodes. The sensitivity, specificity and accuracy obtained in subject dependent analysis were 82%, 77%, and 78%, respectively. This is a significant improvement compared to previously used methods for detecting FOG, bringing this detection system one step closer to a final version that can be used by the patients to improve their symptoms.
Chai, R., Tran, Y.H., Craig, A., Ling, S.S. & Nguyen, H.T. 2014, 'Enhancing Accuracy of Mental Fatigue Classification using Advanced Computational Intelligence in an Electroencephalography System', The 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, The 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Chicago, pp. 1338-1341.
View/Download from: UTS OPUS
A system using electroencephalography (EEG) signals could enhance the detection of mental fatigue while driving a vehicle. This paper examines the classification between fatigue and alert states using an autoregressive (AR) model-based power spectral density (PSD) as the features extraction method and fuzzy particle swarm optimization with cross mutated of artificial neural network (FPSOCM-ANN) as the classification method. Using 32-EEG channels, results indicated an improved overall specificity from 76.99% to 82.02%, an improved sensitivity from 74.92 to 78.99% and an improved accuracy from 75.95% to 80.51% when compared to previous studies. The classification using fewer EEG channels, with eleven frontal sites resulted in 77.52% for specificity, 73.78% for sensitivity and 75.65% accuracy being achieved. For ergonomic reasons, the configuration with fewer EEG channels will enhance capacity to monitor fatigue as there is less set-up time required.
Nguyen, H.H., Nguyen, T.N., Clout, R. & Nguyen, H.T. 2014, 'An advanced control strategy of an electrical-powered hospital bed', Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE, IEEE, Chicago, USA, pp. 1190-1193.
View/Download from: UTS OPUS or Publisher's site
This paper develops a multivariable control technique for low-level control of an intelligent hospital bed. First, multivariable hospital bed models, nominal, upper bounded and lower bounded models, are obtained via an experimental identification procedure. Based on the obtained nominal model, the triangular diagonal dominance (TDD) decoupling technique is applied to reduce a complex multivariable system into a series of scalar systems. For each scalar system, an online adaptive control strategy is then developed to cope with system uncertainties. Compared to the conventional control method, real-time experimental results showed that our proposed multivariable control technique achieved better performance. Experimental results also confirmed that desirable system performance was guaranteed under system uncertainty conditions.
Naik, G.R., Acharyya, A. & Nguyen, H.T. 2014, 'Classification of finger extension and flexion of EMG and Cyberglove data with modified ICA weight matrix', Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, Chicago, USA, pp. 3829-3832.
View/Download from: UTS OPUS or Publisher's site
Argha, A., Su, S.W., Lee, S., Nguyen, H.T. & Celler, B.G. 2014, 'On Heart Rate Regulation in Cycle-Ergometer Exercise', http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6944350, The 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'14), IEEE, Chicago USA, pp. 3390-3393.
View/Download from: UTS OPUS or Publisher's site
In this paper, we have focused on the issue of regulating the human heart rate (HR) to a predefined reference trajectory, especially for cycle-ergometer exercise used for training or rehabilitation. As measuring HR is relatively easy compared to exercise intensity, it has been used in the wide range of training programs. The aim of this paper is to develop a non-model-based control strategy using proportional, integral and derivative (PID) controller/relay controller to regulate the HR to track a desired trajectory. In the case of using PID controller, the controller output signal is interpreted as a voice or auditory command, referred to as biofeedback, which can be heard by the exercising subject as a part of the controlloop. Alternatively, the relay controller output signals can be converted to some special words which can be recognised by the exerciser. However, in both cases, to effectively communicate to the user a change in exercise intensity, the timing of this feedback signal relative to the positions of the pedals becomes quite critical. A feedback signal delivered when the pedals are not in a suitable position to efficiently exert force may be ineffective and may lead to a cognitive disengagement of the user form the feedback controller. In this paper we examine the need and the consequence of synchronising the delivery of the feedback signal with an optimal and user specific placement of the pedal.
Argha, A., Li, L., Su, S.W. & Nguyen, H.T. 2014, 'Decentralized Sliding Mode Control for Uncertain Discrete-Time Large-Scale Systems: An LMI Approach', Australian Control Conference 2014, Canberra Australia.
View/Download from: UTS OPUS
In this paper, a decentralized discrete-time sliding mode control is designed for the uncertain large-scale systems. Firstly, a decentralized sliding surface is developed for the largescale discrete-time systems including uncertainty and exogenous disturbance. Then, a decentralized sliding mode controller is designed for the underlying systems. An LMI approach is deployed to develop a new framework to design the decentralized sliding mode controller which can stabilize the underlying uncertain large-scale system. The ultimate boundedness of the state and sliding function of the underlying closed-loop system is studied accordingly. Illustrative examples are presented to show the effectiveness of the proposed controllers.
Argha, A., Li, L., Su, S. & Nguyen, H.T. 2014, 'Controllability Analysis of the First FM Model of 2D Systems: A Row (Column) Process', Proceedings of the 53rd IEEE Conference on Decision and Control, The 53rd IEEE Conference on Decision and Control, IEEE, Los Angeles - USA, pp. 2414-2419.
View/Download from: UTS OPUS or Publisher's site
Dealing with 1D form of 2D systems is an alternative strategy to reduce the intrinsic complexity of 2D systems and their applications. To obtain the 1D form of 2D systems, a row (column) process is used in this paper. The controllability analysis of the obtained 1D form and its relation to the local controllability of the local states in the original 2D system is the subject of this paper. Moreover, in this paper, a new notion of controllability named directional controllability is defined and studied for the underlying 2D systems.
Argha, A., Li, L., Su, S. & Nguyen, H.T. 2014, 'A New LMI-Based Robust Sliding Mode Control for the Uncertain Discrete-Time Systems', Proceedings of the 53rd IEEE Conference on Decision and Control, The 53rd IEEE Conference on Decision and Control (CDC 2014), IEEE, Los Angeles - USA, pp. 4747-4752.
View/Download from: UTS OPUS or Publisher's site
In this paper, a new approach for designing a robust Discrete-time Sliding Mode Control (DSMC) is proposed for the uncertain discrete-time systems. To this end, an LMI approach is used to develop a new framework to design the linear sliding functions which are linear to the state. The LMI approach proposed in this paper is designed to deal with uncertain systems (matched and unmatched). It is wellknown that the finite sampling rate for the discrete-time systems leads to this fact that state move within a bound around the predetermined sliding surface referred to as quasi-sliding mode band. In this paper, this matter will be discussed in a new point of view and an innovative method will be used to obtain the ultimate bound on the system state.
Roxby, D.N., Tran, N. & Nguyen, H.T. 2014, 'A Simple Microbial Fuel Cell Model for Improvement of BiomedicalDevice Powering Times', Engineering in Medicine and Biology Conference 2014, Institute of Electrical and Electronics Engineers ( IEEE ), Sheraton Chicago Towers and Hotel, Chicago, United States of America.
View/Download from: UTS OPUS
This study describes a Matlab based Microbial Fuel Cell (MFC) model for a suspended microbial population, in the anode chamber for the use of the MFC in powering biomedical devices. The model contains three main sections including microbial growth, microbial chemical uptake and secretion and electrochemical modeling. The microbial growth portion is based on a Continuously Stirred Tank Reactor (CSTR) model for the microbial growth with substrate and electron acceptors. Microbial stoichiometry is used to determine chemical concentrations and their rates of change and transfer within the MFC. These parameters are then used in the electrochemical modeling for calculating current, voltage and power. The model was tested for typically exhibited MFC characteristics including increased electrode distances and surface areas, overpotentials and operating temperatures. Implantable biomedical devices require long term powering which is the main objective for MFCs. Towards this end, our model was tested with different initial substrate and electron acceptor concentrations, revealing a four-fold increase in concentrations decreased the power output time by 50%. Additionally, the model also predicts that for a 35.7% decrease in specific growth rate, a 50% increase in power longevity is possible.
Ling, S.H., San, P.P., Lam, H.K., Nguyen, H.T. & IEEE 2014, 'Non-invasive Detection of Hypoglycemic Episodes in Type1 Diabetes Using Intelligent Hybrid Rough Neural System', 2014 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), pp. 1238-1242.
View/Download from: UTS OPUS
San, P.P., Ling, S.S., Soe, N.N. & Nguyen, H.T. 2014, 'A novel extreme learning machine for hypoglycemia detection', 36nd Annual International conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Chicago, pp. 302-305.
View/Download from: UTS OPUS or Publisher's site
Truong, B.C., Hoang, T.D., Fitzgerald, A.J., Wallace, V.P. & Nguyen, H.T. 2014, 'High Correlation of Double Debye Model Parameters in Skin Cancer Detection', Conf Proc IEEE Eng Med Biol Soc, 36th Annual International Conference of IEEE Engineering in Medicine and Biology Society (EMBC 2014), IEEE, Chicago, US, pp. 718-721.
View/Download from: UTS OPUS or Publisher's site
The double Debye model can be used to capture the dielectric response of human skin in terahertz regime due to high water content in the tissue. The increased water proportion is widely considered as a biomarker of carcinogenesis, which gives rise of using this model in skin cancer detection. Therefore, the goal of this paper is to provide a specific analysis of the double Debye parameters in terms of non-melanoma skin cancer classification. Pearson correlation is applied to investigate the sensitivity of these parameters and their combinations to the variation in tumor percentage of skin samples. The most sensitive parameters are then assessed by using the receiver operating characteristic (ROC) plot to confirm their potential of classifying tumor from normal skin. Our positive outcomes support further steps to clinical application of terahertz imaging in skin cancer delineation.
Ghosh, S., Feng, M., Nguyen, H. & Li, J. 2014, 'Predicting Heart Beats using Co-occurring Constrained Sequential Patterns', http://www.cinc.org/archives/2014/, Computing in Cardiology, IEEE, Boston USA, pp. 265-268.
View/Download from: UTS OPUS
The aim of this study is to develop and evaluate a robust method for heart beat detection using a sequential pattern mining framework, based on the multi-modal Physionet 2014 challenge dataset. Each multi-modal patient time series was initially transformed to a symbolic sequence using Symbolic Aggregation Approximation (SAX). A training set was created, by randomly selecting 70% of the data and the rest 30% was used as the test set. Later, all segments of length 100 were extracted, for annotated beat occurrences. Subsequently, an algorithm was used to extract repetitive frequent subsequences, where consecutive symbols are separated by a pre-defined gap range. The patterns for ECG and BP were then ranked based on length and frequency support. For tests, the highest ranked patterns were used to mark beat segments. True beat occurrences were only considered when patterns co-occurred for both ECG and BP within a width of 150 time points. Our results comprise two parts viz. extracted top ranked sequences and gross test statistics. An interpretive highest ranked sequential pattern for ECG looks like [7,7,7,5,5,5,5,5,4,3,10,10,10,2,2,3,3,4,3,4,5,5,5,6,7], for 10 discrete symbols which identify regional signal activity, with a gap range of [2,4] between contiguous elements. As per our test results, the method gives us a sensitivity of 51.66% and a positive predictivity (PPV) of 67.15%. The novelty of mining gap constrained co-occurring frequent sequential patterns lies in its ability to capture approximate co-occurring long clinical episodes across multiple variables, even if the quality of one signal suffers for a certain period of time. A higher PPV indicates that our method did not have a lot of false positives (detecting non-beats). The method is still being improved and will be further tested in the next stages of the Ph
Ghosh, S., Feng, M., Nguyen, H. & Li, J. 2014, 'Risk Prediction for Acute Hypotensive Patients by using Gap Constrained Sequential Contrast Patterns', http://knowledge.amia.org/56638-amia-1.1540970/t-004-1.1544972?qr=1, American Medical Informatics Association (AMIA) 2014 Annual Symposium, AMIA, Washington D.C., USA.
View/Download from: UTS OPUS
Tareef, A., Al-Ani, A., Nguyen, H. & Chung, Y.Y. 2014, 'A novel tamper detection-recovery and watermarking system for medical image authentication and EPR hiding', 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE Engineering in Medicine and Biology Society Conference (EMBC), IEEE, Chicago, USA, pp. 5554-5557.
View/Download from: UTS OPUS
Recently, the literature has witnessed an increasing interest in the study of medical image watermarking and recovery techniques. In this article, a novel image tamper localization and recovery technique for medical image authentication is proposed. The sparse coding of the Electronic Patient Record (EPR) and the reshaped region of Interest (ROI) is embedded in the transform domain of the Region of Non-Interest (RONI). The first part of the sparse coded watermark is use for saving the patient information along with the image, whereas the second part is used for authentication purpose. When the watermarked image is tampered during transmission between hospitals and medical clinics, the embedded sparse coded ROI can be extracted to recover the tampered image. The experimental results demonstrate the efficiency of the proposed technique in term of tamper correction capability, robustness to attacks, and imperceptibility.
Al-Dmour, H., Al-Ani, A. & Nguyen, H. 2014, 'An efficient steganography method for hiding patient confidential information', 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE Engineering in Medicine and Biology Society Conference (EMBC), IEEE, Chicago, USA, pp. 222-225.
View/Download from: UTS OPUS
This paper deals with the important issue of security and confidentiality of patient information when exchanging or storing medical images. Steganography has recently been viewed as an alternative or complement to cryptography, as existing cryptographic systems are not perfect due to their vulnerability to certain types of attack. We propose in this paper a new steganography algorithm for hiding patient confidential information. It utilizes Pixel Value Differencing (PVD) to identify contrast regions in the image and a Hamming code that embeds 3 secret message bits into 4 bits of the cover image. In order to preserve the content of the region of interest (ROI), the embedding is only performed using the Region of Non-Interest (RONI).
Tran, Y., Thuraisingham, R., Wijesuriya, N., Craig, A. & Nguyen, H.T. 2014, 'Using S-transform in EEG analysis for measuring an alert versus mental fatigue state', 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, Chicago, IL, pp. 5880-5883.
View/Download from: UTS OPUS
This paper presents research that investigated the effects of mental fatigue on brain activity using electroencephalogram (EEG) signals. Since EEG signals are considered to be non-stationary, time-frequency analysis has frequently been used for analysis. The S-transform is a time-frequency analysis method and is used in this paper to analyze EEG signals during alert and fatigue states during a driving simulator task. Repeated-measure MANOVA results show significant differences between alert and fatigue states within the alpha (8-13Hz) frequency band. The two sites demonstrating the greatest increases in alpha activity during fatigue were the Cz and P4 sites. The results show that S-transform analysis can be used to distinguish between alert and fatigue states in the EEG and also supports the use of the S-transform for EEG analysis.
Nguyen, L.L., Su, S. & Nguyen, H.T. 2014, 'Neural network approach for non-invasive detection of hyperglycemia using electrocardiographic signals', 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, Chicago, IL, pp. 4475-4478.
View/Download from: UTS OPUS or Publisher's site
Hyperglycemia or high blood glucose (sugar) level is a common dangerous complication among patients with Type 1 diabetes mellitus (T1DM). Hyperglycemia can cause serious health problems if left untreated such as heart disease, stroke, vision and nerve problems. Based on the electrocardiographic (ECG) parameters, we have identified hyperglycemic and normoglycemic states in T1DM patients. In this study, a classification unit is introduced with the approach of feed forward multi-layer neural network to detect the presences of hyperglycemic/normoglycemic episodes using ECG parameters as inputs. A practical experiment using the real T1DM patients' data sets collected from Department of Health, Government of Western Australia is studied. Experimental results show that proposed ECG parameters contributed significantly to the good performance of hyperglycemia detections in term of sensitivity, specificity and geometric mean (70.59%, 65.38%, and 67.94%, respectively). From these results, it is proved that hyperglycemic events in T1DM can be detected non-invasively and effectively by using ECG signals and ANN approach.
Wang, C., Savkin, A.V., Clout, R. & Nguyen, H.T. 2014, 'A method for collision free navigation of a robotic hospital bed among steady and moving obstacles', 2014 IEEE Conference on Control Applications (CCA), IEEE Conference on Control Applications, Juan Les Antibes, pp. 1058-1063.
View/Download from: UTS OPUS or Publisher's site
We present a reactive navigation algorithm which ensures the safety of the hospital beds in the dynamic environments. The proposed navigation algorithm allows the hospital beds to avoid en-route obstacles with an efficient easy-to-compute sliding mode obstacle avoidance strategy when an obstacle is nearby, and move towards the target location at maximum speed when there is no threat of collision. We provide extensive computer simulation of the proposed navigation algorithm. More importantly, the experiment results with the designed mobile hospital bed in real world scenarios are also presented.
Yuwono, M., Su, S.W., Moulton, B.D., Guo, Y. & Nguyen, H.T. 2014, 'An algorithm for scalable clustering: Ensemble Rapid Centroid Estimation', 2014 IEEE Congress on Evolutionary Computation (CEC), IEEE Congress on Evolutionary Computation, IEEE, Beijing, pp. 1250-1257.
View/Download from: UTS OPUS or Publisher's site
This paper describes a new algorithm, called Ensemble Rapid Centroid Estimation (ERCE), designed to handle large-scale non-convex cluster optimization tasks, and estimate the number of clusters with quasi-linear complexity. ERCE stems from a recently developed Rapid Centroid Estimation (RCE) algorithm. RCE was originally developed as a lightweight simplification of the Particle Swarm Clustering (PSC) algorithm. RCE retained the quality of PSC, greatly reduced the computational complexity, and increased the stability. However, RCE has certain limitations with respect to complexity, and is unsuitable for non-convex clusters. The new ERCE algorithm presented here addresses these limitations.
Chai, R., Tran, Y., Craig, A., Ling, S.H. & Nguyen, H.T. 2014, 'Enhancing accuracy of mental fatigue classification using advanced computational intelligence in an electroencephalography system', 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014, pp. 1318-1341.
View/Download from: UTS OPUS or Publisher's site
&copy; 2014 IEEE. A system using electroencephalography (EEG) signals could enhance the detection of mental fatigue while driving a vehicle. This paper examines the classification between fatigue and alert states using an autoregressive (AR) model-based power spectral density (PSD) as the features extraction method and fuzzy particle swarm optimization with cross mutated of artificial neural network (FPSOCM-ANN) as the classification method. Using 32-EEG channels, results indicated an improved overall specificity from 76.99% to 82.02%, an improved sensitivity from 74.92 to 78.99% and an improved accuracy from 75.95% to 80.51% when compared to previous studies. The classification using fewer EEG channels, with eleven frontal sites resulted in 77.52% for specificity, 73.78% for sensitivity and 75.65% accuracy being achieved. For ergonomic reasons, the configuration with fewer EEG channels will enhance capacity to monitor fatigue as there is less set-up time required.
Zhou, J., Guo, A., Xu, J., Nguyen, H. & Su, S. 2014, 'A game theory control scheme in medium access for wireless body area network', IET Seminar Digest, pp. 404-409.
View/Download from: Publisher's site
Wireless Body Area Network (WBAN) has been considered for applications in medical, healthcare and sports fields. Although there are several protocols for wireless personal area networks, specific features and reliability requirements in WBAN bring new challenges in protocol design. An appropriate control scheme in the MAC layer can make a significant improvement in network performance. Based on traffic priority and prior knowledge this paper proposes a game theoretical framework to smartly control access in contention period and contention free period as defined in IEEE 802.15.6 standard. The coordinator controls access probability of contention period based on users' priority in CSMA/CA and allocates suitable slots with strategies for best payoff based on link states in guaranteed time slots (GTS). The simulation results show the improved performance especially in heavily loaded channel condition when the optimal control mode is applied.
Nguyen, L., Nguyen, V., Ling, S.S. & Nguyen, H.T. 2013, 'Analyzing EEG Signals under Insulin-induced Hypoglycemia in Type 1 Diabetes Patients', Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 35th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Osaka, Japan, pp. 1980-1983.
View/Download from: UTS OPUS or Publisher's site
Hypoglycemia is dangerous and considered as a limiting factor of the glycemic control therapy for patients with type 1 diabetes mellitus (T1DM). Nocturnal hypoglycemia is especially feared because early warning symptoms are unclear during sleep so an episode of hypoglycemia may lead to a fatal effect on patients. The main objective of this paper is to explore the correlation between hypoglycemia and electroencephalography (EEG) signals. To do this, the EEG of five T1DM adolescents from an overnight insulin-induced study is analyzed by spectral analysis to extract four different parameters. We aim to explore the response of these parameters during the clamp study which includes three main phases of normal, hypoglycemia and recovery. We also look at data at the blood glucose level (BGL) of 3.3-3.9 mmol/l to find a threshold to distinguish between non-hypoglycemia and hypoglycemia states. The results show that extracted EEG parameters are highly correlated with patients' conditions during the study. It is also shown that at the BGL of 3.3 mmol/l, responses to hypoglycemia in EEG signals start to significantly occur.
Chai, R., Ling, S.S., Hunter, G., Tran, Y.H. & Nguyen, H.T. 2013, 'Classification of wheelchair commands using brain computer interface: comparison between able-bodied persons and patients with tetraplegia', Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 35th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Osaka, Japan, pp. 989-992.
View/Download from: UTS OPUS or Publisher's site
This paper presents a three-class mental task classification for an electroencephalography based brain computer interface. Experiments were conducted with patients with tetraplegia and able bodied controls. In addition, comparisons with different time-windows of data were examined to find the time window with the highest classification accuracy. The three mental tasks used were letter composing, arithmetic and imagery of a Rubiks cube rolling forward; these tasks were associated with three wheelchair commands: left, right and forward, respectively. An eyes closed task was also recorded for the algorithms testing and used as an additional on/off command. The features extraction method was based on the spectrum from a Hilbert-Huang transform and the classification algorithm was based on an artificial neural network with a fuzzy particle swarm optimization with cross-mutated operation. The results show a strong eyes closed detection for both groups with average accuracy at above 90%. The overall result for the combined groups shows an improved average accuracy of 70.6% at 1s, 74.8% at 2s, 77.8% at 3s, 79.6% at 4s and 81.4% at 5s. The accuracy for individual groups were lower for patients with tetraplegia compared to the able-bodied group, however, does improve with increased duration of the time-window.
Guo, Y., Naik, G. & Nguyen, H.T. 2013, 'Single channel blind source separation based local mean decomposition for biomedical applications', Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 35th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Osaka, Japan, pp. 6812-6815.
View/Download from: UTS OPUS or Publisher's site
Single Channel Blind Source Separation (SCBSS) is an extreme case of underdetermined (more sources and fewer sensors) Blind Source Separation (BSS) problem. In this paper, we propose a novel technique using Local Mean Decomposition (LMD) and Independent Component Analysis (ICA) combined with single channel BSS (LMD_ICA). First, the LMD was used to decompose the single channel source into a series of data sequences, which are called as Product Functions (PF), then, ICA algorithm was used to process PFs to get similar independent components and extract the original signals. A comparison was made between LMD_ICA and previously proposed single channel ICA method (EEMD_ICA). The real time experimental results demonstrated the advantage of the proposed single channel source separation method for artifact removal and in biomedical source separation applications.
Nguyen, L., Nguyen, V., Ling, S.S. & Nguyen, H.T. 2013, 'Combining Genetic Algorithm and Levenberg-Marquardt Algorithm in Training Neural Network for Hypoglycemia Detection using EEG Signals', Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 35th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Osaka, Japan, pp. 5386-5389.
View/Download from: UTS OPUS or Publisher's site
Hypoglycemia is the most common but highly feared complication induced by the intensive insulin therapy in patients with type 1 diabetes mellitus (T1DM). Nocturnal hypoglycemia is dangerous because sleep obscures early symptoms and potentially leads to severe episodes which can cause seizure, coma, or even death. It is shown that the hypoglycemia onset induces early changes in electroencephalography (EEG) signals which can be detected non-invasively. In our research, EEG signals from five T1DM patients during an overnight clamp study were measured and analyzed. By applying a method of feature extraction using Fast Fourier Transform (FFT) and classification using neural networks, we establish that hypoglycemia can be detected efficiently using EEG signals from only two channels. This paper demonstrates that by implementing a training process of combining genetic algorithm and Levenberg-Marquardt algorithm, the classification results are improved markedly up to 75% sensitivity and 60% specificity on a separate testing set.
Nguyen, H., Nguyen, N., Clout, R.B., Gibson, A.J. & Nguyen, H.T. 2013, 'Development of an assistive patient mobile system for hospital environments', Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 35th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Osaka, Japan, pp. 2491-2494.
View/Download from: UTS OPUS or Publisher's site
This paper presents an assistive patient mobile system for hospital environments, which focuses on transferring the patient without nursing help. The system is a combination of an advanced hospital bed and an autonomous navigating robot. This intelligent bed can track the robot and routinely navigates and communicates with the bed. The work centralizes in building a structure, hardware design and robot detection and tracking algorithms by using laser range finder. The assistive patient mobile system has been tested and the real experiments are shown with a high performance of reliability and practicality. The accuracy of the method proposed in this paper is 91% for the targeted testing object with the error rate of classification by 6%. Additionally, a comparison between our method and a related one is also described including the comparison of results.
Truong, B.C., Hoang, T.D. & Nguyen, H.T. 2013, 'Near-Infrared Parameters Extraction: A Potential Method to Detect Skin Cancer', Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 35th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Osaka, Japan, pp. 33-36.
View/Download from: UTS OPUS or Publisher's site
The wavelength-dependent absorption coefficients can be used to analyse optical properties of human skin. Existing absorption models for narrow ranges in the visible and near infrared are insufficient to simultaneously incorporate the spectral contrast produced by differences in chromophores, water and lipid content of skin tissue into skin cancer detection. In the broad range up to 1600 nm, recent analysis approaches for absorption spectra do not consistently provide significant differences between healthy and cancerous skins. We propose an absorption model to fit the absorption coefficient spectra of skin samples over the range from 400 nm to 1600 nm and an advanced algorithm to find the optimal estimation. The extracted parameters of this model are analysed by a statistical t-test. The test results demonstrate the significant differences between all pairs of tumour-normal skin. Therefore, our approach has strong potential for early skin cancer detection using near infrared spectroscopy (NIRS).
Yuwono, M., Su, S.W., Moulton, B.D. & Nguyen, H.T. 2013, 'Unsupervised segmentation of heel-strike IMU dtata using rapid cluster estimation of wavelet features', Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 35th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, OSaka, Japan, pp. 953-956.
View/Download from: UTS OPUS or Publisher's site
When undertaking gait-analysis, one of the most important factors to consider is heel-strike (HS). Signals from a waist worn Inertial Measurement Unit (IMU) provides sufficient accelerometric and gyroscopic information for estimating gait parameter and identifying HS events. In this paper we propose a novel adaptive, unsupervised, and parameter-free identification method for detection of HS events during gait episodes. Our proposed method allows the device to learn and adapt to the profile of the user without the need of supervision. The algorithm is completely parameter-free and requires no prior fine tuning. Autocorrelation features (ACF) of both anteroposterior acceleration (aAP) and medio-lateral acceleration (aML) are used to determine cadence episodes. The Discrete Wavelet Transform (DWT) features of signal peaks during cadence are extracted and clustered using Swarm Rapid Centroid Estimation (Swarm RCE). Left HS (LHS), Right HS (RHS), and movement artifacts are clustered based on intra-cluster correlation. Initial pilot testing of the system on 8 subjects show promising results up to 84.3%9.2% and 86.7%6.9% average accuracy with 86.8%9.2% and 88.9%7.1% average precision for the segmentation of LHS and RHS respectively.
San, P., Ling, S.S. & Nguyen, H.T. 2013, 'Combinational neural logic system and its industrial application on hypoglycemia monitoring system', IEEE Conference on Industrial Electronics and Applications, ICIEA 2013, IEEE, Melbourne, Australia, pp. 947-952.
View/Download from: UTS OPUS or Publisher's site
In this paper, a combinational neural logic network (NLN) with the neural-Logic-AND, -OR and -NOT gates is applied on the development of non-invasive hypoglycemia monitoring system. It is an alarm system which measured physiological parameters of electrocardiogram (ECG) signal and determine the onset of hypoglycemia by use of proposed NLN. Due to different nature of application, conventional neural networks (NNs) with common structure may not always guarantee the optimal solution. Based on knowledge of application, the proposed NLN is designed systematically in order to incorporate the characteristics of application into the structure of proposed network. The parameter of the proposed NLN will be trained by hybrid particle swarm optimization with wavelet mutation (HPSOWM). The proposed NLN will be practically analyzed using real data sets collected from 15 children (569 data sets) with Type 1 diabetes at the Department of Health, Government of Western Australia. By using the proposed method, the detection performance is enhanced. Compared with other conventional NNs, the proposed NLN gives better performance in terms of sensitivity and specificity.
Handojoseno, A.M., Shine, J.M., Nguyen, N., Tran, Y.H., Lewis, S. & Nguyen, H.T. 2013, 'Using EEG Spatial Correlation, Cross Frequency Energy, and Wavelet Coefficients for the Prediction of Freezing of Gait in Parkinson's Disease Patients', Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 35th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Osaka, Japan, pp. 4263-4266.
View/Download from: UTS OPUS or Publisher's site
Parkinsons Disease (PD) patients with Freezing of Gait (FOG) often experience sudden and unpredictable failure in their ability to start or continue walking, making it potentially a dangerous symptom. Emerging knowledge about brain connectivity is leading to new insights into the pathophysiology of FOG and has suggested that electroencephalogram (EEG) may offer a novel technique for understanding and predicting FOG. In this study we have integrated spatial, spectral, and temporal features of the EEG signals utilizing wavelet coefficients as our input for the Multilayer Perceptron Neural Network and k-Nearest Neighbor classifier. This approach allowed us to predict transition from walking to freezing with 87 % sensitivity and 73 % accuracy. This preliminary data affirms the functional breakdown between areas in the brain during FOG and suggests that EEG offers potential as a therapeutic strategy in advanced PD.
Naik, G., Guo, Y. & Nguyen, H.T. 2013, 'A new approach to improve the quality of biosensor signals using fast independent component analysis: Feasibility study using EMG recordings', Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 35th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Osaka, Japan, pp. 1927-1929.
View/Download from: UTS OPUS or Publisher's site
The proposed signal processing technique uses Fast Independent Component Analysis (ICA) algorithm to improve the quality of the original biosensors recordings, which can be used as valuable pre-processing technique such as cross talk removal, artefact reduction etc. Initially, the ill conditioned original surface Electromyography (sEMG) recordings were separated using ICA methods and later they were reconstructed using modified un-mixing matrix. The simulation results showed huge improvement of the original recorded signal after reconstruction. The proposed method has potential applications in various biomedical signal processing techniques.
Nguyen, V., Nguyen, L., Su, S.W. & Nguyen, H.T. 2013, 'Shared Control Strategies for Human-Machine Interface in an Intelligent Wheelchair', Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 35th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Osaka, Japan, pp. 3638-3641.
View/Download from: UTS OPUS or Publisher's site
In this paper, we introduce a shared control mechanism for an intelligent wheelchair designed to support people with mobility impairments, who also have visual, upper limb, or cognitive impairment. The method is designed to allow users to be involved in the movement as much as possible, while still providing the assistance needed to achieve the goal safely. The data collected through URG-04LX and user interface are analyzed to determine whether the desired action is safe to perform. The system then decides to provide assistance or to allow the user input to control the wheelchair. The experiment results indicate that the method performs effectively with high satisfaction.
Nguyen, V., Nguyen, L., Su, S.W. & Nguyen, H.T. 2013, 'The Advancement of an Obstacle Avoidance Bayesian Neural Network for an Intelligent Wheelchair', Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 35th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Osaka, Japan, pp. 3642-3645.
View/Download from: UTS OPUS or Publisher's site
In this paper, an advanced obstacle avoidance system is developed for an intelligent wheelchair designed to support people with mobility impairments who also have visual, upper limb, or cognitive impairment. To avoid obstacles, immediate environment information is continuously updated with range data sampled by an on-board laser range finder URG-04LX. Then, the data is transformed to find the relevant information to the navigating process before being presented to a trained obstacle avoidance neural network which is optimized under the supervision of a Bayesian framework to find its structure and weight values. The experiment results showed that this method allows the wheelchair to avoid collisions while simultaneously navigating through an unknown environment in real-time. More importantly, this new approach significantly enhances the performance of the system to pass narrow openings such as door passing.
Nguyen, L., Su, S.W. & Nguyen, H.T. 2013, 'Effects of Hyperglycemia on Variability of RR, QT, and Corrected QT Intervals in Type 1 Diabetic Patients', Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 35th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Osaka, Japan, pp. 1819-1822.
View/Download from: UTS OPUS or Publisher's site
In this study, we evaluated the effects of hyperglycemia on the variability of RR (HRV), QT interval variability (QTV) and corrected QT interval variability (QTcV) during hyperglycemic and non-hyperglycemic conditions in six Type 1 diabetic patients at nights. The aim of this study was to investigate the association of high blood glucose levels with autonomic modulation of heart rate and variation in ventricular repolarization. Blood glucose level (BGL) threshold for defining hyperglycemia state was set at 8.33 mmol/l. Variability of RR, QT and corrected QT intervals during hyperglycemic and non-hyperglycemic were quantified using time and frequency domain measures. Hypomon&reg; device was used to monitor ECG signals and acquire RR and QT intervals in Type 1 diabetic patients overnight. The results indicated that time and frequency domain HRV variables were significantly decreased under hyperglycemic condition and inversely correlated with BGL. QTV parameters also reduced when BGL increased and time domain measures of QTV were inversely associated with BGL. Variability in QTc interval was much less than in the QT interval and demonstrated a lower SDNN and LF power. We concluded that certain components of HRV, time-domain measures of QTV and QTc but not QTcV are strongly correlated to high blood glucose levels and can be good markers to identify hyperglycemic events in T1DM.
Nguyen, J., Su, S.W. & Nguyen, H.T. 2013, 'Experimental Study on a Smart Wheelchair System using a Combination of Stereoscopic and Spherical Vision', Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 35th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Osaka, Japan, pp. 4597-4600.
View/Download from: UTS OPUS or Publisher's site
This paper is concerned with the experimental study performance of a smart wheelchair system named TIM (Thought-controlled Intelligent Machine), which uses a unique camera configuration for vision. Included in this configuration are stereoscopic cameras for 3-Dimensional (3D) depth perception and mapping ahead of the wheelchair, and a spherical camera system for 360-degrees of monocular vision. The camera combination provides obstacle detection and mapping in unknown environments during real-time autonomous navigation of the wheelchair. With the integration of hands-free wheelchair control technology, designed as control methods for people with severe physical disability, the smart wheelchair system can assist the user with automated guidance during navigation. An experimental study on this system was conducted with a total of 10 participants, consisting of 8 able-bodied subjects and 2 tetraplegic (C-6 to C-7) subjects. The hands-free control technologies utilized for this testing were a head-movement controller (HMC) and a braincomputer interface (BCI). The results showed the assistance of TIMs automated guidance system had a statistically significant reduction effect (p-value = 0.000533) on the completion times of the obstacle course presented in the experimental study, as compared to the test runs conducted without the assistance of TIM.
Argha, R., Su, S.W. & Nguyen, H.T. 2013, 'The Application of Discrete Sliding Mode Control in Parabolic PDE Dynamics', Proceedings of the Australian Control Conference 2013, Australian Control Conference 2013, IEEE, Perth, Australia, pp. 152-157.
View/Download from: UTS OPUS or Publisher's site
In this paper, the problem of applying Discrete Sliding Mode Control (DSMC) on spatially finite-dimensional systems arising from discretization of bi-variate Partial Differential Equations (PDEs) describing spatio-temporal systems is studied. To this end, heat transfer PDE is discretized to create 2D discrete dynamics and eventually this 2D spatiotemporal discrete form is represented in 1D vectorial form. In order to study the effect of discrepancy between original PDE dynamics and their discrete schemes, an uncertainty term is also considered for the obtained discrete dynamics. According to the notion of strong stability and, in addition, using scaling matrices (similarity transformation), a new method for considering the stability of discrete-time systems in the presence of general uncertainty term (matched and unmatched) is developed. It is also shown that the proposed method in this paper can be used for the case with spatial constraints on the actuation. Consequently, as special cases, the problem of spatially piecewise constant, sparse and also boundary control input are studied.
Su, S.W., Savkin, A., Celler, B.G. & Nguyen, H.T. 2013, 'A new unconditional stability criterion and its application on decentralized integral controllability analysis', Proceedings of the 32nd Chinese Control Conference (CCC), Chinese Control Conference, IEEE, Xi'an, China, pp. 119-122.
View/Download from: UTS OPUS
Decentralized integral control, such as multi-loop PI/PID control, is one of the most popular control strategies used in practice. An important issue associated with this strategy is the analysis of Decentralized Integral Controllability (DIC). Campo and Morari showed that for a process, if its steady state gain matrix is not critically D-stable, its DIC can be determined by using its steady state gain matrix only. This paper investigates decentralized integral control with a special focus on the DIC analysis of processes whose steady state gain matrices are critically D-stable. Firstly, this paper proposes a new unconditional stability criterion by using singular perturbation theory and eigenvalue sensitivity analysis, and shows that DIC analysis of such processes can be simplified by using unconditional stability analysis. Then, we presented a multi-loop PI control design method, which gives an explicit low bound of the proportional coefficient to achieve decentralized unconditional stability for 3 3 processes.
Kitoko, V., Nguyen, N. & Nguyen, H.T. 2013, 'An Electro-Mechanical Contact Formulation for Dry/Wet Electrode-Scalp Interfaces in an EEG Headset', The 10th IASTED International Conference on Biomedical Engineering, International Association of Science and Technology for Development International Conference on Biomedical Engineering, Acta Press, Innsbruck, Austria, pp. 199-206.
View/Download from: UTS OPUS or Publisher's site
The process of generating an initial prototype for a new dry electrode wearable EEG headset system design can be time and resource intensive. The ability to predict the mechanical and electrical characteristics of this recording device could lead to major cost savings in this process. Since the skin surface roughness has a deep impact on the decrease of brain electric contact conductance (or the increase of the contact impedance) when electrode with bristles contact scalp skin, the estimation of electric conductance across rough dry and wet boundaries is a challenging task in the designing optimization of the wearable EEG headset system. In this contribution, the contact mechanism to predict the electrical conductance of scalp skin pressed against the electrode is considered as the electrical connection by the mechanical contact. For mechanical contact analysis, a new normal force-displacement approach based on the micro-mechanical studies is developed for analyse of the non-linear electrode-skin contact interface problem with high contact precision. For the electrical contact conductance modelling, in this paper, we have extended the Pohrt and Popov model by including the effects of conductive gel. An experiment is developed and carried-out to validate the interfacial contact impedance model.
Wang, C., Matveev, A.S., Savkin, A.V., Nguyen, N. & Nguyen, H.T. 2013, 'A Collision Avoidance Strategy for Safe Autonomous Navigation of an Intelligent Electric-Powered Wheelchair in Dynamic Uncertain Environments with Moving Obstacles', Control Conference (ECC), 2013 European, European Control Conference, IEEE, Zurich Switzerland, pp. 4382-4387.
View/Download from: UTS OPUS
We present a reactive navigation algorithm that guarantees the safety of automated intelligent wheelchairs for people with mobility impairments in dynamic uncertain environments. The proposed navigation algorithm restricts neither the natures nor the motions of the obstacles, the shapes of the obstacles can be time-varying (deforming obstacles). Furthermore, the proposed navigation algorithm does not require prior information about the positions and velocities of the obstacles to accomplish obstacle avoidance. Simulation and experimental results show that intelligent electric-powered wheelchairs are able to successfully avoid collisions with moving obstacles such as pedestrians or vehicles under the guidance of the proposed algorithm and reach the target.
Hoang, T.D., Savkin, A.V., Nguyen, N. & Nguyen, H.T. 2013, 'Decentralised Model Predictive Control with Asymptotically Positive Realness', IEEE International Conference on Control and Automation (ICCA), IEEE International Conference on Control and Automation, IEEE, Hangzhou, China, pp. 822-827.
View/Download from: UTS OPUS or Publisher's site
This paper presents a novel distributed model predictive control strategy for a large-scale system consisting of interconnected subsystems. A constructive method of online stabilisation that is applicable to the model predictive controllers (MPC) is developed to facilitate the control strategy. The system stability is achievable by the newly introduced asymptotically positive realness constraint (APRC) for MPC. Simulations are provided to demonstrate the efficacy of the presented stability constraint.
Dehestani, D., Su, S.W., Nguyen, H.T. & Guo, Y. 2013, 'Robust Fault Tolerant Application for HVAC System Based on Combination of online SVM and ANN Black Box Model', 2013 European Control Conference, European Control Conference, IEEE, Zurich, Switzerland, pp. 2976-2981.
View/Download from: UTS OPUS
Efficient heating, ventilation, and air-conditioning (HVAC) systems are one of the big challenges today around the world. The fault detection and isolation (FDI) play a significant role in the monitoring, repairing and maintaining of technical systems for the final destination of cost reduction. FDI makes it possible to reduce total cost effective of maintenance and thus increase the capacity utilization rates of equipment. Reduction of energy wasting in the system by on time fault detection is another goal. Therefore, this work proposes a new fault detector based on a black box Artificial Neural Network (ANN) model and online support vector machines (SVM) classifier which integrates a dimension reduction scheme to analyze the failure of air fan supply and dampers fault. The key advantage of this algorithm is to make robustness for SVM to recognize a faulty condition with unexpected sensors values. The ANN generates a high accurate model which is based reference for SVM classifier. Now by using this black box model we make possibility of robustness for SVM to increase detection probability. Finally, a series of faulty experimental data are applied to evaluate the effectiveness of the robust classifier. Final results show that online SVM can detect accurately the air supply fan fault and damper fault of a HVAC system with minimum usage data. It is also outperforms offline SVM on such energy systems for classification.
Wang, C., Matveev, A.S., Savkin, A.V., Clout, R. & Nguyen, H.T. 2013, 'A real-time obstacle avoidance strategy for safe autonomous navigation of intelligent hospital beds in dynamic uncertain environments', Australasian Conference on Robotics and Automation, ACRA.
We present a reactive navigation algorithm for safe operation of hospital beds in dynamic environments. The proposed navigation is implementation efficient in the sense that it does not require any measurements from the velocities, shapes, dimensions or orientations of the obstacles. Furthermore, it is applicable for a variety of real world scenario where the natures and the motions of the obstacles are not known, and the shapes of the obstacles may be time-varying and deforming. The only information available for computation of control signals is the minimum distance from the hospital bed to the closest obstacle. The mathematically rigorous analysis of the proposed navigation algorithm is presented and its performance is demonstrated by the computer simulations and real world experiments with a hospital bed control system (Flexbed).
Savkin, A.V., Xi, Z. & Nguyen, H.T. 2013, 'An algorithm of decentralized encircling coverage and termination of a moving deformable region by mobile robotic sensor/actuator networks', 2013 9th Asian Control Conference, ASCC 2013.
View/Download from: Publisher's site
The paper introduces the problems of encircling coverage and termination of a moving a deformable planar region by a mobile sensor/actuator network. We propose a decentralized randomized algorithm for self-deployment of a network of mobile robotic sensors/actuators for these problems. In the encircling coverage problem, the aim is to deploy sensors around a bounded connected region so that any point of a certain neighbourhood of the region is sensed by at least one mobile robotic sensor. In the termination problem, the aim is to terminate a moving region that may represent an oil spill or a hazardous chemical field. In this case, the moving robots are equipped with not only sensors but with actuators releasing neutralizing chemical so that the shape of the polluted region is controlled. The proposed algorithm is based only on information about the closest neighbours of each sensor. The moving region is of an arbitrary shape and not known to the sensors a priori. We give mathematically rigorous proofs of asymptotic optimality and convergence with probability 1 of the proposed randomized algorithm. &copy; 2013 IEEE.
Savkin, A.V., Wang, C., Baranzadeh, A., Xi, Z. & Nguyen, H.T. 2013, 'A method for decentralized formation building for unicycle-like mobile robots', 2013 9th Asian Control Conference, ASCC 2013.
View/Download from: Publisher's site
The paper presents a method for decentralized flocking and global formation building for a network of unicy-cles described by the standard kinematics equations with hard constraints on the vehicles linear and angular velocities. We propose decentralized motion coordination control algorithms for the robots so that they collectively move in a desired geometric pattern from any initial position. There are no predefined leaders in the group and only local information is required for the control. The effectiveness of the proposed control algorithms is illustrated via computer simulations. &copy; 2013 IEEE.
Chai, R., Hunter, G., Ling, S.S. & Nguyen, H.T. 2012, 'Real-Time Microcontroller based Brain Computer Interface for Mental Task Classifications using Wireless EEG Signals from Two Channels', Proceedings of the Ninth IASTED International Conference on Biomedical Engineering, The Ninth IASTED International Conference on Biomedical Engineering, ACTA Press, Innsbruck, Austria, pp. 336-342.
View/Download from: UTS OPUS or Publisher's site
A brain computer interface (BCI) using electroencephalography (EEG) to measure brain activities could provide severely disabled people with alternative means of control and communication. In a practical system, portability, low power and real-time operation are the keys requirements. This could be accomplished by using an embedded microcontroller based system. The main contribution of this paper shows the development of a real-time BCI prototype system to classify groups of mental tasks based on such a system. The relevant mental tasks used are mental arithmetic, figure rotation, letter composing, visual counting and eyes closed action. Moreover, the system uses a separate two channels only wireless EEG measurement module with the active positions at parietal and occipital lobes. The result shows the wireless EEG module has a good performance with a CMRR of more than 95dB. In addition, the size of the module is small (36x36 mm2) and current consumption is low enough to operate off a 3V coin cell battery. The mental tasks were classified using a feed-forward back-propagation artificial neural network (ANN) trained with the Levenberg-Marquardt algorithm. An accuracy of around 70% was achieved with bit rate at around 0.4 bits/trial for six subjects tested to select between three separate mental tasks.
Yuwono, M., Su, S.W., Moulton, B.D. & Nguyen, H.T. 2012, 'Gait cycle spectrogram analysis using a torso-attached inertial sensor', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 34th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, San Diego, California, USA, pp. 6539-6542.
View/Download from: UTS OPUS or Publisher's site
Measurement of gait parameters can provide important information about a person's health and safety. Automatic analysis of gait using kinematic sensors is a newly emerging area of research. We describe a new way to detect walking, and measure gait cadence, by using time-frequency signal processing together with spectrogram analysis of signals from a chest-worn inertial measurement unit (IMU). A pilot study of 11 participants suggests that this method is able to distinguish between walk and non-walk activities with up to 88.70% sensitivity and 97.70% specificity. Limitations of the method include instability associated with manual fine-tuning of local and global threshold levels.
Truong, B.C., Hoang, T.D., Ha, K. & Nguyen, H.T. 2012, 'Global optimization for human skin investigation in TeraHertz', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 34th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, San Diego, California, USA, pp. 5474-5477.
View/Download from: UTS OPUS or Publisher's site
In this paper, the electromagnetic interaction between human skin and terahertz radiation is investigated through the double Debye parameters&acirc; extraction algorithm. The changes of skin content are contrasted at the frequencies below one terahertz(THz) but the recent approaches could provide only a rough estimation. We propose an global optimization based identification, which results in globally accurate estimators in the frequency range up to two THz, and thus supports the validity of Debye model for Terahertz wave&acirc;s propagation and reflection in skin. Simulation results confirm our prominent methodology.
Tran, Y.H., Thuraisingham, R., Craig, A.R. & Nguyen, H.T. 2012, 'Stationary and variability in eyes open and eyes closed EEG signals from able-bodied and spinal cord injured persons', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 34th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, San Diego, California, USA, pp. 2861-2864.
View/Download from: UTS OPUS or Publisher's site
This paper examines the assumption of stationarity used in EEG brain activity analyses, despite EEG data often being non-stationary. Transformations necessary to obtain stationary data from measured non-stationary EEG data and methods to assess non-stationarity are illustrated using eyes open (EO) and eyes closed (EC) data. The study shows that even short time EEG records of 10s duration exhibit nonstationary behavior. Examination of the change in variance when going from the EO to the EC state for both able bodied and spinal cord injured participants show that the difference in variance is consistently positive and statistically significant only when stationary data is used. This has implications for brain computer interfaces that utilizes changes in EO and EC EEG signals.
San, P., Ling, S.S. & Nguyen, H.T. 2012, 'Intelligent detection of hypoglycemic episodes in children with Type 1 diabetes using adaptive neural-fuzzy inference system', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 34th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, San Diego, California, USA, pp. 6325-6328.
View/Download from: UTS OPUS or Publisher's site
Hypoglycemia, or low blood glucose, is the most common complication experienced by Type 1 diabetes mel- litus (T1DM) patients. It is dangerous and can result in unconsciousness, seizures and even death. The most common physiological parameter to be effected from hypoglycemic reaction are heart rate (HR) and correct QT interval (QTc) of the electrocardiogram (ECG) signal. Based on physiological parameters, an intelligent diagnostics system, using the hybrid approach of adaptive neural fuzzy inference system (ANFIS), is developed to recognize the presence of hypoglycemia. The proposed ANFIS is characterized by adaptive neural network capabilities and the fuzzy inference system. To optimize the membership functions and adaptive network parameters, a global learning optimization algorithm called hybrid particle swarm optimization with wavelet mutation (HPSOWM) is used. For clinical study, 15 children with Type 1 diabetes volunteered for an overnight study. All the real data sets are collected from the Department of Health, Government of Western Australia. Several experiments were conducted with 5 patients each, for a training set (184 data points), a validation set (192 data points) and a testing set (153 data points), which are randomly selected. The effectiveness of the proposed detection method is found to be satisfactory by giving better sensitivity, 79.09% and acceptable specificity, 51.82%.
Nguyen, L., Su, S.W. & Nguyen, H.T. 2012, 'Identification of hypoglycemia and hyperglycemia in Type 1 diabetic patients using ECG parameters', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 34th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, San Diego, California, USA, pp. 2716-2719.
View/Download from: UTS OPUS or Publisher's site
Hypoglycemia and Hyperglycemia are both serious diseases related to diabetes mellitus. Among Type 1 Diabetic patients, there are who experience both hypoglycemic and hyperglycemic events. The aim of this study was to identify of hypoglycemia and hyperglycemia based on ECG changes in this population. An ECG Acquisition and Analysis System based on LabVIEW software has been developed for collecting ECG signals and extracting features with abnormal changes. ECG parameters included Heart rate (HR), corrected QT interval (QTc), PR interval, corrected RT interval (RTc) and corrected TpTe interval (TpTeC). The results indicated that hypoglycemic and hyperglycemic states produce significant inverse changes on those ECG parameters.
Nguyen, J., Nguyen, N., Tran, Y.H., Su, S.W., Craig, A.R. & Nguyen, H.T. 2012, 'Real-time performance of a hands-free semi-autonomous wheelchair system using a combination of stereoscopic and spherical vision', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 34th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, San Diego, California, USA, pp. 3069-3072.
View/Download from: UTS OPUS or Publisher's site
This paper is concerned with the operational performance of a semi-autonomous wheelchair system named TIM (Thought-controlled Intelligent Machine), which uses cameras in a system configuration modeled on the vision system of a horse. This new camera configuration utilizes stereoscopic vision for 3-Dimensional (3D) depth perception and mapping ahead of the wheelchair, combined with a spherical camera system for 360-degrees of monocular vision. The unique combination allows for static components of an unknown environment to be mapped and any surrounding dynamic obstacles to be detected, during real-time autonomous navigation, minimizing blind-spots and preventing accidental collisions with people or obstacles. Combining this vision system with a shared control strategy provides intelligent assistive guidance during wheelchair navigation, and can accompany any hands-free wheelchair control technology for people with severe physical disability. Testing of this system in crowded dynamic environments has displayed the feasibility and real-time performance of this system when assisting handsfree control technologies, in this case being a proof-of-concept brain-computer interface (BCI).
Nguyen, V., Nguyen, L., Su, S.W. & Nguyen, H.T. 2012, 'Development of a Bayesian neural network to perform obstacle avoidance for an intelligent wheelchair', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 34th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, San Diego, California, USA, pp. 1884-1887.
View/Download from: UTS OPUS or Publisher's site
This paper presents an extension of a real-time obstacle avoidance algorithm for our laser-based intelligent wheelchair, to provide independent mobility for people with physical, cognitive, and/or perceptual impairments. The laser range finder URG-04LX mounted on the front of the wheelchair collects immediate environment information, and then the raw laser data are directly used to control the wheelchair in real-time without any modification. The central control role is an obstacle avoidance algorithm which is a neural network trained under supervision of Bayesian framework, to optimize its structure and weight values. The experiment results demonstrated that this new approach provides safety, smoothness for autonomous tasks and significantly improves the performance of the system in difficult tasks such as door passing.
Nguyen, L., Nguyen, V., Ling, S.S. & Nguyen, H.T. 2012, 'An adaptive strategy of classification for detecting hypoglycemia using only two EEG channels', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 34th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, San Diego, California, USA, pp. 3515-3518.
View/Download from: UTS OPUS or Publisher's site
Hypoglycemia is the most common but highly feared side effect of the insulin therapy for patients with Type 1 Diabetes Mellitus (T1DM). Severe episodes of hypoglycemia can lead to unconsciousness, coma, and even death. The variety of hypoglycemic symptoms arises from the activation of the autonomous central nervous system and from reduced cerebral glucose consumption. In this study, electroencephalography (EEG) signals from five T1DM patients during an overnight clamp study were measured and analyzed. By applying a method of feature extraction using Fast Fourier Transform (FFT) and classification using neural networks, we establish that hypoglycemia can be detected non-invasively using EEG signals from only two channels. This paper demonstrates that a significant advantage can be achieved by implementing adaptive training. By adapting the classifier to a previously unseen person, the classification results can be improved from 60% sensitivity and 54% specificity to 75% sensitivity and 67% specificity.
Handojoseno, A.M., Shine, J.M., Nguyen, N., Tran, Y.H., Lewis, S. & Nguyen, H.T. 2012, 'The detection of freezing of gait in Parkinson's Disease patients using EEG signals based on wavelet decomposition', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 34th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, San Diego, California, USA, pp. 69-72.
View/Download from: UTS OPUS or Publisher's site
Freezing of Gait (FOG) is one of the most disabling gait disturbances of Parkinson&acirc;s disease (PD). The experience has often been described as &acirc;feeling like their feet have been glued to the floor while trying to walk&acirc; and as such it is a common cause of falling in PD patients. In this paper, EEG subbands Wavelet Energy and Total Wavelet Entropy were extracted using the multiresolution decomposition of EEG signal based on the Discrete Wavelet Transform and were used to analyze the dynamics in the EEG during freezing. The Back Propagation Neural Network classifier has the ability to identify the onset of freezing of PD patients during walking using these features with average values of accuracy, sensitivity and specificity are around 75 %. This results have proved the feasibility of utilized EEG in future treatment of FOG.
Chai, R., Ling, S.S., Hunter, G. & Nguyen, H.T. 2012, 'Toward Fewer EEG Channels and Better Feature Extractor of Non-Motor Imagery Mental Tasks Classification for a Wheelchair Thought Controller', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2012), 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2012), IEEE, San Diego, CA, USA, pp. 5266-5269.
View/Download from: UTS OPUS or Publisher's site
This paper presents a non-motor imagery tasks classification electroencephalography (EEG) based brain computer interface (BCI) for wheelchair control. It uses only two EEG channels and a better feature extractor to improve the portability and accuracy in the practical system. In addition, two different features extraction methods, power spectral density (PSD) and Hilbert Huang Transform (HHT) energy are compared to find a better method with improved classification accuracy using a Genetic Algorithm (GA) based neural network classifier. The results from five subjects show that using the original eight channels with three tasks, accuracy between 76% and 85% is achieved. With only two channels in combination with the best chosen task using a PSD feature extractor, the accuracy is reduced to between 65% and 79%. However, the HHT based method provides an improved accuracy between 70% and 84% for the classification of three discriminative tasks using two EEG channels.
Chai, R., Ling, S.S., Hunter, G. & Nguyen, H.T. 2012, 'Mental Task Classifications Using Prefrontal Cortex Electroencephalograph Signals', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2012), the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2012), IEEE, San Diego, CA, USA, pp. 1831-1834.
View/Download from: UTS OPUS or Publisher's site
For an electroencephalograph (EEG)-based brain computer interface (BCI) application, the use of gel on the hair area of the scalp is needed for low impedance electrical contact. This causes the set up procedure to be time consuming and inconvenient for a practical BCI system. Moreover, studies of other cortical areas are useful for BCI development. As a more convenient alternative, this paper presents the EEG based-BCI using the prefrontal cortex non-hair area to classify mental tasks at three electrodes position: Fp1, Fpz and Fp2. The relevant mental tasks used are mental arithmetic, ringtone, finger tapping and words composition with additional tasks which are baseline and eyes closed. The feature extraction is based on the Hilbert Huang Transform (HHT) energy method and the classification algorithm is based on an artificial neural network (ANN) with genetic algorithm (GA) optimization. The results show that the dominant alpha wave during eyes closed can still clearly be detected in the prefrontal cortex. The classification accuracy for five subjects, mental tasks vs. baseline task resulted in average accuracy is 73% and the average accuracy for pairs of mental task combinations is 72%.
Yuwono, M., Su, S.W., Moulton, B.D. & Nguyen, H.T. 2012, 'Gait episode identification based on wavelet feature clustering of spectrogram images', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 34th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, San Diego, California, USA, pp. 2949-2952.
View/Download from: UTS OPUS or Publisher's site
Automatic analysis of gait using kinematic sensors is a newly emerging area of research. We describe a new way to detect walking, and measure gait cadence, by using time-frequency signal processing together with spectrogram analysis of signals from a chest-worn inertial measurement unit (IMU). A pilot study of 11 participants suggests that this method is able to distinguish between walk and non-walk activities with up to 88.70% sensitivity and 97.70% specificity. Limitations of the method include instability associated with manual fine-tuning of local and global threshold levels.
Thuraisingham, R., Tran, Y.H., Craig, A.R. & Nguyen, H.T. 2012, 'Frequency analysis of eyes open and eyes closed EEG signals using the Hilbert-Huang transform', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 34th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, San Diego, California, USA, pp. 2865-2868.
View/Download from: UTS OPUS or Publisher's site
Frequency analysis based on the Hilbert-Huang transform (HHT) is examined as an alternative to Fourier spectral analysis in the study of EEG signals. This method overcomes the need for the EEG signal to be linear and stationary, assumptions necessary for the application of Fourier spectral analysis. The HHT method comprises two components: empirical mode decomposition (EMD) of the signal into intrinsic mode functions (IMF&acirc;s); and the Hilbert transform of the IMF&acirc;s. This technique is applied here in the study of consecutive eyes open (EO), eyes closed (EC) EEG signals of able bodied and spinal cord injured participants. The study found that in this EO, EC pair the instantaneous frequencies in the EO state were higher compared to the EC state. The Hilbert weighted frequency, a measure of the mean of the instantaneous frequencies present in an IMF, is used here to detect these changes from EO to the EC state in an EEG signal. Although there was a good detection of this change with information obtained from just one IMF (94% in able-bodied persons and 84% in SCI persons), almost 100% success in detecting between group differences was achieved using all the IMF's. This result has implications for assistive technology that rely on EEG changes in EO and EC states.
San, P., Ling, S.S. & Nguyen, H.T. 2012, 'Hybrid Particle Swarm Optimization Based Normalized Radial Basis Function Neural Network For Hypoglycemia Detection', International Joint Conference on Neural Networks, WCCI 2012 IEEE World Congress on Computational Intelligence, IEEE, Brisbane, Australia, pp. 2718-2723.
View/Download from: UTS OPUS or Publisher's site
In this study, a normalized radial basis function neural network (NRBFNN) is presented for detection of hypoglycemia episodes by using physiological parameters of electrocardiogram (ECG) signal. ypoglycemia is a common and serious side effect of insulin therapy in patients with Type 1 diabetes. Based on heart rate (HR) and corrected QT interval (QTc) of electrocardiogram (ECG) signal, a hybrid particle swarm optimization based normalized RBFNN is developed for recognization of hypoglycemia episodes. A global learning algorithm called hybrid particle swarm optimization with wavelet mutation (HPSOWM) is used to optimize the parameters of NRBFNN. From a clinical study of 15 children with Type 1 diabetes, natural occurrence of nocturnal hypoglycemic episodes associated with increased heart rates and corrected QT interval are studied. The overall data are organized into a training set (5 patients), validation set (5 patients) and testing set (5 patients) randomly selected. Using the optimized NRBFNN, the testing performance for detection of hypoglycemic episodes are satisfactory with 76.74% of sensitivity and 51.82% of specificity.
Chai, R., Ling, S.S., Hunter, G. & Nguyen, H.T. 2012, 'Mental non-motor imagery tasks classifications of brain computer interface for wheelchair commands using genetic algorithm-based neural network', Proceedings of the 2012 International Joint Conference on Neural Networks (IJCNN 2012), 2012 IEEE World Congress on Computational Intelligence (WCCI 2012) / 2012 International Joint Conference on Neural Networks (IJCNN 2012), IEEE, Brisbane, Australia, pp. 978-984.
View/Download from: UTS OPUS or Publisher's site
A genetic algorithm (GA)-based neural network classification in the application of brain computer interface (BCI) for controlling a wheelchair is presented in this paper. This study uses an electroencephalography (EEG) as a non-invasive BCI approach to discriminate three non-motor imagery mental tasks for disabled individuals who may have difficulty in using BCI based motor imagery tasks. The three tasks classification is mapped into three wheelchair movements: left, right and forward and the relevant combination mental tasks used in this study are mental arithmetic, letter composing, Rubik's cube rolling, visual counting, ringtone imagery and spatial navigation. The results show the proposed system provides good classification performance after selecting the most effective of three discriminative tasks across combination of the different non-motor imagery mental tasks for the five subjects tested. The average classification accuracy is between 76% and 85 %, with information transfer rates varies from 0.5 to 0.8 bits per trial.
Yuwono, M., Su, S.W., Moulton, B.D. & Nguyen, H.T. 2012, 'Optimization strategies for rapid centroid estimation', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 34th Annual Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, San Diego, California, USA, pp. 6212-6215.
View/Download from: UTS OPUS or Publisher's site
Particle swarm algorithm has been extensively utilized as a tool to solve optimization problems. Recently proposed particle swarm&Acirc;&plusmn;based clustering algorithm called the Rapid Centroid Estimation (RCE) is a lightweight alteration to Particle Swarm Clustering (PSC). The RCE in its standard form is shown to be superior to conventional PSC algorithm. We have observed some limitations in RCE including the possibility to stagnate at a local minimum combination and the restriction in swarm size. We propose strategies to optimize RCE further by introducing RCE+ and swarm RCE+. Five benchmark datasets from UCI machine learning database are used to test the performance of these new strategies. In Glass dataset swarm RCE+ is able to achieve highest purity centroid combinations with less iteration (90.3%&Acirc;&plusmn;1.1% in 9&Acirc;&plusmn;5 iterations) followed by RCE+ (89%&Acirc;&plusmn;3.5% in 65&Acirc;&plusmn;62 iterations) and RCE (87%&Acirc;&plusmn;5.9% in 54&Acirc;&plusmn;44). Similar quality is also reflected in other benchmark datasets including Iris, Wine, Breast Cancer, and Diabetes.
San, P., Ling, S.S. & Nguyen, H.T. 2012, 'Optimized variable translation wavelet neural network and its application on hypoglycemia detection system', 7th IEEE Conference on Industrial Electronics and Applications, 7th IEEE Conference on Industrial Electronics and Applications, IEEE, Singapore, pp. 547-551.
View/Download from: UTS OPUS or Publisher's site
An hybrid particle swarm optimization based optimized variable translation wavelet neural network (VTWNN) is proposed for detection of hypoglycemic episodes in patients with Type 1 diabetes mellitus (T1DM). Due to excellent performance in capturing nonstationary signal and nonlinear function modeling of VTWNN, it is used as a suitable classifier in hypoglycemia detection system. A global training algorithm called hybrid particle swarm optimization with wavelet mutation (HPSOWM) operation is investigated for parameters optimization of proposed VTWNN detection system. In this clinical study, 15 children with Type 1 diabetes were observed overnight. All the real data sets collected from Department of Heath, Government of Western Australia. Several experiments are performed over a randomly selected training set 5 patients (184 data points), validation set 5 patients (192 data points) and testing set 5 patients (153 data points) respectively. Using variable translation wavelet neural network (VTWNN), the value of testing sensitivity and specificity are 79.07 % and 50.00 %. The results show that the proposed detection system performs well in terms of good sensitivity and acceptable specificity.
Ling, S.S., Nguyen, H.T., Leung, F.H., Chan, K.Y. & Jiang, F. 2012, 'Intelligent fuzzy particle swarm optimization with cross-mutated operation', IEEE Congress on Evolutionary Computation, IEEE Congress on Evolutionary Computation (CEC), IEEE, Australia, pp. 3009-3016.
View/Download from: UTS OPUS or Publisher's site
This paper presents a novel fuzzy particle swarm optimization with cross-mutated operation (FPSOCM), where a fuzzy logic is applied to determine the inertia weight of PSO and the control parameter of the proposed cross-mutated operation based on human knowledge. By introducing the fuzzy system, the value of the inertia weight of PSO becomes adaptive. The new cross-mutated operation effectively drives the solution to escape from local optima. To illustrate the performance of the FPSOCM, a suite of benchmark test functions are employed. Experimental results show the proposed FPSOCM method performs better than some existing hybrid PSO methods in terms of solution quality and solution reliability (standard deviation upon many trials). Moreover, an industrial application of economic load dispatch is given to show that the FPSOCM method performs statistically more significant than the existing hybrid PSO methods
Nguyen, L., Nguyen, V., Ling, S.S. & Nguyen, H.T. 2012, 'A particle swarm optimization-based neural network for detecting nocturnal hypoglycemia using electroencephalograph (EEG) signals', 2012 IEEE World Congress on Computational Intelligence, IEEE, Brisbane, Australia, pp. 2730-2735.
View/Download from: UTS OPUS or Publisher's site
For patients with Type 1 Diabetes Mellitus (T1DM), hypoglycemia or the state of low blood glucose level is a very common but dangerous complication. Hypoglycemia episodes can lead to a large number of serious symptoms and effects, including unconsciousness, coma and even death. The variety of hypoglycemia symptoms is originated from the inadequate supply of glucose to the brain. By analyzing electroencephalography (EEG) signals from five T1DM patients during an overnight study, we find that under hypoglycemia, both centroid theta frequency and centroid alpha frequency change significantly against non-hypoglycemia conditions. Furthermore, a neural network is developed to detect hypoglycemia using the mentioned two EEG features. A standard particle swarm optimization strategy is applied to optimize the parameters of this neural network. By using the proposed method, we obtain the classification performance of 82% sensitivity and 63% specificity. The results demonstrate that hypoglycemia episodes can be detected non-invasively and effectively from EEG signals.
Yuwono, M., Su, S.W., Moulton, B.D. & Nguyen, H.T. 2012, 'Fast unsupervised learning method for rapid estimation of cluster centroids', 2012 IEEE Congress of Evolutionary Computation, IEEE Congress of Evolutionary Computation, IEEE, Brisbane, pp. 889-896.
View/Download from: UTS OPUS or Publisher's site
Data clustering is a process where a set of data points is divided into groups of similar points. Recent approaches for data clustering have seen the development of unsupervised learning algorithms based on Particle Swarm Optimization (PSO) techniques. These include Particle Swarm Clustering (PSC) and Modified PSC (mPSC) algorithms for solving clustering problems. However, the PSC and mPSC algorithms tend to be computationally expensive when applied to datasets that have higher levels of dimensionality and large volumes. This paper presents a novel and more efficient swarm clustering strategy we call Rapid Centroid Estimation (RCE). We compare the performance of RCE with the performance of PSC and mPSC in several ways including complexity analyses and particle behavior analyses. Our benchmark testing suggests that RCE can reach a solution 274 times quicker than PSC and 270 times quicker than mPSC for a clustering task where the dataset has a dimension of 80 and a volume of 500. We also investigated particle behaviors on two-class two-dimensional datasets with volume of 500, presenting 250 data for each well-separated class with known Gaussian centers. We found that RCE converged to the appropriate centers at 70 updates on average, compared to 19802 updates for PSC and 23006 updates for mPSC. An ANOVA indicates RCE is significantly faster than both PSC and mPSC.
Nguyen, H.T., Truong, B.C., Ha, K. & Hoang, T.D. 2013, 'System identification for Terahertz wave's propagation and reflection in human skin', Communications and Electronics (ICCE), 2012 Fourth International Conference on, ICCE 2012, IEEE, Hue, Vietnam, pp. 364-368.
View/Download from: UTS OPUS or Publisher's site
This paper is concerned with parameter identification for the double Debye model of the Terahertz wave's propagation and reflection in human skin. The existing methods could provide estimators, which are accurate at the frequencies higher than one THz but rather row at the lower frequencies, where the majority of contrast for differentiating the changes of skin content is present. We propose another approach by using parametric quadratic optimization to locate the global optimal estimator. Simulation results confirm our reliable and prominent technique.
Haddad, A., Su, S.W., Celler, B.G. & Nguyen, H.T. 2012, 'Enhancement interval training exercise based on the analysis of dynamic cardio-respiratory response', Proceedings of the IASTED International Conference Biomedical Engineering (BioMed 2012), IASTED International Conference Biomedical Engineering, Acta Press, Innsbruck, Austria, pp. 458-464.
View/Download from: UTS OPUS or Publisher's site
Interval training is an effective method of improving aerobic function and cardiovascular fitness. Heart rate (HR) and oxygen uptake (VO2) are major indicators of human cardiovascular response to exercises. This study investigates human heart rate as well as oxygen uptake response dynamics to running exercises. Eight healthy male subjects were asked to run on a motor-controlled treadmill under a predefined running protocol. Heart rate and oxygen consumption were monitored and recorded using a COSMED portable gas analyzer (K4b2, Cosmed). The running protocol was repeated twice by each subject and averaged values were taken of each data set to reduce the influence of various internal and environmental factors on the measurements. Experimental results showed that the time constant of offset exercise for both heart rate and oxygen uptake is longer than that of onset exercise; they also showed that VO2 reached the steady state faster than heart rate for both onset and offset cases. These experimental results will also be used to build an interval training protocol. This study also showed how onset and offset time constants, as well as onset and offset steady state gains of an average VO2 profile can be used to simulate an interval training protocol.
Zhang, Y., Haddad, A., Su, S.W., Celler, B.G. & Nguyen, H.T. 2012, 'Onset and offset exercise response model in electronic terms', Proceedings of the IASTED International Conference Biomedical Engineering (BioMed 2012), IASTED International Conference Biomedical Engineering (BioMed 2012), Acta Press, Innsbruck, Austria, pp. 122-128.
View/Download from: UTS OPUS or Publisher's site
This paper investigated human heart rate (HR) and oxygen uptake (VO2) dynamics to running exercise and developed an electronic circuitry based mathematical model to quantitatively depict the metabolic and energy-generating process at both onset and offset of exercises. In order to investigate transient responses of both HR and VO2, eight healthy male subjects were asked to run on a motor-controlled treadmill exercise under a predefined running protocol. Heart rate and oxygen consumption were monitored and recorded using a COSMED portable gas analyzer (K4b2, Cosmed). The observed experimental results verified the belief that cardio-respiratory responses dynamics at onset and offset of moderate or high intense exercises are significantly different. In order to find a rational explanation for this phenomenon, a novel idea was inspired by applying a simple switchable resistance-capacitor (RC) circuit to unify the complex dynamics at onset and offset of exercises. The proposed physical system can not only analytically explain body's energy-generating process, metabolism and cardio-respiratory responses, but also mathematically account for cardio-respiratory dynamics at both onset and offset of exercises, in which the continuity of the output and states during switching is guaranteed.
Ling, S.S., Nuryani, N. & Nguyen, H.T. 2012, 'Hybrid Particle Swarm - based Fuzzy Support Vector Machine for Hypoglycaemia Detection', IEEE International Conference on Fuzzy Systems, IEEE, Australia, pp. 450-455.
View/Download from: UTS OPUS or Publisher's site
Severe hypoglycemia is potentially life-threatening. This article introduces a novel hypoglycemia detection strategy using a hybrid particle swarm - based fuzzy support vector machine (SFisSvm) technique. The inputs of this system are six electrocardiographic (ECG) parameters. The system parameters of SFisSvm are optimized using a particle swarm optimization method. The proposed hypoglycemia detector system is a combination of two subsystems, namely, fuzzy inference system (FIS) and support vector machine (SVM). Two most significant inputs, heart rate and RTpc are fed to FIS, and its output is used for input of the SVM. The other ECG parameters and the output of FIS are fed to SVM and, then, are classified to indicate the presence of hypoglycemia. In this study, three and five membership functions are investigated for FIS. Furthermore, radial basis function (RBF), sigmoid and linear kernel functions are employed for mapping the inputs to high dimensional space in SVM. Performances of SFisSvm with different kernel functions are compared. As conclusion, the performance of SFisSvm is found with 75.19%, 83.71% and 79.33% in terms of sensitivity, specificity and geometric mean.
Chan, K.Y., Ling, S.S., Nguyen, H.T. & Jiang, F. 2012, 'A hypoglycemic episodes diagnosis system based on neural networks for Type 1 diabetes mellitus', IEEE Congress on Evolutionary Computation, CEC 2012, IEEE, Australia, pp. 2046-2051.
View/Download from: UTS OPUS or Publisher's site
Hypoglycemia (or low blood glucose) is dangerous for Type 1 diabetes mellitus (T1DM) patients, as this can cause unconsciousness or even death. However, it is impossible to monitor the hypoglycemia by measuring patients blood glucose levels all the time, especially at night. In this paper, a hypoglycemic episode diagnosis system is proposed to determine T1DM patients blood glucose levels based on these patients physiological parameters which can be measured online. It can be used not only to diagnose hypoglycemic episodes in T1DM patients, but also to generate a set of rules, which describe the domains of physiological parameters that lead to hypoglycemic episodes. The hypoglycemic episode diagnosis system addresses the limitations of the traditional neural network approaches which cannot generate implicit information. The performance of the proposed hypoglycemic episode diagnosis system is evaluated by using real T1DM patients data sets collected from the Department of Health, Government of Western Australia, Australia. Results show that satisfactory diagnosis accuracy can be obtained. Also, explicit knowledge can be produced such that the deficiency of traditional neural networks can be overcome. A clear understanding of how they perform diagnosis can be indicated.
Yuwono, M., Su, S.W., Moulton, B.D. & Nguyen, H.T. 2012, 'Method for increasing the computation speed of an unsupervised learning approach for data clustering', IEEE Congress of Evolutionary Computation, IEEE Congress of Evolutionary Computation, IEEE, Brisbane, pp. 2957-2964.
View/Download from: UTS OPUS or Publisher's site
Clustering can be especially effective where the data is irregular, noisy and/or not differentiable. A major obstacle for many clustering techniques is that they are computationally expensive, hence limited to smaller data volume and dimension. We propose a lightweight swarm clustering solution called Rapid Centroid Estimation (RCE). Based on our experiments, RCE has significantly quickened optimization time of its predecessors, Particle Swarm Clustering (PSC) and Modified Particle Swarm Clustering (mPSC). Our experimental results show that on benchmark datasets, RCE produces generally better clusters compared to PSC, mPSC, K-means and Fuzzy C-means. Compared with K-means and Fuzzy C-means which produces clusters with 62% and 55% purities on average respectively, thyroid dataset has successfully clustered on average 71% purity in 14.3 seconds.
Wang, C., Savkin, A.V., Nguyen, N. & Nguyen, H.T. 2012, 'An algorithm for collision free navigation of an intelligent powered wheelchair in dynamic environments', 2012 12th International Conference on Control Automation Robotics & Vision (ICARCV), International Conference on Control Automation Robotics & Vision, IEEE, Guangzhou, China, pp. 1571-1575.
View/Download from: UTS OPUS or Publisher's site
We propose a biologically inspired navigation algorithm and implement it on an intelligent wheelchair. The intelligent wheelchair demonstrates an excellent performance in detecting and avoiding static and moving obstacles under the guidance of the proposed algorithm, and it is able to safely and efficiently reach the target in a cluttered dynamic environment.
Wong, M., He, X., Nguyen, H. & Yeh, W. 2012, 'Particle Swarm Optimization Based Feature Selection in Mammogram Mass Classification', Proceedings of 2012 International Conference on Computerized Healthcare, 2012 International Conference on Computerized Healthcare, IEEE, Hong Kong, pp. 152-157.
View/Download from: UTS OPUS or Publisher's site
Mammography is currently the most effective method for early detection of breast cancer. This paper proposes an effective technique to classify regions of interests (ROIs) of digitized mammograms into mass and normal tissue regions by first finding the significant texture features of ROI using binary particle swarm optimization (BPSO). The data set used consisted of sixty-nine ROIs from the MIAS Mini-Mammographic database. Eighteen texture features were derived from the gray level co-occurrence matrix (GLCM) of each ROI. Significant features are found by a feature selection technique based on BPSO. The decision tree classifier is then used to classify the test set using these significant features. Experimental results show that the significant texture features found by the BPSO based feature selection technique can have better classification accuracy when compared to the full set of features. The BPSO feature selection technique also has similar or better performance in classification accuracy when compared to other widely used existing techniques
Nguyen, J.S., Nguyen, T.N., Tran, Y., Su, S.W., Craig, A. & Nguyen, H.T. 2012, 'Real-time performance of a hands-free semi-autonomous wheelchair system using a combination of stereoscopic and spherical vision', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 3069-3072.
View/Download from: Publisher's site
This paper is concerned with the operational performance of a semi-autonomous wheelchair system named TIM (Thought-controlled Intelligent Machine), which uses cameras in a system configuration modeled on the vision system of a horse. This new camera configuration utilizes stereoscopic vision for 3-Dimensional (3D) depth perception and mapping ahead of the wheelchair, combined with a spherical camera system for 360-degrees of monocular vision. The unique combination allows for static components of an unknown environment to be mapped and any surrounding dynamic obstacles to be detected, during real-time autonomous navigation, minimizing blind-spots and preventing accidental collisions with people or obstacles. Combining this vision system with a shared control strategy provides intelligent assistive guidance during wheelchair navigation, and can accompany any hands-free wheelchair control technology for people with severe physical disability. Testing of this system in crowded dynamic environments has displayed the feasibility and real-time performance of this system when assisting hands-free control technologies, in this case being a proof-of-concept brain-computer interface (BCI). &copy; 2012 IEEE.
Handojoseno, A.M.A., Shine, J.M., Nguyen, T.N., Tran, Y., Lewis, S.J.G. & Nguyen, H.T. 2012, 'The detection of Freezing of Gait in Parkinson's disease patients using EEG signals based on Wavelet decomposition', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 69-72.
View/Download from: Publisher's site
Freezing of Gait (FOG) is one of the most disabling gait disturbances of Parkinson's disease (PD). The experience has often been described as feeling like their feet have been glued to the floor while trying to walk and as such it is a common cause of falling in PD patients. In this paper, EEG subbands Wavelet Energy and Total Wavelet Entropy were extracted using the multiresolution decomposition of EEG signal based on the Discrete Wavelet Transform and were used to analyze the dynamics in the EEG during freezing. The Back Propagation Neural Network classifier has the ability to identify the onset of freezing of PD patients during walking using these features with average values of accuracy, sensitivity and specificity are around 75 %. This results have proved the feasibility of utilized EEG in future treatment of FOG. &copy; 2012 IEEE.
Nguyen, L.L., Su, S. & Nguyen, H.T. 2012, 'Identification of Hypoglycemia and Hyperglycemia in Type 1 Diabetic patients using ECG parameters', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 2716-2719.
View/Download from: Publisher's site
Hypoglycemia and Hyperglycemia are both serious diseases related to diabetes mellitus. Among Type 1 Diabetic patients, there are who experience both hypoglycemic and hyperglycemic events. The aim of this study was to identify of hypoglycemia and hyperglycemia based on ECG changes in this population. An ECG Acquisition and Analysis System based on LabVIEW software has been developed for collecting ECG signals and extracting features with abnormal changes. ECG parameters included Heart rate (HR), corrected QT interval (QTeC), PR interval, corrected RT interval (RTC) and corrected TpTe interval (TpTeC). Blood glucose levels were used to classify glycemic states in subjects as hypoglycemic state ( 60 mml/l, Hypo), as normoglycemic state (80 to 110 mmol/l, Normo), and as hyperglycemic state 150 mml/l, Hyper). The results indicated that hypoglycemic and hyperglycemic states produce significant inverse changes on those ECG parameters. &copy; 2012 IEEE.
Nguyen, A.V., Nguyen, L.B., Su, S. & Nguyen, H.T. 2012, 'Development of a Bayesian neural network to perform obstacle avoidance for an intelligent wheelchair', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 1884-1887.
View/Download from: Publisher's site
This paper presents an extension of a real-time obstacle avoidance algorithm for our laser-based intelligent wheelchair, to provide independent mobility for people with physical, cognitive, and/or perceptual impairments. The laser range finder URG-04LX mounted on the front of the wheelchair collects immediate environment information, and then the raw laser data are directly used to control the wheelchair in real-time without any modification. The central control role is an obstacle avoidance algorithm which is a neural network trained under supervision of Bayesian framework, to optimize its structure and weight values. The experiment results demonstrated that this new approach provides safety, smoothness for autonomous tasks and significantly improves the performance of the system in difficult tasks such as door passing. &copy; 2012 IEEE.
San, P.P., Ling, S.H. & Nguyen, H.T. 2012, 'Intelligent detection of hypoglycemic episodes in children with type 1 diabetes using adaptive neural-fuzzy inference system', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 6325-6328.
View/Download from: Publisher's site
Hypoglycemia, or low blood glucose, is the most common complication experienced by Type 1 diabetes mellitus (T1DM) patients. It is dangerous and can result in unconsciousness, seizures and even death. The most common physiological parameter to be effected from hypoglycemic reaction are heart rate (HR) and correct QT interval (QTc) of the electrocardiogram (ECG) signal. Based on physiological parameters, an intelligent diagnostics system, using the hybrid approach of adaptive neural fuzzy inference system (ANFIS), is developed to recognize the presence of hypoglycemia. The proposed ANFIS is characterized by adaptive neural network capabilities and the fuzzy inference system. To optimize the membership functions and adaptive network parameters, a global learning optimization algorithm called hybrid particle swarm optimization with wavelet mutation (HPSOWM) is used. For clinical study, 15 children with Type 1 diabetes volunteered for an overnight study. All the real data sets are collected from the Department of Health, Government of Western Australia. Several experiments were conducted with 5 patients each, for a training set (184 data points), a validation set (192 data points) and a testing set (153 data points), which are randomly selected. The effectiveness of the proposed detection method is found to be satisfactory by giving better sensitivity, 79.09% and acceptable specificity, 51.82%. &copy; 2012 IEEE.
Yuwono, M., Su, S.W., Moulton, B.D. & Nguyen, H.T. 2012, 'Gait episode identification based on wavelet feature clustering of spectrogram images', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 2949-2952.
View/Download from: Publisher's site
Measurement of gait parameters can provide important information about a person's health and safety. Automatic analysis of gait using kinematic sensors is a newly emerging area of research. We propose a new approach to detect gait episodes using Neural Network and and clustering of wavelet-decomposed spectrogram images. Signals from a chest-worn inertial measurement unit (IMU) is processed using Explicit Complementary Filter (ECF) to estimate and track torso angle. Using the feature obtained from wavelet decomposition of spectrogram images, we use an Augmented Radial Basis Neural Network (ARBF) to classify walking episodes. Cluster centroids of ARBF are optimized using Rapid Cluster Estimation (RCE). A pilot study of 11 participants suggests that our approach is able to distinguish between walk and non-walk activities with up to 85.71% sensitivity and 91.34% specificity. &copy; 2012 IEEE.
Chai, R., Ling, S.H., Hunter, G.P. & Nguyen, H.T. 2012, 'Mental task classifications using prefrontal cortex electroencephalograph signals', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 1831-1834.
View/Download from: Publisher's site
For an electroencephalograph (EEG)-based brain computer interface (BCI) application, the use of gel on the hair area of the scalp is needed for low impedance electrical contact. This causes the set up procedure to be time consuming and inconvenient for a practical BCI system. Moreover, studies of other cortical areas are useful for BCI development. As a more convenient alternative, this paper presents the EEG based-BCI using the prefrontal cortex non-hair area to classify mental tasks at three electrodes position: Fp1, Fpz and Fp2. The relevant mental tasks used are mental arithmetic, ringtone, finger tapping and words composition with additional tasks which are baseline and eyes closed. The feature extraction is based on the Hilbert Huang Transform (HHT) energy method and the classification algorithm is based on an artificial neural network (ANN) with genetic algorithm (GA) optimization. The results show that the dominant alpha wave during eyes closed can still clearly be detected in the prefrontal cortex. The classification accuracy for five subjects, mental tasks vs. baseline task resulted in average accuracy is 73% and the average accuracy for pairs of mental task combinations is 72%. &copy; 2012 IEEE.
Yuwono, M., Su, S.W., Moulton, B.D. & Nguyen, H.T. 2012, 'Gait cycle spectrogram analysis using a torso-attached inertial sensor', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 6539-6542.
View/Download from: Publisher's site
Measurement of gait parameters can provide important information about a person's health and safety. Automatic analysis of gait using kinematic sensors is a newly emerging area of research. We describe a new way to detect walking, and measure gait cadence, by using time-frequency signal processing together with spectrogram analysis of signals from a chest-worn inertial measurement unit (IMU). A pilot study of 11 participants suggests that this method is able to distinguish between walk and non-walk activities with up to 88.70% sensitivity and 97.70% specificity. Limitations of the method include instability associated with manual fine-tuning of local and global threshold levels. &copy; 2012 IEEE.
Chai, R., Ling, S.H., Hunter, G.P. & Nguyen, H.T. 2012, 'Toward fewer EEG channels and better feature extractor of non-motor imagery mental tasks classification for a wheelchair thought controller', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 5266-5269.
View/Download from: Publisher's site
This paper presents a non-motor imagery tasks classification electroencephalography (EEG) based brain computer interface (BCI) for wheelchair control. It uses only two EEG channels and a better feature extractor to improve the portability and accuracy in the practical system. In addition, two different features extraction methods, power spectral density (PSD) and Hilbert Huang Transform (HHT) energy are compared to find a better method with improved classification accuracy using a Genetic Algorithm (GA) based neural network classifier. The results from five subjects show that using the original eight channels with three tasks, accuracy between 76% and 85% is achieved. With only two channels in combination with the best chosen task using a PSD feature extractor, the accuracy is reduced to between 65% and 79%. However, the HHT based method provides an improved accuracy between 70% and 84% for the classification of three discriminative tasks using two EEG channels. &copy; 2012 IEEE.
Dehestani, D., Su, S., Nguyen, H., Guo, Y., Wall, J. & Eftekhari, F. 2012, 'Comprehensive sensitivity analysis of Heat Ventilating and Air Conditioning (HVAC) system based on neural network model', 10th International Conference on Healthy Buildings 2012, pp. 1555-1560.
Finding healthy HVAC model as the health reference for monitoring and fault tolerant system is the main aim in this area. To dispel this concern a comprehensive transient model of Heat Ventilation and Air Conditioning (HVAC) systems is developed by a fast Artificial Neural Network (ANN) in this study. The model is based on experimental data that are taken from our HVAC laboratory scale. The neural network is developed by using MATLAB coding and simulation technique. Our proposed model is validated against real HVAC system by minimum error. The developed model in this study can be used for a pre tuning of control system and put to good use for fault detection and isolation in order to accomplish highquality health monitoring and result in energy saving. The magnitude and trait of features are a good potential for automatic fault tolerant system based on machine learning systems.
Dehestani, D., Su, S., Nguyen, H., Vakiloroaya, V., Wall, J. & Guo, Y. 2012, 'Intelligent model based fault detection for heat ventilating and air conditioning (HVAC) system based on ANN model and SVM classifier', 10th International Conference on Healthy Buildings 2012, pp. 1253-1258.
Due to a growing demand in improving energy efficiency in the built environment, reducing the energy consumption and operating costs of heating, ventilating and air-conditioning (HVAC) systems while still maintaining occupant comfort has become one of the critical issues. Reports indicate that efficiency and availability are heavily dependent upon high reliability and maintainability. Recently, the concept of e-maintenance has been introduced to reduce the cost of maintenance. In e-maintenance systems, the intelligent fault detection and isolation (FDI) system plays a crucial role for identifying equipment and other system failures. Applying these techniques to HVAC system fault detection makes it possible to improve total cost effectiveness of maintenance and thus increase the capacity utilization rates of equipment. Reduction of energy wasting in the system by on time fault detection is another important goal of applying these techniques. Therefore, this work proposes a new model based fault detection technique for HVAC systems based on Neural Network (NN) model and online support vector machines (SVM) classifier which integrates a dimension reduction scheme to analyze the failure of system. The NN generate a high accurate model which is based reference for SVM classifier. Finally, a series of experimental fault data are applied to evaluate the effectiveness of the proposed technique. Final results show that online SVM can accurately detect faults in a HVAC cooling tower with minimum usage data. The technique is also shown to outperform an offline SVM on such energy systems for classification.
Zhang, Y., Su, S., Savkin, A., Celler, B. & Nguyen, H. 2012, 'Multi-loop integral controllability analysis for nonlinear multiple-input single-output processes', 2012 2nd Australian Control Conference, AUCC 2012, pp. 81-85.
Multi-loop integral control is still one of the most popular control strategies in industry due to its simplicity, efficiency, offset free tracking, and capability for fault tolerance. Skogestad and Morari introduced Decentralized Integral Controllability (DIC) to investigate the decentralized unconditional stability under multi-loop integral control for square systems. However, in engineering practice, some multivariable processes may not be square, which often utilize multiple redundant control inputs for the regulation of only one single output. This study extends the concept of Decentralized Integral Controllability to non-square systems, and presents sufficient conditions for Multiple-Input Single-Output nonlinear processes based on singular perturbation analysis. The proposed controllability analysis method is applied in the control of a real time temperature control system and achieves desired temperature tracking results. &copy; 2012 Institute of Engineers.
Nguyen, L.D. & Nguyen, H.T. 2012, 'Relationship between floor number and labor productivity in multistory structural work: A case study', Construction Research Congress 2012: Construction Challenges in a Flat World, Proceedings of the 2012 Construction Research Congress, pp. 1520-1529.
View/Download from: Publisher's site
Construction activities are repetitive from floor to floor in multistory building construction. Labor productivity may neither reach 100 percent of the normal level at the very first floors nor the very top floors. Nevertheless labor productivity may follow a certain pattern as construction activities progress. This research aims at exploring the relationship between floor number and labor productivity in multistory structural activities, namely formwork installation and rebar fabrication/installation. The case study methodology and learning curve theory are adopted for this research. Records from the structural works of an apartment building were analyzed to calculate floor number-based labor productivities for the two investigated activities. The unit rate of the formwork activity reduced more than 50 percent in the first five floors. If the first cycle (floor 2) is omitted, the straight-line learning curve model shows a learning rate of 83.5%. Productivity of the formwork activity tended to level off in the remaining thirteen floors. The unit rate of the rebar activity was prone to reduce in the first fifteen floors. If the first two cycles are omitted, the straight-line learning curve model indicates a learning rate of 83.6%. If only the first cycle is omitted, the learning rate of the rebar activity is 87.9%. Productivity of the rebar activity tended to decrease in the last three top floors though data points were not adequate to confirm such pattern. &copy; 2012 ASCE.
Tran, T., Ha, Q.P. & Nguyen, H.T. 2011, 'Semi-automatic control of modular systems with intermittent data losses', Proceedings of the 2011 IEEE Conference on Automation Science and Engineering, IEEE Conference on Automation Science and Engineering, IEEE, Trieste Italy, pp. 625-630.
View/Download from: UTS OPUS
This paper presents a control procedure of distributed stabilising agents for dynamically-coupled systems operating in the imperfect data environment of a mesh device network. A multivariable controller is applied to each single modular subsystem, which also allows for a manual control mode. To deal with the device network, intermittent data losses are compensated for on-the-fly using the incrementally accumulative quadratic constraint (AQC). The incrementally AQC is employed in the procedure of stabilising agents to accommodate the coexistence of closed-loop control and man-inthe- loop regulation. These agents render stabilising bounds for the manipulated variables in the automatic control mode, and at the same time, provide warning signals and manipulation guidance for the operators to prevent possible plant-wide destabilisation in the semi-automatic control mode. Taking the control constraints into consideration, the feasibility of AQCbased stabilising bounds is guaranteed for the consecutive datalost periods of device networks. The innovative aspect of the proposed approach rests on the stability condition developed from the input and output evolution prescribed in the controller AQC and the system dissipativity, as well as the method of remedying data losses right after the incidents. Simulation results are provided for the model predictive control of an industrial modular system in the mineral processing industry.
Tran, T., Ha, Q.P., Nguyen, H.T. & Hoang, T.D. 2011, 'Toward Plant-wide Control of Reticulated Systems Arising in Alumina Refinery with Online Stabilisation', Preprints of the 18th World Congress of the International Federation of Automatic Control (IFAC), International Federation of Automatic Control World Congress, International Federation of Automatic Control (IFAC), Milano Italy, pp. 10529-10534.
View/Download from: UTS OPUS
This paper presents a novel distributed model predictive control strategy for reticulated systems of the alumina refining process. The plant-wide control is facilitated by the constructive method of online stabilisations that is applicable to the model predictive controllers (MPC) as stability constraints. The plant-wide process is modeled as a large-scale system formed by the subsystems of different unit operations interconnected to each other. The stability condition for the interconnected system is derived from the accumulative quadratic constraint (AQC), which is subsequently developed into receding-horizon stability constraints for MPC. The proposed online stabilisation scheme can be implemented for a department and/or the whole alumina refinery, which consists of four main departments of digestion, clarification, precipitation-filtration, and evaporation. The theoretical results are illustrated by simulations for a typical example of three dynamically-coupled subsystems.
Kitoko, V., Nguyen, N., Nguyen, J., Tran, Y.H. & Nguyen, H.T. 2011, 'Performance of dry electrode with bristle in recording EEG rhythms across brain state changes', Engineering in Medicine and Biology Society,EMBC, 2011 Annual International Conference of the IEEE, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Boston, USA, pp. 59-62.
View/Download from: UTS OPUS or Publisher's site
In this paper we evaluate the physiological performance of a silver-silver chloride dry electrode with bristle (B-Electrode) in recording EEG data. For this purpose, we compare the performance of the bristle electrode in recording EEG data with the standard wet gold-plated cup electrode (G-Electrode) using two different brain state change tasks including resting condition with eyes-closed and performing mathematical task with eyes-open. Using a 2 channel recording device, eyes-closed command data were collected from each of 6 participants for a period of 20sec and the same procedure was applied for the mathematical calculation task. These data were used for statistical and classification analyse. Although, B-electrode has shown a slightly higher performance compared with G-electrode in both tasks, but analyse did not reveal any significant differences between both electrodes in all six subjects tested.
Tran, Y.H., Thuraisingham, R., Craig, A.R., Tomlinson, E., Davis, G.M., Middleton, J. & Nguyen, H.T. 2011, 'Changes in Blood Volume Pulse during Excercise Recovery in Activity-based Therapy for Spinal Cord Injury', 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Boston, Massachusetts, USA, pp. 693-696.
View/Download from: UTS OPUS
This paper presents the results of cardiovascular changes that occur during a novel rehabilitation strategy called activity based therapy (ABT). Blood volume pulse (BVP) signals were measured during functional electrical stimulation (FES)-induced cycling in adults with spinal cord injury (SCI) persons and results were compared to a passive cycling task and able-bodied controls performing normal cycling. BVP signals were compared during three conditions, a baseline preexercise condition, 5 minutes after exercise and after 30- minutes rest following exercise. Exercise recovery was evaluated using normalized inner products values in BVP signals. The results showed that FES-induced cycling in SCI participants resulted in a significantly greater peripheral resistance level and longer time to recover from exercise compared with passive cycling and normal cycling in ablebodied controls.
Nguyen, J., Tran, Y.H., Su, S.W. & Nguyen, H.T. 2011, 'Semi-autonomous wheelchair developed using a unique camera system configuration biologically inspired by equine vision', 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Boston, Massachusetts, USA, pp. 5762-5765.
View/Download from: UTS OPUS
This paper is concerned with the design and development of a semi-autonomous wheelchair system using cameras in a system configuration modeled on the vision system of a horse. This new camera configuration utilizes stereoscopic vision for 3-Dimensional (3D) depth perception and mapping ahead of the wheelchair, combined with a spherical camera system for 360-degrees of monocular vision. This unique combination allows for static components of an unknown environment to be mapped and any surrounding dynamic obstacles to be detected, during real-time autonomous navigation, minimizing blind-spots and preventing accidental collisions with people or obstacles. This novel vision system combined with shared control strategies provides intelligent assistive guidance during wheelchair navigation and can accompany any hands-free wheelchair control technology. Leading up to experimental trials with patients at the Royal Rehabilitation Centre (RRC) in Ryde, results have displayed the effectiveness of this system to assist the user in navigating safely within the RRC whilst avoiding potential collisions.
Craig, A.R., Tran, Y.H., Wijesuriya, N.S., Thuraisingham, R. & Nguyen, H.T. 2011, 'Switching rate changes associated with mental fatigue for assistive technologies', 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Boston, Massachusetts, USA, pp. 3071-3074.
View/Download from: UTS OPUS or Publisher's site
This paper presents research that investigated the effects of mental fatigue on brain activity associated with eyes open and eyes closed conditions. The changes associated with electroencephalography (EEG) alpha wave activity (8-13Hz) during eye closure has previously been shown to be an effective strategy for switching and activating devices as an environmental control system (ECS) designed for people with severe disability like spinal cord injury (SCI). The results showed that switching times did increase due to fatigue, however, these increases were not large (around 1 second longer to switch) and this difference was not significant. When baselines were readjusted taking into account the change in alpha wave activity due to the fatigue, switching reduced to times typically seen when the person was alert. Error rates were similar between the alert and fatigue sates. Implications of these results for a hands-free ECS are discussed.
Nguyen, V., Su, S.W. & Nguyen, H.T. 2011, 'Development of a Bayesian recursive algorithm to find freespaces for an intelligent wheelchair', 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Boston, Massachusetts, USA, pp. 7250-7253.
View/Download from: UTS OPUS
This paper introduces a new shared control strategy for an intelligent wheelchair using a Bayesian recursive algorithm. Using the local environment information gathered by a laser range finder sensor and commands acquired through a user interface, a Bayesian recursive algorithm has been developed to find the most appropriate free-space, which corresponds to the highest posterior probability value. Then, an autonomous navigation algorithm will assist to manoeuvre the wheelchair in the chosen freespace. Experiment results demonstrate that the new method provides excellent performance with great flexibility and fast response.
San, P., Ling, S.S. & Nguyen, H.T. 2011, 'Block-based neural network for hypoglycemia detection', 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Boston, Massachusetts, USA, pp. 5666-5669.
View/Download from: UTS OPUS
In this paper, evolvable block based neural network (BBNN) is presented for detection of hypoglycemia episodes. The structure of BBNN consists of a two-dimensional (2D) array of fundamental blocks with four variable inputoutput nodes and weight connections. Depending on the structure settings, each block can have one of four different internal configurations. To provide early detection of hypoglycemia episodes, the physiological parameters such as heart rate (HR) and corrected QT interval (QTc) of electrocardiogram (ECG) signal are used as the inputs of BBNN. The overall structure and weights of BBNN are optimized by an evolutionary algorithm called hybrid particle swarm optimization with wavelet mutation (HPSOWM). The optimized structures and weights of BBNN are capable to compensate large variations of ECG patterns caused by individual and temporal difference since a fixed structure classifiers are easy to fail to trace ECG signals with large variations. The ECG data of 15 patients are organized into a training set, a testing set and a validation set, each of which has randomly selected 5 patients. The simulation results shows that the proposed algorithm, BBNN with HPSOWM can successfully detect the hypoglycemic episodes in T1DM in term of testing sensitivity (76.74%) and test specificity (50.91%).
Yuwono, M., Handojoseno, A.M. & Nguyen, H.T. 2011, 'Optimization of head movement recognition using augmented radial basis function neural network', 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Boston, Massachusetts, USA, pp. 2776-2779.
View/Download from: UTS OPUS
For people with severe spine injury, head movement recognition control has been proven to be one of the most convenient and intuitive ways to control a power wheelchair. While substantial research has been done in this area, the challenge to improve system reliability and accuracy remains due to the diversity in movement tendencies and the presence of movement artifacts. We propose a Neural- Network Configuration which we call Augmented Radial Basis Function Neural-Network (ARBF-NN). This network is constructed as a Radial Basis Function Neural-Network (RBF-NN) with a Multilayer Perceptron (MLP) augmentation layer to negate optimization limitation posed by linear classifiers in conventional RBF-NN. The RBF centroid is optimized through Regrouping Particle Swarm Optimization (RegPSO) seeded with K-Means. The trial results of ARBFNN on Head-movement show a significant improvement on recognition accuracy up to 98.1% in sensitivity.
Nuryani, N., Ling, S.S. & Nguyen, H.T. 2011, 'Ventricular Repolarization Variability for Hypoglycemia Detection', 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Boston, Massachusetts, USA, pp. 7961-7964.
View/Download from: UTS OPUS
Hypoglycemia is the most acute and common complication of Type 1 diabetes and is a limiting factor in a glycemic management of diabetes. In this paper, two main contributions are presented; firstly, ventricular repolarization variabilities are introduced for hypoglycemia detection, and secondly, a swarm-based support vector machine (SVM) algorithm with the inputs of the repolarization variabilities is developed to detect hypoglycemia. By using the algorithm and including several repolarization variabilities as inputs, the best hypoglycemia detection performance is found with sensitivity and specificity of 82.14% and 60.19%, respectively.
Ling, S.S., Jiang, F., Chan, K.Y. & Nguyen, H.T. 2011, 'Permutation flow shop scheduling: fuzzy particle swarm optimization approach', IEEE International Conference on Fuzzy Systems 2011, IEEE International Conference On Fuzzy Systems, IEEE, Taipei, Taiwam, pp. 572-578.
View/Download from: UTS OPUS
AbstractA fuzzy particle swarm optimization (PSO) for the minimization of makespan in permutation flow shop scheduling problem is presented in this paper. In the proposed fuzzy PSO, the inertia weight of PSO and the control parameter of the crossmutated operation are determined by a set of fuzzy rules. To escape the local optimum, cross-mutated operation is introduced. In order to make PSO suitable for solving permutation flow shop scheduling problem, a roulette wheel mechanism is proposed to convert the continuous position values of particles to job permutations. Meanwhile, a swap-based local search for scheduling problem is designed for the local exploration on a discrete job permutation space. Flow shop benchmark functions are employed to evaluate the performance of the fuzzy PSO for flow shop scheduling problems and the results indicate that the algorithm performs better compared with existing hybrid PSO algorithms.
Ling, S.S., Nguyen, H.T. & Leung, F.H. 2011, 'Hypoglycemia detection using fuzzy inference system with genetic algorithm', IEEE International Conference on Fuzzy Systems 2011, IEEE International Conference on Fuzzy Systems, IEEE, Taipei, Taiwan, pp. 2225-2231.
View/Download from: UTS OPUS or Publisher's site
AbstractIn this paper, we develope a genetic algorithm based fuzzy inference system to recognize hypoglycemic episodes based on heart rate and corrected QT interval of the telectrocardiogram (ECG) signal. Genetic algorithm is introduced to optimize the membership functions and fuzzy rules. A practical experiment based on data from 15 children with T1DM is studied. All the data sets are collected from the Department of Health, Government of Western Australia. To prevent the phenomenon of overtraining (over-fitting), a validation strategy that may adjust the fitness function is proposed. Thus, the data are organized into a training set, a validation set, and a testing set randomly selected. The classification results in term of sensitivity, specificity, and receiver operating characteristic (ROC) analysis show that the proposed classification method performs well.
Nguyen, N., Nguyen, H.T., Su, S.W. & Celler, B.G. 2011, 'Robust online adaptive neural network control for the regulation of treadmill exercises', Engineering in Medicine and Biology Society,EMBC, 2011 Annual International Conference of the IEEE, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Boston, USA, pp. 1005-1008.
View/Download from: UTS OPUS or Publisher's site
The paper proposes a robust online adaptive neural network control scheme for an automated treadmill system. The proposed control scheme is based on Feedback-Error Learning Approach (FELA), by using which the plant Jacobian calculation problem is avoided. Modification of the learning algorithm is proposed to solve the overtraining issue, guaranteeing to system stability and system convergence. As an adaptive neural network controller can adapt itself to deal with system uncertainties and external disturbances, this scheme is very suitable for treadmill exercise regulation when the model of the exerciser is unknown or inaccurate. In this study, exercise intensity (measured by heart rate) is regulated by simultaneously manipulating both treadmill speed and gradient in order to achieve fast tracking for which a single input multi output (SIMO) adaptive neural network controller has been designed. Real-time experiment result confirms that robust performance for nonlinear multivariable system under model uncertainties and unknown external disturbances can indeed be achieved.
Weng, K., Zhang, Y., Nguyen, N., Haddad, A., Celler, B.G., Su, S.W., Guo, Y. & Nguyen, H.T. 2011, 'Multi-Loop Integral Control By Using Redundant Control Inputs For Passive Fault Tolerant Implementation', 2011 2nd International Conference on Measurement and Control Engineering (ICMCE 2011), International Conference on Measurement and Control Engineering, ASME Press, Pueto Rico, USA, pp. 7-11.
View/Download from: UTS OPUS or Publisher's site
One of the advantages of using more than one actuator and multi-loop control structure for the control of a single output variable is its potential to tolerate system failures. Based on the analysis of the steady state behaviour of the process, this paper presents a theoretical examination of processes with redundant actuators. The concept of Decentralized Integral Controllability (DIC) has been extended to non-square nonlinear processes, and a steady state sufficient condition has been provided for the multi-loop integral control configuration. We illustrate the proposed analysis method by using the example of the regulation of heart rate response for treadmill exercises, in which both treadmill speed and gradient are served as control inputs for the regulation of a single output, heart rate.
Nguyen, L., Ling, S.S., Jones, T.W. & Nguyen, H.T. 2011, 'Identification of hypoglycemic states for patients with T1DM using various parameters derived from EEG signals', 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Boston, Massachusetts, USA, pp. 2760-2763.
View/Download from: UTS OPUS
For patients with Type 1 Diabetes Mellitus (T1DM), hypoglycemia is a very common but dangerous complication which can lead to unconsciousness, coma and even death. The variety of hypoglycemia symptoms is originated from the inadequate supply of glucose to the brain. In this study, we explore the connection between hypoglycemic episodes and the electrical activity of neurons within the brain or electroencephalogram (EEG) signals. By analyzing EEG signals from a clinical study of five children with T1DM, associated with hypoglycemia at night, we find that some EEG parameters change significantly under hypoglycemia condition. Based on these parameters, a method of detecting hypoglycemic episodes using EEG signals with a feed-forward multi-layer neural network is proposed. In our application, the classification results are 72% sensitivity and 55% specificity when the EEG signals are acquired from 2 electrodes C3 and O2. Furthermore, signals from different channels are also analyzed to observe the contributions of each channel to the performance of hypoglycemia classification.
Nguyen, T.N., Nguyen, H., Su, S. & Celler, B. 2011, 'Robust online adaptive neural network control for the regulation of treadmill exercises', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 1005-1008.
View/Download from: Publisher's site
The paper proposes a robust online adaptive neural network control scheme for an automated treadmill system. The proposed control scheme is based on Feedback-Error Learning Approach (FELA), by using which the plant Jacobian calculation problem is avoided. Modification of the learning algorithm is proposed to solve the overtraining issue, guaranteeing to system stability and system convergence. As an adaptive neural network controller can adapt itself to deal with system uncertainties and external disturbances, this scheme is very suitable for treadmill exercise regulation when the model of the exerciser is unknown or inaccurate. In this study, exercise intensity (measured by heart rate) is regulated by simultaneously manipulating both treadmill speed and gradient in order to achieve fast tracking for which a single input multi output (SIMO) adaptive neural network controller has been designed. Real-time experiment result confirms that robust performance for nonlinear multivariable system under model uncertainties and unknown external disturbances can indeed be achieved. &copy; 2011 IEEE.
Nguyen, L.B., Ling, S.S.H., Jones, T.W. & Nguyen, H.T. 2011, 'Identification of hypoglycemic states for patients with T1DM using various parameters derived from EEG signals', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 2760-2763.
View/Download from: Publisher's site
For patients with Type 1 Diabetes Mellitus (T1DM), hypoglycemia is a very common but dangerous complication which can lead to unconsciousness, coma and even death. The variety of hypoglycemia symptoms is originated from the inadequate supply of glucose to the brain. In this study, we explore the connection between hypoglycemic episodes and the electrical activity of neurons within the brain or electroencephalogram (EEG) signals. By analyzing EEG signals from a clinical study of five children with T1DM, associated with hypoglycemia at night, we find that some EEG parameters change significantly under hypoglycemia condition. Based on these parameters, a method of detecting hypoglycemic episodes using EEG signals with a feed-forward multi-layer neural network is proposed. In our application, the classification results are 72% sensitivity and 55% specificity when the EEG signals are acquired from 2 electrodes C3 and O2. Furthermore, signals from different channels are also analyzed to observe the contributions of each channel to the performance of hypoglycemia classification. &copy; 2011 IEEE.
San, P.P., Ling, S.H. & Nguyen, H.T. 2011, 'Block based neural network for hypoglycemia detection', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 5666-5669.
View/Download from: Publisher's site
In this paper, evolvable block based neural network (BBNN) is presented for detection of hypoglycemia episodes. The structure of BBNN consists of a two-dimensional (2D) array of fundamental blocks with four variable input-output nodes and weight connections. Depending on the structure settings, each block can have one of four different internal configurations. To provide early detection of hypoglycemia episodes, the physiological parameters such as heart rate (HR) and corrected QT interval (QTc) of electrocardiogram (ECG) signal are used as the inputs of BBNN. The overall structure and weights of BBNN are optimized by an evolutionary algorithm called hybrid particle swarm optimization with wavelet mutation (HPSOWM). The optimized structures and weights of BBNN are capable to compensate large variations of ECG patterns caused by individual and temporal difference since a fixed structure classifiers are easy to fail to trace ECG signals with large variations. The ECG data of 15 patients are organized into a training set, a testing set and a validation set, each of which has randomly selected 5 patients. The simulation results shows that the proposed algorithm, BBNN with HPSOWM can successfully detect the hypoglycemic episodes in T1DM in term of testing sensitivity (76.74%) and test specificity (50.91%). &copy; 2011 IEEE.
Nguyen, A.V., Su, S. & Nguyen, H.T. 2011, 'Development of a Bayesian recursive algorithm to find free-spaces for an intelligent wheelchair', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 7250-7253.
View/Download from: Publisher's site
This paper introduces a new shared control strategy for an intelligent wheelchair using a Bayesian recursive algorithm. Using the local environment information gathered by a laser range finder sensor and commands acquired through a user interface, a Bayesian recursive algorithm has been developed to find the most appropriate free-space, which corresponds to the highest posterior probability value. Then, an autonomous navigation algorithm will assist to manoeuvre the wheelchair in the chosen free-space. Experiment results demonstrate that the new method provides excellent performance with great flexibility and fast response. &copy; 2011 IEEE.
Nuryani, N., Ling, S. & Nguyen, H.T. 2011, 'Ventricular repolarization variability for hypoglycemia detection', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 7961-7964.
View/Download from: Publisher's site
Hypoglycemia is the most acute and common complication of Type 1 diabetes and is a limiting factor in a glycemic management of diabetes. In this paper, two main contributions are presented; firstly, ventricular repolarization variabilities are introduced for hypoglycemia detection, and secondly, a swarm-based support vector machine (SVM) algorithm with the inputs of the repolarization variabilities is developed to detect hypoglycemia. By using the algorithm and including several repolarization variabilities as inputs, the best hypoglycemia detection performance is found with sensitivity and specificity of 82.14% and 60.19%, respectively. &copy; 2011 IEEE.
Tran, Y., Thuraisingham, R., Craig, A., Tomlinson, E., Davis, G.M., Middleton, J. & Nguyen, H. 2011, 'Changes in blood volume pulse during exercise recovery in activity-based therapy for spinal cord injury', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 693-696.
View/Download from: Publisher's site
This paper presents the results of cardiovascular changes that occur during a novel rehabilitation strategy called activity based therapy (ABT). Blood volume pulse (BVP) signals were measured during functional electrical stimulation (FES)-induced cycling in adults with spinal cord injury (SCI) persons and results were compared to a passive cycling task and able-bodied controls performing normal cycling. BVP signals were compared during three conditions, a baseline pre-exercise condition, 5 minutes after exercise and after 30-minutes rest following exercise. Exercise recovery was evaluated using normalized inner products values in BVP signals. The results showed that FES-induced cycling in SCI participants resulted in a significantly greater peripheral resistance level and longer time to recover from exercise compared with passive cycling and normal cycling in able-bodied controls. &copy; 2011 IEEE.
Kitoko, V., Nguyen, T.N., Nguyen, J.S., Tran, Y. & Nguyen, H.T. 2011, 'Performance of dry electrode with bristle in recording EEG rhythms across brain state changes', Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 59-62.
View/Download from: Publisher's site
In this paper we evaluate the physiological performance of a silver-silver chloride dry electrode with bristle (B-Electrode) in recording EEG data. For this purpose, we compare the performance of the bristle electrode in recording EEG data with the standard wet gold-plated cup electrode (G-Electrode) using two different brain state change tasks including resting condition with eyes-closed and performing mathematical task with eyes-open. Using a 2 channel recording device, eyes-closed command data were collected from each of 6 participants for a period of 20sec and the same procedure was applied for the mathematical calculation task. These data were used for statistical and classification analyse. Although, B-electrode has shown a slightly higher performance compared with G-electrode in both tasks, but analyse did not reveal any significant differences between both electrodes in all six subjects tested. &copy; 2011 IEEE.
Tran, T., Nguyen, H.T. & Ha, Q.P. 2010, 'Stability of Complex Systems with Mixed Connection Configurations under Shared Control', Proc. of the 11th. Int. Conf. Control, Automation, Robotics and Vision (ICARCV 2010), Int. Conf. Control, Automation, Robotics and Vision, IEEE, Singapore, pp. 512-517.
View/Download from: UTS OPUS or Publisher's site
This paper presents a new stabilizing method for the control of complex systems operating in semi-automatic modes. The complex system is modeled by several spatially-coupled subsystems interconnected in parallel, serial and cycle configurations. Each subsystem is regulated by a dedicated autonomous controller that also allows for a manual control mode. An interconnection stability condition which takes the couplings between subsystems into consideration is derived from the renowned dissipative systems theory. Built upon this stability condition, decentralized stabilizing agents for autonomous controllers are subsequently deployed independently and segregatedly from the control algorithms. Due to this independence, human errors from manmachine interactions, that may destabilize the control systems, can be avoidable; also different types of control algorithms and controllers of subsystems are interoperable with the same stabilizing mechanism. To accomplish such tasks simultaneously, the stabilizing agents render overriding outputs for the automatic controllers, and at the same time, provide instability warning signals and manipulation guidance to the operators to successfully regulate the subsystems in the manual control mode, yet maintain the plant-wide stability. Real-time data of control inputs and plant outputs is exerted under the auspices of controller dissipativity indices and trajectories to stabilize the systems with closed-loop control and man-in-the-loop coexistence. Our main results are illustrated in simulation for a three-unit system.
Ling, S.S., Nguyen, H.T. & Chan, K.Y. 2010, 'Genetic algorithm based fuzzy multiple regression for the nocturnal hypoglycemic classification', IEEE Congress on Evolutionary Computation (CEC) - 2010 IEEE WORLD Congress on Computational Intelligence, IEEE Congress on Evolutionary Computation, IEEE, Barcelona, Spain, pp. 2659-2664.
View/Download from: UTS OPUS or Publisher's site
Low blood glucose (Hypoglycaemia) is dangerous and can result in unconsciousness, seizures and even death. It has a common and serious side effect of insulin therapy in patients with diabetes. We measure physiological parameters (heart rate, corrected QT interval of the electrocardiogram (ECG) signal, change of heart rate, and the change of corrected QT interval) continuously to provide detection of hypoglycaemic. Based on these physiological parameters, we have developed a genetic algorithm based multiple regression model to determine the presence of hypoglycaemic episodes. Genetic algorithm is used to determine the optimal parameters of the multiple regression. The overall data were organized into a training set (8 patients) and a testing set (another 8 patient) which are randomly selected. The clinical results show that the proposed algorithm can achieve predictions with good sensitivities and acceptable specificities.
Ling, S.S., Nuryani, N. & Nguyen, H.T. 2010, 'Evolved Fuzzy Reasoning Model for Hypoglycaemic Detection', Proceedings of the 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society 'Merging Medical Humanism and Technology', IEEE Engineering in Medicine and Biology Society Annual Conference, Piscataway, USA, Buenos Aires, Argentina, pp. 4662-4665.
View/Download from: UTS OPUS or Publisher's site
Hypoglycaemia is a serious side effect of insulin therapy in patients with diabetes. We measure physiological parameters (heart rate, corrected QT interval of the electrocardiogram (ECG) signal) continuously to provide early detection of hypoglycemic episodes in Type 1 diabetes mellitus (T1DM) patients. Based on the physiological parameters, an evolved fuzzy reasoning model (FRM) to recognize the presence of hypoglycaemic episodes is developed. To optimize the fuzzy rules and the fuzzy membership functions of FRM, an evolutionary algorithm called hybrid particle swarm optimization with wavelet mutation operation is investigated. All data sets are collected from Department of Health, Government of Western Australia for a clinical study. The results show that the proposed algorithm performs well in terms of the clinical sensitivity and specificity.
Nuryani, N., Ling, S.S. & Nguyen, H.T. 2010, 'Electrocardiographic T-wave Peak-to-end Interval for Hypoglycaemia Detection', Proceedings of the 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Merging Medical Humanism and Technology, IEEE Engineering in Medicine and Biology Society Annual Conference, The Printing House, Inc., Buenos Aires, Argentina, pp. 618-621.
View/Download from: UTS OPUS or Publisher's site
Electrocardiographic T wave peak-to-end interval (TpTe) is one parameter of T wave morphology, which contains indicators for hypoglycaemia. This paper shows the corrected TpTe (TpTec) interval as one of the inputs contributing to detect hypoglycaemia. Support vector machine (SVM) and fuzzy support vector machine (FSVM) utilizing radial basis function (RBF) are used as the classification methods in this paper. By comparing with the classification systems using inputs of corrected QT interval (QTc) and heart rate only, the results indicate that the inclusion of TpTec in combination with QTc and heart rate performs better in the detection of hypoglycaemia in terms of sensitivity, specificity and accuracy.
Weng, K., Turk, B., Dolores, L., Nguyen, N., Celler, B.G., Su, S.W. & Nguyen, H.T. 2010, 'Fast tracking of a given heart rate profile in treadmill exercise', Proceedings of the 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society 'Merging Medical Humanism and Technology', IEEE Engineering in Medicine and Biology Society Annual Conference, The Printing House, Inc., Buenos Aires, Argentina, pp. 2569-2572.
View/Download from: UTS OPUS or Publisher's site
This paper investigates the application of a multi-loop PID controller in an automated treadmill exercise machine. The approach is to design a computer-controlled treadmill control system for the regulation of heart rate (HR) during treadmill exercise. A single-input and multiple-output (SIMO) controller was implemented to fast track a given heart rate profile in treadmill exercise. Two separate single-input and single-output (SISO) PID control systems are initially implemented to modify either the treadmill speed or its angle of inclination in order to achieve a desired HR. The purpose of this paper is to apply a SIMO control system by implementing a control algorithm which includes the two PID controllers working simultaneously to track the desired HR profile. The performance of the SIMO and SISO control systems are compared through the closed loop responses recorded during experimentation. This would also help future development of safe treadmill exercise system.
Nguyen, J., Su, S.W. & Nguyen, H.T. 2010, 'Spherical Vision Cameras in a Semi-autonomous Wheelchair System', Proceedings of the 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society 'Merging Medical Humanism and Technology', IEEE Engineering in Medicine and Biology Society Annual Conference, The Printing House, Inc., Buenos Aires, Argentina, pp. 4064-4067.
View/Download from: UTS OPUS or Publisher's site
This paper is concerned with the methods developed for extending the capabilities of a spherical vision camera system to allow detection of surrounding objects and whether or not they pose a danger for movement in that direction during autonomous navigation of a power wheelchair. A Point Grey Research (PGR) Ladybug2 spherical vision camera system was attached to the power wheelchair for surrounding vision. The objective is to use this Ladybug2 system to provide information about obstacles all around the wheelchair and aid the automated decision-making process involved during navigation. Through instantaneous neural network classification of individual camera images to determine whether obstacles are present, detection of obstacles have been successfully achieved with accuracies reaching 96%. This assistive technology has the purpose of automated obstacle detection, navigational path planning and decision-making, and collision avoidance during navigation.
Su, S.W., Nguyen, H.T. & Ha, Q.P. 2010, 'Laboratory Demonstration for Model Predictive Multivariable Control with a Coupled Drive System', Proc. of the 11th International Conference on Control, Automation, Robotics and Vision (ICARCV 2010), International Conference on Control, Automation, Robotics and Vision, IEEE, Singapore, pp. 762-767.
View/Download from: UTS OPUS or Publisher's site
Teaching multivariable control usually involves a certain level of mathematical sophistication and hence requires some labaratorial exemplification of the material given in formal lectures. This paper reports on a hands-on approach to multivariable control education via the implementation of a model predictive controller on a two-input, two output coupled drive apparatus. This scaled-down system represents many industrial processes while provides an excellent set-up for demonstrating the cross-coupled effects in multi-input multi-output systems. Here, a model predictive controller (MPC) is developed and implemented on the basis of a constrained optimization problem to show control performance via the belt tension and velocity outputs, demonstrate the decoupling capability, and also illustrate such issues as control input saturation, the selection of operating point, reference inputs, and system robustness to external disturbance and varying parameters. The implementation is based on Labview and MATLAB Model Predictive Control Toolbox.
Ling, S.S., Nuryani, N. & Nguyen, H.T. 2010, 'Hypoglycaemia detection for Type 1 diabetic patients based on ECG parameters using fuzzy support vector machine', International Joint Conference on Neural Networks - 2010 IEEE World Congress on Computational Intelligence, International Joint Conference on Neural Networks, IEEE, Spain, pp. 2253-2259.
View/Download from: UTS OPUS or Publisher's site
Nocturnal hypoglycaemia in type 1 diabetic patients can be dangerous in which symptoms may not be apparent while blood glucose level decreases to very low level, and for this reason, an effective detection system for hypoglycaemia is crucial. This research work proposes a detection system for the hypoglycaemia based on the classification of electrocardiographic (ECG) parameters. The classification uses a Fuzzy Support Vector Machine (FSVM) with inputs of heart rate, corrected QT (QT c) interval and corrected TpTe (TpTec) interval. Three types of kernel functions (radial basis function (RBF), exponential radial basis function (ERBF) and polynomial function) are investigated in the classification. Moreover, parameters of the kernel functions are tuned to find the optimum of the classification. The results show that the FSVM classification using RBF kernel function demonstrates better performance than using SVM. However, both classifiers result approximately same performance if ERBF and polynomial kernel functions are used.
Chan, K.Y., Ling, S.S., Dillon, T.S. & Nguyen, H.T. 2010, 'Classification of Hypoglycemic Episodes for Type 1 Diabetes Mellitus based on Neural Networks', IEEE Congress on Evolutionary Computation (CEC) - 2010 IEEE World Congress on Computational Intelligence, IEEE Congress on Evolutionary Computation, IEEE, Barcelona, Spain, pp. 1444-1448.
View/Download from: UTS OPUS or Publisher's site
Hypoglycemia is dangerous for Type 1 diabetes mellitus (T1DM) patients. Based on the physiological parameters, we have developed a classification unit with hybridizing the approaches of neural networks and genetic algorithm to identify the presences of hypoglycemic episodes for TIDM patients. The proposed classification unit is built and is validated by using the real T1DM patients' data sets collected from Department of Health, Government of Western Australia. Experimental results show that the proposed neural network based classification unit can achieve more accurate results on both trained and unseen T1DM patients' data sets compared with those developed based on the commonly used classification methods for medical diagnosis including statistical regression, fuzzy regression and genetic programming.
Tran, Y.H., Craig, A.R., Wijesuriya, N. & Nguyen, H.T. 2010, 'Improving Classification Rates for Use in Fatigue Countermeasure Devices using Brain Activity', Proceedings of the 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society 'Merging Medical Humanism and Technology', IEEE Engineering in Medicine and Biology Society Annual Conference, The Printing House, Inc., Buenos Aires, Argentina, pp. 4460-4463.
View/Download from: UTS OPUS or Publisher's site
Fatigue can be defined as a state that involves psychological and physical tiredness with a range of symptoms such as tired eyes, yawning and increased blink rate. It has major implications for work place and road safety as well as a negative symptom of many acute and chronic illnesses. As such there has been considerable research dedicated to systems or algorithms that can be used to detect and monitor the onset of fatigue. This paper examines using electroencephalography (EEG) signals to classify fatigue and alert states as a function of subjective self-report, driving performance and physiological symptoms. The results show that EEG classification network for fatigue improved from 75% to 80% when these factors are applied, especially when the data is grouped by subjective self-report of fatigue with classification accuracy improving to 84.5%.
Nguyen, H.T. & Jones, T.W. 2010, 'Detection of Nocturnal Hypoglycemic Episodes using EEG Signals', Proceedings of the 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society 'Merging Medical Humanism and Technology', IEEE Engineering in Medicine and Biology Society Annual Conference, The Printing House, Inc., Buenos Aires, Argentina, pp. 4930-4933.
View/Download from: UTS OPUS or Publisher's site
Hypoglycemia (low blood glucose) or the fear of hypoglycemia constitutes a significant barrier to the achievement of good glycemic control in the insulin treated diabetic patients. By measuring physiological responses derived from EEG and analyzing these, we establish that hypoglycemia can be detected non-invasively. From a clinical study of six children with type 1 diabetes (T1D), associated with hypoglycemic episodes at night, their centroid (centre of gravity) alpha frequency reduced significantly (P<;;0.001) and their centroid theta frequency increased significantly (P<;;0.02). The overall data were organized into a training set (3 patients) and a test set (another 3 patients) randomly selected. Using the optimal Bayesian neural network which was derived from the training set with the highest log evidence, the estimated blood glucose profiles produced a significant correlation (P<;;0.005) against measured values in the test set.
Weng, K., Turk, B., Dolores, L., Nguyen, T.N., Celler, B., Su, S. & Nguyen, H.T. 2010, 'Fast tracking of a given heart rate profile in treadmill exercise', 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10, pp. 2569-2572.
View/Download from: Publisher's site
This paper investigates the application of a multi-loop PID controller in an automated treadmill exercise machine. The approach is to design a computer-controlled treadmill control system for the regulation of heart rate (HR) during treadmill exercise. A single-input and multiple-output (SIMO) controller was implemented to fast track a given heart rate profile in treadmill exercise. Two separate single-input and single-output (SISO) PID control systems are initially implemented to modify either the treadmill speed or its angle of inclination in order to achieve a desired HR. The purpose of this paper is to apply a SIMO control system by implementing a control algorithm which includes the two PID controllers working simultaneously to track the desired HR profile. The performance of the SIMO and SISO control systems are compared through the closed loop responses recorded during experimentation. This would also help future development of safe treadmill exercise system. &copy; 2010 IEEE.
Ling, S.H., Nuryani & Nguyen, H.T. 2010, 'Evolved fuzzy reasoning model for hypoglycaemic detection', 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10, pp. 4662-4665.
View/Download from: Publisher's site
Hypoglycaemia is a serious side effect of insulin therapy in patients with diabetes. We measure physiological parameters (heart rate, corrected QT interval of the electrocardiogram (ECG) signal) continuously to provide early detection of hypoglycemic episodes in Type 1 diabetes mellitus (T1DM) patients. Based on the physiological parameters, an evolved fuzzy reasoning model (FRM) to recognize the presence of hypoglycaemic episodes is developed. To optimize the fuzzy rules and the fuzzy membership functions of FRM, an evolutionary algorithm called hybrid particle swarm optimization with wavelet mutation operation is investigated. All data sets are collected from Department of Health, Government of Western Australia for a clinical study. The results show that the proposed algorithm performs well in terms of the clinical sensitivity and specificity. &copy; 2010 IEEE.
Nuryani, Ling, S. & Nguyen, H.T. 2010, 'Electrocardiographic T-wave peak-to-end interval for hypoglycaemia detection', 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10, pp. 618-621.
View/Download from: Publisher's site
Electrocardiographic T wave peak-to-end interval (TpTe) is one parameter of T wave morphology, which contains indicators for hypoglycaemia. This paper shows the corrected TpTe (TpTec) interval as one of the inputs contributing to detect hypoglycaemia. Support vector machine (SVM) and fuzzy support vector machine (FSVM) utilizing radial basis function (RBF) are used as the classification methods in this paper. By comparing with the classification systems using inputs of corrected QT interval (QTc) and heart rate only, the results indicate that the inclusion of TpTec in combination with QTc and heart rate performs better in the detection of hypoglycaemia in terms of sensitivity, specificity and accuracy. &copy; 2010 IEEE.
Tran, Y.H., Thuraisingham, R., Craig, A.R. & Nguyen, H.T. 2009, 'Evaluating the efficacy of an automated procedure for EEG artifact removal', Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Minneapolis, Minnesota, USA, pp. 376-379.
View/Download from: UTS OPUS
Electroencephalography (EEG) signals are often contaminated with artifacts arising from many sources such as those with ocular and muscular origins. Artifact removal techniques often rely on the experience of the EEG technician to detect these artifact components for removal. This paper presents the results comparing an automated procedure (AT) against visually (VT) choosing artifactual components for removal, using second order blind identification (SOBI) and canonical correlation analyses. The results show that the resulting EEG signal after artifact removal for the AT and VT were comparable using a technique that measures the variance amongst electrodes and spectral energy. The AT technique is objective, faster and easier to use, and shown here to be comparable to the standard technique of visually detecting artifact component
Dalvand, H., Nguyen, H.T. & Ha, Q.P. 2009, 'Design of second-order sliding mode controllers for MR damper-embedded smart structures', Proceedings of the 26th International Symposium on Automation and Robotics in Construction, International Symposium on Automation and Robotics in Construction, IAARC-University of Texas at Austin, Austin USA, pp. 332-340.
View/Download from: UTS OPUS
Design of a current controlled system for MR damper-embedded civil structures
Ling, S.S., Nguyen, H.T. & Chan, K.Y. 2009, 'A New Particle Swarm Optimization Algorithm for Neural Network Optimization', 2nd International Workshop on Data Mining and Artificial Intelligence (DMAI 2009), IEEE International Conference on Network and System Security, International Conference on network and System Security, IEEE, Gold Coast, Australia, pp. 516-521.
View/Download from: UTS OPUS or Publisher's site
This paper presents a new particle swarm optimization (PSO) algorithm for tuning parameters (weights) of neural networks. The new PSO algorithm is called fuzzy logic-based particle swarm optimization with cross-mutated operation (FPSOCM), where the fuzzy inference system is applied to determine the inertia weight of PSO and the control parameter of the proposed cross-mutated operation by using human knowledge. By introducing the fuzzy system, the value of the inertia weight becomes variable. The cross-mutated operation is effectively force the solution to escape the local optimum. Tuning parameters (weights) of neural networks is presented using the FPSOCM. Numerical example of neural network is given to illustrate that the performance of the FPSOCM is good for tuning the parameters (weights) of neural networks.
Weng, K., Nguyen, N., Nguyen, H.T. & Su, S.W. 2009, 'Rate estimation for the monitoring of rehabilitation exercises', Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, The Printing House, Inc., Minneapolis, Minnesota, USA, pp. 6267-6270.
View/Download from: UTS OPUS or Publisher's site
This study investigates the rate estimation problem encountered in rehabilitation exercise monitoring by using noninvasive portable sensors. The purpose of this paper has two main parts. The first part is to find suitable approaches for the rate detection of tri-axial accelerometer (TA) signals and ECG signals respectively. It is found that the integral type approaches (the average magnitude difference function (AMDF) and autocorrelation function (ACF)) are particularly suitable for TA signal pre-processing, while differential type approaches are very efficient for electrocardiographic (ECG) signal pre-processing. The second part is to develop a square wave matching method to detect the rate from the pre-processed signals. Experimental results indicate that the proposed methods can effectively detect pace rate from TA and heart rate from ECG and remove undesirable spikes.
Nguyen, N., Nguyen, H.T. & Su, S.W. 2009, 'Robust Multivariable Strategy and its Applications to a Powered Wheelchair', Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Minneapolis, Minnesota, USA, pp. 7114-7117.
View/Download from: UTS OPUS
The paper proposes a systematic robust multivariable control strategy based on combination of systematic triangularization technique and robust control strategies. Two design stages are required. In the first design stage, multivariable control problem is reduced into a series of scalar control problems via triangularization technique. For each specific scalar system, two advanced control strategies are proposed and implemented in the second design stage. The first one is based on Model Predictive Control, which is an iterative, finite horizon optimization procedure. The second control strategy is known as Neuro-Sliding Mode Control, which integrates Sliding Mode Control (SMC) and Neural Network Design to achieve both chattering-free and system robustness. Real-time implementation on a powered wheelchair system confirms that robustness and desired performance of a multivariable system under model uncertainties and unknown external disturbances can indeed be achieved by the combination of triangularization technique and Neuro-Sliding Mode Control.
Trieu, T., Willey, K. & Nguyen, H.T. 2009, 'Adaptive shared control strategies based on the Bayesian recursive technique for an intelligent wheelchair', Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Minneapolis, Minnesota, USA, pp. 7118-7121.
View/Download from: UTS OPUS
In this paper we present an adaptive shared control method for an intelligent wheelchair based on the Bayesian recursive technique to assist a disable user in performing obstacle avoidance tasks. Three autonomous tasks have been developed for different types of environments to improve the performance of the overall system. The system combines local environmental information gathered using a laser range finder sensor with the user&acirc;s intentions to select the most suitable autonomous task in different situations. The evidences of these tasks are estimated by the Bayesian recursive technique during movements of the wheelchair. The most appropriate task is chosen to be the with the highest evidence value. Experimental results show significant performance improvements compared to our previously reported shared control methods.
Nguyen, J., Nguyen, H.T. & Nguyen, H.T. 2009, 'Semi-autonomous wheelchair system using stereoscopic cameras', Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Minneapolis, Minnesota, USA, pp. 5068-5071.
View/Download from: UTS OPUS
This paper is concerned with the design and development of a semi-autonomouswheelchair system using stereoscopic cameras to assist hands-free control technologies for severely disabled people. The stereoscopic cameras capture an image from both the left and right cameras, which are then processed with a Sum of Absolute Differences (SAD) correlation algorithm to establish correspondence between image features in the different views of the scene. This is used to produce a stereo disparity image containing information about the depth of objects away from the camera in the image. A geometric projection algorithm is then used to generate a 3- Dimensional (3D) point map, placing pixels of the disparity image in 3D space. This is then converted to a 2-Dimensional (2D) depth map allowing objects in the scene to be viewed and a safe travel path for the wheelchair to be planned and followed based on the user's commands. This assistive technology utilising stereoscopic cameras has the purpose of automated obstacle detection, path planning and following, and collision avoidance during navigation. Experimental results obtained in an indoor environment displayed the effectiveness of this assistive technology.
Thuraisingham, R., Tran, Y.H., Craig, A.R., Wijesuriya, N.S. & Nguyen, H.T. 2009, 'Using microstate intensity for the analysis of spontaneous EEG: tracking changes from alert to fatigue state', Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Minneapolis, Minnesota, USA, pp. 4982-4985.
View/Download from: UTS OPUS
Fatigue is a negative symptom of many illnesses and also has major implications for road safety. This paper presents results using a method called microstate segmentation (MSS). It was used to distinguish changes from an alert to a fatigue state. The results show a significant increase in MSS instantaneous amplitude during the fatigue state. Plotting the linear gradient of the nonlinear part of the phase data from the MSS also showed a significant difference (P<0.01) in the gradients of the alert state compared to the fatigue state. The results suggest that MSS can be used in analyzing spontaneous electroencephalography (EEG) signals to detect changes in physiological states. The results have implications for countermeasures used in detecting fatigue.
Nguyen, H.T., Ghevondian, N. & Jones, T.W. 2009, 'Real-time detection of nocturnal hypoglycemic episodes using a novel non-invasive hypoglycemia monitor', Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Minneapolis, Minnesota, USA, pp. 3822-3825.
View/Download from: UTS OPUS or Publisher's site
Hypoglycemia or low blood glucose is a common and serious side effect of insulin therapy in patients with diabetes. Hypoglycemia is unpleasant and can result in unconsciousness, seizures and even death. HypoMon is a realtime non-invasive monitor that measures relevant physiological parameters continuously to provide detection of hypoglycemic episodes in Type 1 diabetes mellitus patients (T1DM). Based on heart rate and corrected QT interval of the ECG signal, we have continued to develop effective algorithms for early detection of nocturnal hypoglycemia. From a clinical study of 24 children with T1DM, associated with natural occurrence of hypoglycemic episodes at night, their heart rates increased (1.021&Acirc;&plusmn;0.264 vs. 1.068&Acirc;&plusmn;0.314, P<0.053) and their corrected QT intervals increased significantly (1.030&Acirc;&plusmn;0.079 vs. 1.052&Acirc;&plusmn;0.078, P<0.002). It is interesting to note that QT interval and heart rate are less correlated when the patients experienced hypoglycemic episodes through natural occurrence compared to when clamp studies were performed. The overall data were organized into a training set (12 patients) and a test set (another 12 patients) randomly selected. Using the optimal Bayesian neural network which was derived from the training set with the highest log evidence, the estimated blood glucose profiles produced a significant correlation (P<0.02) against measured values in the test set.
Su, S.W., Anderson, B., Chen, W. & Nguyen, H.T. 2009, 'Multi-realisation of nonlinear systems', Proceedings of the 48th IEEE Conference on Decision and Control, 2009 held jointly with the 2009 28th Chinese Control Conference. CDC/CCC 2009., IEEE Conference on Decision and Control, IEEE, Shanghai, China, pp. 5901-5905.
View/Download from: UTS OPUS or Publisher's site
The system multi-realization problem is to find a state-variable realization for a set of systems, sharing as many parameters as possible. A multi-realization can be used to efficiently implement a multi-controller architecture for Multiple Model Adaptive Control (MMAC). We extend the linear multi-realization problem to nonlinear systems. The problem of minimal multi-realization of a set of MIMO systems is introduced and solved for feedback linearizable systems.
Smith, S., Winchester, D., Jamieson, R. & Nguyen, H.T. 2009, 'Information Systems Security Compliance in e-Government', Proceedings of Pacific Asia Conference on Information Systems (PACIS) 2009, Pacific Asia Conference on Information Systems, AIS Electronic Library, Hyderabad, Inidia, pp. 1-13.
View/Download from: UTS OPUS
The aim of this research paper is the development of a Fuzzy Logic model framed on Activity Theory to predict and benchmark compliance of Government agencies activities, with information systems security (ISS) standard, AS17799 (2006). The ISS standard has 10 main categories and 127 controls for which survey questions were asked in an online process. This project is a longitudinal study that commenced in 2002. The questions for the Fuzzy Logic project were piloted in August 2002, followed by three annual surveys from November 2002. The paper describes the development of an enhanced Fuzzy Logic model using activity Theory. The results from the Fuzzy Logic model helped to focus attention and monitor the progress of agencies that appear unlikely to reach ISS compliance. The main contribution of this study is the simplification of a complex system guided by Activity Theory using a fuzzy logic tool for analysis of a large number of inputs across a large number of agencies. A practical contribution to the New South Wales Government was that the Fuzzy Logic tool removed the complexity in computation, saved time and resources. Our approach using Fuzzy Logic also permits input from expert&acirc;s embracing an organisations human capital.
Su, S.W., Nguyen, H.T., Jarman, R., Zhu, J., Lowe, D.B., McLean, P.B., Huang, S., Nguyen, N., Nicholson, R.S. & Weng, K. 2009, 'Model Predictive Control of Gantry Crane with Input Nonlinearity Compensation', International Conference on Control, Automation and Systems Engineering, International Conference on Control, Automation and Systems Engineering, World Academy of Science, Engineering and Technology, Penang, Malaysia, pp. 312-316.
View/Download from: UTS OPUS
This paper proposed a nonlinear model predictive control (MPC) method for the control of gantry crane. One of the main motivations to apply MPC to control gantry crane is based on its ability to handle control constraints for multivariable systems. A pre-compensator is constructed to compensate the input nonlinearity (nonsymmetric dead zone with saturation) by using its inverse function. By well tuning the weighting function matrices, the control system can properly compromise the control between crane position and swing angle. The proposed control algorithm was implemented for the control of gantry crane system in System Control Lab of University of Technology, Sydney (UTS), and achieved desired experimental results.
Nguyen, H.T., Ghevondian, N. & Jones, T.W. 2009, 'Real-time detection of nocturnal hypoglycemic episodes using a novel non-invasive hypoglycemia monitor', Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009, pp. 3822-3825.
View/Download from: Publisher's site
Hypoglycemia or low blood glucose is a common and serious side effect of insulin therapy in patients with diabetes. Hypoglycemia is unpleasant and can result in unconsciousness, seizures and even death. HypoMon is a real-time non-invasive monitor that measures relevant physiological parameters continuously to provide detection of hypoglycemic episodes in Type 1 diabetes mellitus patients (T1DM). Based on heart rate and corrected QT interval of the ECG signal, we have continued to develop effective algorithms for early detection of nocturnal hypoglycemia. From a clinical study of 24 children with T1DM, associated with natural occurrence of hypoglycemic episodes at night, their heart rates increased (1.021&plusmn;0.264 vs. 1.068&plusmn;0.314, P<0.053) and their corrected QT intervals increased significantly (1.030&plusmn;0.079 vs. 1.052&plusmn;0.078, P<0.002). It is interesting to note that QT interval and heart rate are less correlated when the patients experienced hypoglycemic episodes through natural occurrence compared to when clamp studies were performed. The overall data were organized into a training set (12 patients) and a test set (another 12 patients) randomly selected. Using the optimal Bayesian neural network which was derived from the training set with the highest log evidence, the estimated blood glucose profiles produced a significant correlation (P<0.02) against measured values in the test set. &copy;2009 IEEE.
Nguyen, H.T., Ghevondian, N. & Jones, T.W. 2008, 'Detection of Nocturnal Hypoglycemic Episodes (Natural Occurence) in Children with Type 1 Diabetes using an Optimal Bayesian Neural Network Algorithm', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Vancouver, Canada, pp. 1311-1314.
View/Download from: UTS OPUS or Publisher's site
Hypoglycemia or low blood glucose is dangerous and can result in unconsciousness, seizures and even death. It is a common and serious side effect of insulin therapy in patients with diabetes. HypoMon is a non-invasive monitor that measures some physiological parameters continuously to provide detection of hypoglycemic episodes in Type 1 diabetes mellitus patients (T1DM). Based on heart rate and corrected QT interval of the ECG signal, we have continued to develop Bayesian neural network detection algorithms to recognize the presence of hypoglycemic episodes. From a clinical study of 16 children with T1DM, natural occurrence of nocturnal hypoglycemic episodes are associated with increased heart rates (1.033&Acirc;&plusmn;0.242 vs. 1.082&Acirc;&plusmn;0.298, P<0.06) and increased corrected QT intervals (1.031&Acirc;&plusmn;0.086 vs. 1.060&Acirc;&plusmn;0.084, P<0.001). The overall data were organized into a training set (8 patients) and a test set (another 8 patients) randomly selected. Using the optimal Bayesian neural network with 10 hidden nodes which was derived from the training set with the highest log evidence, the sensitivity (true positive) value for detection of hypoglycemia in the test set is 89.2%.
Nguyen, H.T., Ghevondian, N. & Jones, T.W. 2008, 'Neural-network Detection of Nocturnal Hypoglycemia (Natural Occurence) in Children with Type 1 Diabetes', The American Diabetes Associateion's 68th Scientific Sessions, The American Diabetes Associateion's 68th Scientific Sessions, Marathon Multimedia, San Francisco, USA, pp. 408-408.
Nguyen, H.T., Nguyen, J. & Nguyen, H.T. 2008, 'Bayesian Recursive Algorithm for Width Estimation of Freespace for a Power Wheelchair using Stereoscopic Cameras', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Vancouver, Canada, pp. 4234-4237.
View/Download from: UTS OPUS or Publisher's site
This paper is concerned with the estimation of freespace based on a Bayesian recursive (BR) algorithm for an autonomous wheelchair using stereoscopic cameras by severely disabled people. A stereo disparity map processed from both the left and right camera images is constructed to generate a 3D point map through a geometric projection algorithm. This is then converted to a 2D distance map for the purpose of freespace estimation. The width of freespace is estimated using a BR algorithm based on uncertainty information and control data. Given the probabilities of this width computed, a possible movement decision is then made for the mobile wheelchair. Experimental results obtained in an indoor environment show the effectiveness of this estimation algorithm.
Trieu, T., Nguyen, H.T. & Willey, K. 2008, 'Advanced Obstacle Avoidance for a Laser-based Wheelchair using Optimised Bayesian Neural Networks', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Vancouver, Canada, pp. 3463-3466.
View/Download from: UTS OPUS or Publisher's site
In this paper we present an advanced method of obstacle avoidance for a laser based intelligent wheelchair using optimized Bayesian neural networks. Three neural networks are designed for three separate sub-tasks: passing through a door way, corridor and wall following and general obstacle avoidance. The accurate usable accessible space is determined by including the actual wheelchair dimensions in a real-time map used as inputs to each networks. Data acquisitions are performed separately to collect the patterns required for specified sub-tasks. Bayesian frame work is used to determine the optimal neural network structure in each case. Then these networks are trained under the supervision of Bayesian rule. Experiment results showed that compare to the VFH algorithm our neural networks navigated a smoother path following a near optimum trajectory.
Trieu, T., Nguyen, H.T. & Willey, K. 2008, 'Shared Control Strategies for Obstacle Avoidance Tasks in an Intelligent Wheelchair', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Vancouver, Canada, pp. 3463-3466.
View/Download from: UTS OPUS or Publisher's site
In this paper we present a method of shared control strategy for an intelligent wheelchair to assist a disable user in performing obstacle avoidance tasks. The system detects obstacles in front of the wheelchair using a laser range finder sensor. As the wheelchair moves the information from the laser range finder is combined with data from the encoders mounted in its driving wheels to build a 360&Acirc;&ordm; real-time map. The accuracy of the map is improved by eliminating the systematic error that would result from both the uncertainty of effective wheelbase and unequal driving wheel diameters. The usable wheelchair accessible space is determined by including the actual wheelchair dimensions in producing the real-time map. In making a decision the shared control method considers the user's intentions via the head-movement interface, accessible space of the environment and user safety. The experiments show promising results in the intelligent wheelchair system.
Nguyen, N., Nguyen, H.T. & Su, S.W. 2008, 'Optimal Path-following Control of a Smart Powered Wheelchair', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Vancouver, Canada, pp. 5025-5028.
View/Download from: UTS OPUS or Publisher's site
This paper proposes an optimal path-following control approach for a smart powered wheelchair. Lyapunov&acirc;s second method is employed to find a stable position tracking control rule. To guarantee robust performance of this wheelchair system even under model uncertainties, an advanced robust tracking is utilised based on the combination of a systematic decoupling technique and a neural network design. A calibration procedure is adopted for the wheelchair system to improve positioning accuracy. After the calibration, the accuracy is improved significantly. Two real-time experimental results obtained from square tracking and door passing tasks confirm the performance of proposed approach.
Nguyen, N., Nguyen, H.T. & Su, S.W. 2008, 'Neuro-Sliding Mode Multivariable Control of a Powered Wheelchair', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Vancouver, Canada, pp. 3471-3474.
View/Download from: UTS OPUS or Publisher's site
This paper proposes a neuro-sliding mode multivariable control approach for the control of a powered wheelchair system. In the first stage, a systematic decoupling technique is applied to the wheelchair system in order to reduce the multivariable control problem into two independent scalar control problems. Then two Neuro-Sliding Mode Controllers (NSMCs) are designed for these independent subsystems to guarantee system robustness under model uncertainties and unknown external disturbances. Both off-line and on-line trainings are involved in the second stage. Realtime experimental results confirm that robust performance for this multivariable wheelchair control system under model uncertainties and unknown external disturbances can indeed be achieved.
Wan, S.H. & Nguyen, H.T. 2008, 'Human Computer Interaction using Hand Gesture', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Vancouver, Canada, pp. 2357-2360.
View/Download from: UTS OPUS or Publisher's site
Hand gesture is a very natural form of human interaction and can be used effectively in human computer interaction (HCI). This project involves the design and implementation of a HCI using a small hand-worn wireless module with a 3-axis accelerometer as the motion sensor. The small stand-alone unit contains an accelerometer and a wireless Zigbee transceiver with microcontroller. To minimize intrusiveness to the user, the module is designed to be small (3cm by 4 cm). A time-delay neural network algorithm is developed to analyze the time series data from the 3-axis accelerometer. Power consumption is reduced by the noncontinuous transmission of data and the use of low-power components, efficient algorithm and sleep mode between sampling for the wireless module. A home control interface is designed so that the user can control home appliances by moving through menus. The results demonstrate the feasibility of controlling home appliances using hand gestures and would present an opportunity for a section of the aging population and disabled people to lead a more independent life.
Tran, Y.H., Wijesuriya, N.S., Thuraisingham, R., Craig, A.R. & Nguyen, H.T. 2008, 'Increase in Regularity and Decrease in Variability seen in Electroencephalogram (EEG) Signals from Alert to Fatigue suring a Driving Simulated Task', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Vancouver, Canada, pp. 1096-1099.
View/Download from: UTS OPUS or Publisher's site
Driver fatigue is a prevalent problem and a major risk for road safety accounting for approximately 20-40% of all motor vehicle accidents. One strategy to prevent fatigue related accidents is through the use of countermeasure devices. Research on countermeasure devices has focused on methods that detect physiological changes from fatigue, with the fast temporal resolution from brain signals, using the electroencephalogram (EEG) held as a promising technique This paper presents the results of nonlinear analysis using sample entropy and second-order difference plots quantified by central tendency measure (CTM) on alert and fatigue EEG signals from a driving simulated task. Results show that both sample entropy and second-order difference plots significantly increases the regularity and decreases the variability of EEG signals from an alert to a fatigue state.
Wijesuriya, N.S., Tran, Y.H., Thuraisingham, R., Nguyen, H.T. & Craig, A.R. 2008, 'Effects of Mental Fatigue on 8-13 Hz Brain Activity in People with Spinal Cord Injury', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Vancouver, Canada, pp. 5716-5719.
View/Download from: UTS OPUS or Publisher's site
Brain computer interfaces (BCIs) can be implemented into assistive technologies to provide &acirc;hands-free&acirc; control for the severely disabled. BCIs utilise voluntary changes in one&acirc;s brain activity as a control mechanism to control devices in the person&acirc;s immediate environment. Performance of BCIs could be adversely affected by negative physiological conditions such as fatigue and altered electrophysiology commonly seen in spinal cord injury (SCI). This study examined the effects of mental fatigue from an increase in cognitive demand on the brain activity of those with SCI. Results show a trend of increased alpha (8-13Hz) activity in able-bodied controls after completing a set of cognitive tasks. Conversely, the SCI group showed a decrease in alpha activity due to mental fatigue. Results suggest that the brain activity of SCI persons are altered in its mechanism to adjust to mental fatigue. These altered brain conditions need to be addressed when using BCIs in clinical populations such as SCI. The findings have implications for the improvement of BCI technology.
Nguyen, H.T., Ghevondian, N. & Jones, T.W. 2008, 'Real-time Detection of Nocturnal Hypoglycaemia using a Non-invasive Continuous Hypoglycaemia Monitor', Australian Diabetes Society & Australian Diabetes Educator Association Annual Scientific Meeting, Australian Diabetes Society & Australian Diabetes Educator Association Annual Scientific Meeting, Servier, Melbourne, pp. 125-125.
Su, S.W., Nguyen, H.T. & Ha, Q.P. 2008, 'Integral Controller Design for Nonlinear Systems using Inverse Optimal Control', Proceedings of the 10th International Conference on Control, Automation, Robotics and Vision, International Conference on Control, Automation, Robotics and Vision, Research Publishinh Services, Hanoi, Vietnam, pp. 2154-2158.
View/Download from: UTS OPUS or Publisher's site
This paper proposes an integral controller design scheme for nonlinear systems based on optimal control and the passivity theorem in order to suppress the effect of external disturbances. The main strategy is to augment an optimal controller with a PI type controller. To guarantee the proposed controller has a desired stability margin, the passivity-based design method is introduced. Here, the inverse optimal control technique is employed to avoid the need of solving a Hamilton- Jacobi equation. An illustrative example is given to show the design procedure and the controller effectiveness.
Nguyen, H.T., Ghevondian, N. & Jones, T.W. 2008, 'Comparison of two Overnight Studies (Glucose Clamp and Natural Occurence) in Children with Type 1 Diabetes for the Detection of Nocturnal Hypoglycemia', The American Diabetes Association's 68th Scientific Sessions, The American Diabetes Association's 68th Scientific Sessions, American Diabetes Association, San Francisco, USA, pp. 400-400.
The purpose of this study was to evaluate the clinical effectiveness of a new non-invasive and continuous hypoglycemia monitoring device (HypoMon from AIMedics Pty Ltd) for real-time detection of nocturnal hypoglycemia in patients with Type 1 diabetes mellitus (T1DM). HypoMon consists of a chest belt transmitter that houses a set of four skin-surface bio-sensor electrodes for the measurement of physiological parameters, and a wireless hand -held computer unit.
Su, S.W., Celler, B.G., Savkin, A.V., Nguyen, H.T., Cheng, T.M., Guo, Y. & Wang, L. 2008, 'Portable sensor based dynamic estimation of human oxygen uptake via nonlinear multivariable modeling', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Vancouver, Canada, pp. 2431-2434.
View/Download from: UTS OPUS or Publisher's site
Noninvasive portable sensors are becoming popular in biomedical engineering practice due to its ease of use. This paper investigates the estimation of human oxygen uptake (VO2) of treadmill exercises by using multiple portable sensors (wireless heart rate sensor and triaxial accelerometers). For this purpose, a multivariable Hammerstein model identification method is developed. Well designed PRBS type of exercises protocols are employed to decouple the identification of linear dynamics with that of nonlinearities of Hammerstein systems. The support vector machine regression is applied to model the static nonlinearities. Multivariable ARX modelling approach is used for the identification of dynamic part of the Hammerstein systems. It is observed the obtained nonlinear multivariable model can achieve better estimations compared with single input single output models. The established multivariable model has also the potential to facilitate dynamic estimation of energy expenditure for outdoor exercises, which is the next research step of this study.
Nguyen, N., Nguyen, H.T. & Su, S. 2008, 'Optimal path-following control of a smart powered wheelchair', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology", pp. 5025-5028.
This paper proposes an optimal path-following control approach for a smart powered wheelchair. Lyapunov's second method is employed to find a stable position tracking control rule. To guarantee robust performance of this wheelchair system even under model uncertainties, an advanced robust tracking is utilised based on the combination of a systematic decoupling technique and a neural network design. A calibration procedure is adopted for the wheelchair system to improve positioning accuracy. After the calibration, the accuracy is improved significantly. Two real-time experimental results obtained from square tracking and door passing tasks confirm the performance of proposed approach. &copy; 2008 IEEE.
Trieu, H.T., Nguyen, H.T. & Willey, K. 2008, 'Advanced obstacle avoidance for a laser based wheelchair using optimised Bayesian neural networks', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology", pp. 3463-3466.
In this paper we present an advanced method of obstacle avoidance for a laser based intelligent wheelchair using optimized Bayesian neural networks. Three neural networks are designed for three separate sub-tasks: passing through a door way, corridor and wall following and general obstacle avoidance. The accurate usable accessible space is determined by including the actual wheelchair dimensions in a real-time map used as inputs to each networks. Data acquisitions are performed separately to collect the patterns required for specified sub-tasks. Bayesian frame work is used to determine the optimal neural network structure in each case. Then these networks are trained under the supervision of Bayesian rule. Experiment results showed that compare to the VFH algorithm our neural networks navigated a smoother path following a near optimum trajectory. &copy; 2008 IEEE.
Trieu, H.T., Nguyen, H.T. & Willey, K. 2008, 'Shared control strategies for obstacle avoidance tasks in an intelligent wheelchair', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology", pp. 4254-4257.
In this paper we present a method of shared control strategy for an intelligent wheelchair to assist a disable user in performing obstacle avoidance tasks. The system detects obstacles in front of the wheelchair using a laser range finder sensor. As the wheelchair moves the information from the laser range finder is combined with data from the encoders mounted in its driving wheels to build a 360&deg; real-time map. The accuracy of the map is improved by eliminating the systematic error that would result from both the uncertainty of effective wheelbase and unequal driving wheel diameters. The usable wheelchair accessible space is determined by including the actual wheelchair dimensions in producing the real-time map. In making a decision the shared control method considers the user's intentions via the head-movement interface, accessible space of the environment and user safety. The experiments show promising results in the intelligent wheelchair system. &copy; 2008 IEEE.
Nguyen, T.H., Nguyen, J.S. & Nguyen, H.T. 2008, 'Bayesian recursive algorithm for width estimation of freespace for a power wheelchair using stereoscopic cameras', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology", pp. 4234-4237.
This paper is concerned with the estimation of freespace based on a Bayesian recursive (BR) algorithm for an autonomous wheelchair using stereoscopic cameras by severely disabled people. A stereo disparity map processed from both the left and right camera images is constructed to generate a 3D point map through a geometric projection algorithm. This is then converted to a 2D distance map for the purpose of freespace estimation. The width of freespace is estimated using a BR algorithm based on uncertainty information and control data. Given the probabilities of this width computed, a possible movement decision is then made for the mobile wheelchair. Experimental results obtained in an indoor environment show the effectiveness of this estimation algorithm. &copy; 2008 IEEE.
Wijesuriya, N., Tran, Y., Thuraisingham, R.A., Nguyen, H.T. & Craig, A. 2008, 'Effects of mental fatigue on 8-13Hz brain activity in people with spinal cord injury', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology", pp. 5716-5719.
Brain computer interfaces (BCIs) can be implemented into assistive technologies to provide 'hands-free' control for the severely disabled. BCIs utilise voluntary changes in one's brain activity as a control mechanism to control devices in the person's immediate environment. Performance of BCIs could be adversely affected by negative physiological conditions such as fatigue and altered electrophysiology commonly seen in spinal cord injury (SCI). This study examined the effects of mental fatigue from an increase in cognitive demand on the brain activity of those with SCI. Results show a trend of increased alpha (8-13Hz) activity in able-bodied controls after completing a set of cognitive tasks. Conversely, the SCI group showed a decrease in alpha activity due to mental fatigue. Results suggest that the brain activity of SCI persons are altered in its mechanism to adjust to mental fatigue. These altered brain conditions need to be addressed when using BCIs in clinical populations such as SCI. The findings have implications for the improvement of BCI technology &copy; 2008 IEEE.
Nguyen, H.T., Ghevondian, N. & Jones, T.W. 2008, 'Detection of nocturnal hypoglycemic episodes (natural occurrence) in children with Type 1 diabetes using an optimal Bayesian neural network algorithm', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology", pp. 1311-1314.
Hypoglycemia or low blood glucose is dangerous and can result in unconsciousness, seizures and even death. It is a common and serious side effect of insulin therapy in patients with diabetes. HypoMon is a non-invasive monitor that measures some physiological parameters continuously to provide detection of hypoglycemic episodes in Type 1 diabetes mellitus patients (T1DM). Based on heart rate and corrected QT interval of the ECG signal, we have continued to develop Bayesian neural network detection algorithms to recognize the presence of hypoglycemic episodes. From a clinical study of 16 children with T1DM, natural occurrence of nocturnal hypoglycemic episodes are associated with increased heart rates (1.033&plusmn;0.242 vs. 1.082&plusmn;0.298, P0.06) and increased corrected QT intervals (1.031&plusmn;0.086 vs. 1.060&plusmn;0.084, P0.001). The overall data were organized into a training set (8 patients) and a test set (another 8 patients) randomly selected. Using the optimal Bayesian neural network with 10 hidden nodes which was derived from the training set with the highest log evidence, the sensitivity (true positive) value for detection of hypoglycemia in the test set is 89.2%. &copy; 2008 IEEE.
Wan, S. & Nguyen, H.T. 2008, 'Human computer interaction using hand gesture', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology", pp. 2357-2360.
Hand gesture is a very natural form of human interaction and can be used effectively in human computer interaction (HCI). This project involves the design and implementation of a HCI using a small hand-worn wireless module with a 3-axis accelerometer as the motion sensor. The small stand-alone unit contains an accelerometer and a wireless Zigbee transceiver with microcontroller. To minimize intrusiveness to the user, the module is designed to be small (3cm by 4 cm). A time-delay neural network algorithm is developed to analyze the time series data from the 3-axis accelerometer. Power consumption is reduced by the noncontinuous transmission of data and the use of low-power components, efficient algorithm and sleep mode between sampling for the wireless module. A home control interface is designed so that the user can control home appliances by moving through menus. The results demonstrate the feasibility of controlling home appliances using hand gestures and would present an opportunity for a section of the aging population and disabled people to lead a more independent life. &copy; 2008 IEEE.
Tran, Y., Wijesuryia, N., Thuraisingham, R.A., Craig, A. & Nguyen, H.T. 2008, 'Increase in regularity and decrease in variability seen in electroencephalography (EEG) signals from alert to fatigue during a driving simulated task', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology", pp. 1096-1099.
Driver fatigue is a prevalent problem and a major risk for road safety accounting for approximately 20-40% of all motor vehicle accidents. One strategy to prevent fatigue related accidents is through the use of countermeasure devices. Research on countermeasure devices has focused on methods that detect physiological changes from fatigue, with the fast temporal resolution from brain signals, using the electroencephalogram (EEG) held as a promising technique. This paper presents the results of nonlinear analysis using sample entropy and second-order difference plots quantified by central tendency measure (CTM) on alert and fatigue EEG signals from a driving simulated task. Results show that both sample entropy and second-order difference plots significantly increases the regularity and decreases the variability of EEG signals from an alert to a fatigue state. &copy; 2008 IEEE.
Nguyen, N., Nguyen, H.T. & Su, S. 2008, 'Neuro-sliding mode multivariable control of a powered wheelchair', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology", pp. 3471-3474.
This paper proposes a neuro-sliding mode multivariable control approach for the control of a powered wheelchair system. In the first stage, a systematic decoupling technique is applied to the wheelchair system in order to reduce the multivariable control problem into two independent scalar control problems. Then two Neuro-Sliding Mode Controllers (NSMCs) are designed for these independent subsystems to guarantee system robustness under model uncertainties and unknown external disturbances. Both off-line and on-line trainings are involved in the second stage. Realtime experimental results confirm that robust performance for this multivariable wheelchair control system under model uncertainties and unknown external disturbances can indeed be achieved. &copy; 2008 IEEE.
Skinner, B., Nguyen, H.T. & Liu, D. 2007, 'Classification of EEG signals using a genetic-based machine learning classifier', Proceedings of the 29th International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Lyon, France, pp. 3120-3123.
View/Download from: UTS OPUS or Publisher's site
This paper investigates the efficacy of the geneticbased learning classifier system XCS, for the classification of noisy, artefact-inclusive human electroencephalogram (EEG) signals represented using large condition strings (108bits). EEG signals from three participants were recorded while they performed four mental tasks designed to elicit hemispheric responses. Autoregressive (AR) models and Fast Fourier Transform (FFT) methods were used to form feature vectors with which mental tasks can be discriminated. XCS achieved a maximum classification accuracy of 99.3% and a best average of 88.9%. The relative classification performance of XCS was then compared against four non-evolutionary classifier systems originating from different learning techniques. The experimental results will be used as part of our larger research effort investigating the feasibility of using EEG signals as an interface to allow paralysed persons to control a powered wheelchair or other devices.
Nguyen, H.T., Ghevondian, N., Jones, T.W. & Skladnev, V. 2007, 'Comparison of the overnight and daytime physiological responses of children with type 1 diabetes using the HYpoMon - Results of the glucose clamp studies', Diabetes, Abstract Book, 67th Scientific Sessions, The American Diabetes Association's 67th Scientific Sessions, American Diabetes Association, Chicago, USA, pp. 117-117.
Twenty five T1DM children (14.4 &Acirc;&plusmn; 1.6 years), HbA1c 7.65 % (5.9-12.7) volunteered for the 4-hour hyperinsulinaemic clamp studies. The HypoMon&Acirc;&reg; measured the ECG (QTc-interval), heart rate (R-R interval) and the skin impedance, while the actual blood glucose levels (BGL) were collected as reference (Yellow Springs Instruments) during the five glycemic phases: 30 minute baseline (115 &Acirc;&plusmn; 31.4 mg/dL), 60 minute euglycemia (97.6 &Acirc;&plusmn; 16.4 mg/dL), 30 minute ramp phase (72.7 &Acirc;&plusmn; 13.6 mg/dL), 40 minute hypoglycemia (49.9 &Acirc;&plusmn; 5.9 mg/dL) and further 30 minute euglycemia (94.2 &Acirc;&plusmn; 20.5 mg/dL). The counterregulatory hormones and the standardised symptoms questionnaires were also obtained for hypoglycemia unaware analysis. These results were applied to the learning algorithm in a 2 stage process: learning phase (15 patients) and test phase (10 patients). All three parameters demonstrated significant changes from the euglycemia to hypoglycemia phase. The heart rate, QTc-interval and skin imp. changed by +14.2% (&Icirc;&iexcl; < 0.004), +8.2% (&Icirc;&iexcl;< 0.001) and &acirc;24.4% (&Icirc;&iexcl; < 0.05) respectively. The trained algorithm, applied to the test patients detected hypoglycemia with a sensitivity and specificity of 0.77 and 0.94 respectively.
Skinner, B., Nguyen, H.T. & Liu, D. 2007, 'Hybrid optimisation method using PGA and SQP algorithm', Proceedings of the IEEE Symposium on Foundations of Computational Intelligence, Symposium on Foundations of Computational Intelligence, IEEE, Honolulu, Hawaii, USA, pp. 73-80.
View/Download from: UTS OPUS
This paper investigates the hybridisation of two very different optimisation methods, namely the Parallel Genetic Algorithm (PGA) and Sequential Quadratic Programming (SQP) algorithm. The different characteristics of genetic-based and traditional quadratic programming-based methods are discussed and to what extent the hybrid method can benefit the solving of optimisation problems with nonlinear complex objective and constraint functions. Experiments show the hybrid method effectively combines the robust and global search property of Parallel Genetic Algorithms with the high convergence velocity of the Sequential Quadratic Programming Algorithm, thereby reducing computation time, maintaining robustness and increasing solution quality.
Nguyen, H.T., Ghevondian, N., Nguyen Thanh, S. & Jones, T.W. 2007, 'Detection of hypoglycemic episodes in children with type 1 diabetes using an optimal Bayesian neural network algorithm', Proceedings of the 29th International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Lyon, France, pp. 3140-3143.
View/Download from: UTS OPUS or Publisher's site
Hypoglycemia or low blood glucose is a common and serious side effect of insulin therapy in patients with diabetes. HypoMon is a non-invasive monitor that measures some physiological parameters continuously to provide detection of hypoglycemic episodes in Type 1 diabetes mellitus patients (T1DM). Based on heart rate, corrected QT interval of the ECG signal and skin impedance, a Bayesian neural network detection algorithm has been developed to recognize the presence of hypoglycemic episodes. From a clinical study of 25 children with T1DM, associated with hypoglycemic episodes, their heart rates increased (1.152&Acirc;&plusmn;0.157 vs. 1.035&Acirc;&plusmn;0.108, P<0.0001), their corrected QT intervals increased (1.088&Acirc;&plusmn;0.086 vs. 1.020&Acirc;&plusmn;0.062, P<0.0001) and their skin impedances reduced significantly (0.679&Acirc;&plusmn;0.195 vs. 0.837&Acirc;&plusmn;0.203, P<0.0001). The overall data were organized into a training set (14 cases) and a test set 14 cases) randomly selected. Using an optimal Bayesian neural network with 11 hidden nodes, and an algorithm developed from the training set, a sensitivity of 0.8346 and specificity of 0.6388 were achieved for the test set.
Trieu, T., Nguyen, H.T. & Willey, K. 2007, 'Obstacle avoidance for power wheelchair using Bayesian neural network', Proceedings of the 29th International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Lyon, France, pp. 4771-4774.
View/Download from: UTS OPUS or Publisher's site
In this paper we present a real-time obstacle avoidance algorithm using a Bayesian neural network for a laser based wheelchair system. The raw laser data is modified to accommodate the wheelchair dimensions, allowing the freespace to be determined accurately in real-time. Data acquisition is performed to collect the patterns required for training the neural network. A Bayesian frame work is applied to determine the optimal neural network structure for the training data. This neural network is trained under the supervision of the Bayesian rule and the obstacle avoidance task is then implemented for the wheelchair system. Initial results suggest this approach provides an effective solution for autonomous tasks, suggesting Bayesian neural networks may be useful for wider assistive technology applications.
Nguyen, N., Nguyen, H.T. & Su, S.W. 2007, 'Advanced robust tracking control of a powered wheelchair', Proceedings of the 29th International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Lyon, France, pp. 4767-4770.
View/Download from: UTS OPUS or Publisher's site
In this paper, the dynamic multivariable model of the wheelchair system is obtained including the presence of transportation lags. The triangular diagonal dominance (TDD) decoupling technique is applied to reduce this multivariable control problem into two independent scalar control problems. An advanced robust control technique for the wheelchair has been developed based on the combination of a TDD decoupling strategy and neural network controller design. The results obtained from the real-time implementation confirm that robust performance for this multivariable wheelchair control system can indeed be achieved.
Nguyen, T., Nguyen, J., Pham, M.D. & Nguyen, H.T. 2007, 'Real-time obstacle detection for an autonomous wheelchair using stereoscopic cameras', Proceedings of the 29th International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Lyon, France, pp. 4775-4778.
View/Download from: UTS OPUS or Publisher's site
This paper is concerned with the development of a real-time obstacle avoidance system for an autonomous wheelchair using stereoscopic cameras by severely disabled people. Based on the left and right images captured from stereoscopic cameras mounted on the wheelchair, the optimal disparity is computed using the Sum of Absolute Differences (SAD) correlation method. From this disparity, a 3D depth map is constructed based on a geometric projection algorithm. A 2D map converted from this 3D map can then be employed to provide an effective obstacle avoidance strategy for this wheelchair. Experiment results obtained in a practical environment show the effectiveness of this real-time implementation.
Craig, D.A. & Nguyen, H.T. 2007, 'Adaptive EEG thought pattern classifier for advanced wheelchair control', Proceedings of the 29th International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Engineering in Medicine and Biology Society Annual Conference, IEEE, Lyon, France, pp. 2544-2547.
View/Download from: UTS OPUS or Publisher's site
This paper presents a real-time Electroencephalogram (EEG) classification system, with the goal of enhancing the control of a head-movement controlled power wheelchair for patients with chronic Spinal Cord Injury (SCI). Using a 32 channel recording device, mental command data was collected from 10 participants. This data was used to classify three different mental commands, to supplement the five commands already available using head movement control. Of the 32 channels that were recorded only 4 were used in the classification, achieving an average classification rate of 82%. This paper also demonstrates that there is an advantage to be gained by doing adaptive training of the classifier. That is, customizing the classifier to a person previously unseen by the classifier caused their average recognition rates to improve from 52.5% up to 77.5%.
Tran, Y.H., Thuraisingham, R., Wijesuriya, N.S., Nguyen, H.T. & Craig, A.R. 2007, 'Detecting neural changes during stress and fatigue effectively: a comparison of spectral analysis and sample entropy', Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering of the IEEE Engineering in Medicine and Biology Society, IEEE EMBS Neural Engineering Conference, IEEE, Kohala Coast, Hawaii, USA, pp. 350-353.
View/Download from: UTS OPUS or Publisher's site
Brain computer interface (BCI) technology as its name implies, relies upon decoding brain signals into operational commands. Aside from needing effective means of control, successful BCIs need to remain stable in varying physiological conditions. BCIs need to be developed with mechanisms to recognise and respond to physiological states (such as stress and fatigue) that can disrupt user capability. This paper compares a spectral analysis of EEG signals technique with a nonlinear method of sample entropy to detect changes in brain dynamics during moments of stress and fatigue. The results demonstrated few changes in the spectral frequency bands of the EEG during fatigue and stress conditions. However, when the EEG signals were analysed with the nonlinear technique of sample entropy the results indicated a reduction of complexity during moments of fatigue and stress and an increase in complexity during moments of engagement to the task.
Tran, Y.H., Thuraisingham, R., Boord, P.R., Nguyen, H.T. & Craig, A.R. 2007, 'Using fractal analysis to improve switching rates in hands-free environmental control technology for the severely disabled', Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering of the IEEE Engineering in Medicine and Biology Society, IEEE EMBS Neural Engineering Conference, IEEE, Kohala, Hawaii, USA, pp. 406-409.
View/Download from: UTS OPUS or Publisher's site
A negative impact on the quality of life of the severely neurologically disordered such as spinal cord injured persons is the loss of the ability to control devices in their immediate environment. Consequently, we have conducted research on technology designed to restore some measure of independence by providing hands free control over these devices by using EEG signals associated with eye closure (EC) and eye opening (EO). In a previous study we demonstrated that the nonlinear technique fractal dimension analysis was a viable alternative to spectral analysis in detecting these signals in the EEG of able bodied persons. This paper explores the efficacy of using fractal dimension to detect EC/EO signals in a spinal cord injured population. The fractal dimension method was found to improve from the standard spectral analysis technique in that there was a significant reduction is the occurrence of false positive and false negative switching. This improved detection of EC/EO in the brain activity of severely disabled people will be utilised in our technology for remote switching of electrical devices.
Nguyen, H.T., Ghevondian, N., Nguyen Thanh, S. & Jones, T.W. 2007, 'Optimal Bayesian neural-network detection of hypoglycemia in children with type 1 diabetes using a non-invasive and continuous monitor (HypoMon)', Diabetes, Abstract Book, 67th Scientific Sessions, The American Diabetes Association's 67th Scientific Sessions, American Diabetes Association, Chicago, USA, pp. 115-115.
Twenty-five children with T1DM (14.4+/-1.6 years) volunteered for the 4-hour glucose clamp study to provide 28 sets of physiological responses. HypoMon was used to measure the physiological parameters, while the actual blood glucose (BG) levels were collected as reference using Yellow Spring Instruments. The main parameters used for the detection of hypoglycemia are the skin impedance, heart rate, rate-corrected QT interval and their rates of change. A neural network algorithm was developed to detect hypoglycemic episodes (BG<=60 mg/dl). Associated with the above clinical study, the heart rates of the children increased (1.152&Acirc;&plusmn;0.157 vs. 1.035&Acirc;&plusmn;0.108, P<0.0001), their corrected QT intervals increased (1.088&Acirc;&plusmn;0.086 vs. 1.020&Acirc;&plusmn;0.062, P<0.0001) and their skin impedances reduced significantly (0.679&Acirc;&plusmn;0.195 vs. 0.837&Acirc;&plusmn;0.203, P<0.0001). The overall dataset was organized into a training set (14 cases) and a test set (14 cases) randomly selected. We applied the evidence framework for Bayesian inference to the training set and found the feed forward neural network architecture with 11 hidden nodes yielded the highest evidence. Using this optimal neural network architecture, the estimated BG profiles produced a significant correlation (p<0.0001) against measured values. The corresponding ROC Curve area for the training set was 0.9135 with 95% CI of (0.8748, 0.9521) and the optimum cut-off point was -0.09082. For the test set, this neural network algorithm produced a sensitivity of 0.8346 and a specificity of 0.6388.
Nguyen, H.T., Ghevondian, N. & Jones, T.W. 2007, 'Detection of nocturnal hypoglycemia in children with type 1 diabetes using a non-invasive glucose monitor', Diabetes, Abstract Book, 67th Scientific Sessions, The American Diabetes Association's 67th Scientific Sessions, American Diabetes Association, Chicago, USA, pp. 119-119.
A neural network algorithm was developed to detect nocturnal hypoglycemic episodes (BG<=60 mg/dl). Useful information was limited to a 5-hour window from the start of the euglycemia phase to a part of the recovery phase. Associated with the above clinical study, the normalized heart rates of the children increased (1.145&Acirc;&plusmn;0.101 vs. 1.044&Acirc;&plusmn;0.110, P<0.0001), their corrected QT intervals increased (1.153&Acirc;&plusmn;0.138 vs. 1.101&Acirc;&plusmn;0.131, P<0.02) and their skin impedances reduced significantly (0.900&Acirc;&plusmn;0.067 vs. 0.924&Acirc;&plusmn;0.066, P<0.05). The overall dataset was organized into a training set (3 cases) and a validation set (2 cases) randomly selected. Using an optimal neural network architecture with 11 hidden nodes, the estimated BG profiles produced a significant correlation against measured values. The corresponding ROC Curve area for the training set was 0.8565 with 95% CI of (0.7808, 0.9321) and the optimum cut-off point was -0.7897. For the validation set, this neural network algorithm produced a sensitivity of 0.8947 and a specificity of 0.5147. The above result indicates the potential that nocturnal hypoglycemia in children with T1DM can be detected non-invasively and continuously from the physiological parameters measured by HypoMon.
Skinner, B., Nguyen, H.T. & Liu, D. 2007, 'Distributed classifier migration in XCS for classification of electroencephalographic signals', Proceedings of the IEEE Congress on Evolutionary Computation, IEEE Congress on Evolutionary Computation, IEEE, Singapore, pp. 2829-2836.
View/Download from: UTS OPUS or Publisher's site
This paper presents an investigation into combining migration strategies inspired by multi-deme parallel genetic algorithms with the XCS learning classifier system to provide parallel and distributed classifier migration. Migrations occur between distributed XCS classifier sub-populations using classifiers ranked according to numerosity, fitness or randomly selected. The influence of the degree-of-connectivity introduced by fully-connected, bi-directional ring and uni-directional ring topologies is examined. Results indicate that classifier migration is an effective method for improving classification accuracy, improving learning speed and reducing final classifier population size, in the single-step classification of noisy, artefact- inclusive human electroencephalographic signals. The experimental results will be used as part of our larger research effort investigating the feasibility of using EEG signals as an interface to allow paralysed persons to control a powered wheelchair or other devices.
Nguyen, N.T., Nguyen, H.T. & Su, S. 2007, 'Advanced robust tracking control of a powered wheelchair system', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 4767-4770.
View/Download from: Publisher's site
In this paper, the dynamic multivariable model of the wheelchair system is obtained including the presence of transportation lags. The triangular diagonal dominance (TDD) decoupling technique is applied to reduce this multivariable control problem into two independent scalar control problems. An advanced robust control technique for the wheelchair has been developed based on the combination of a TDD decoupling strategy and neural network controller design. The results obtained from the real-time implementation confirm that robust performance for this multivariable wheelchair control system can indeed be achieved. &copy; 2007 IEEE.
Trieu, H.T., Nguyen, H.T. & Willey, K. 2007, 'Obstacle avoidance for power wheelchair using Bayesian neural network', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 4771-4774.
View/Download from: Publisher's site
In this paper we present a real-time obstacle avoidance algorithm using a Bayesian neural network for a laser based wheelchair system. The raw laser data is modified to accommodate the wheelchair dimensions, allowing the freespace to be determined accurately in real-time. Data acquisition is performed to collect the patterns required for training the neural network. A Bayesian frame work is applied to determine the optimal neural network structure for the training data. This neural network is trained under the supervision of the Bayesian rule and the obstacle avoidance task is then implemented for the wheelchair system. Initial results suggest this approach provides an effective solution for autonomous tasks, suggesting Bayesian neural networks may be useful for wider assistive technology applications. &copy; 2007 IEEE.
Nguyen, H.T., Ghevondian, N., Nguyen, S.T. & Jones, T.W. 2007, 'Detection of hypoglycemic episodes in children with type 1 diabetes using an optimal Bayesian neural network algorithm', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 3140-3143.
View/Download from: Publisher's site
Hypoglycemia or low blood glucose is a common and serious side effect of insulin therapy in patients with diabetes. HypoMon is a non-invasive monitor that measures some physiological parameters continuously to provide detection of hypoglycemic episodes in Type 1 diabetes mellitus patients (TlDM). Based on heart rate, corrected QT interval of the ECG signal and skin impedance, a Bayesian neural network detection algorithm has been developed to recognize the presence of hypoglycemic episodes. From a clinical study of 25 children with T1DM, associated with hypoglycemic episodes, their heart rates increased (1.152&plusmn;0.157 vs. 1.035&plusmn;0.108, P<0.0001), their corrected QT intervals increased (1.088&plusmn;0.086 vs. 1.020&plusmn;0.062, P<0.0001) and their skin impedances reduced significantly (0.67&plusmn;0.195 vs. 0.837&plusmn;0.203, P<0.0001). The overall data were organized into a training set (14 cases) and a test set 14 cases) randomly selected. Using an optimal Bayesian neural network with 11 hidden nodes, and an algorithm developed from the training set, a sensitivity of 0.8346 and specificity of 0.6388 were achieved for the test set. &copy; 2007 IEEE.
Nguyen, A., Ha, Q.P. & Nguyen, H.T. 2006, 'Virtual-head robot tracking and three-point l-l control for multiple mobile robots', Dis 2006: Ieee Workshop On Distributed Intelligent Systems: Collective Intelligence And Its Applications, Proceedings, IEEE Workshop on Distributed Intelligent Systems, IEEE Computer Soc, Prague, CZECH REPUBLIC, pp. 73-78.
View/Download from: UTS OPUS
In the context of robotic formation control, the commonly-used virtual robot tracking combined with l-l control has limitations in the establishment of a line formation, the possibility of collision between robots, and the singularity cases involved. Thi
Nguyen, H.T., Ghevondian, N. & Jones, T.W. 2006, 'Neural-network detection of hypoglycemic episodes in children with type 1 diabetes using physiological responses', Proceedings of the 28th IEEE EMBS Annual International Conference, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, New York, USA, pp. 6053-6056.
View/Download from: UTS OPUS or Publisher's site
The most common and highly feared adverse effect of intensive insulin therapy in patients with diabetes is the increased risk of hypoglycemia. Symptoms of hypoglycemia arise from the activation of the autonomous central nervous systems and from reduced cerebral glucose consumption. HypoMon is a non-invasive monitor that measures some physiological parameters continuously to provide detection of hypoglycemic episodes in Type 1 diabetes mellitus patients (T1DM). Based on heart rate, corrected QT interval of the ECG signal and skin impedance, a neural network detection algorithm has been developed to recognize the presence of hypoglycemic episodes. From a clinical study of 21 children with T1DM, associated with hypoglycemic episodes, their heart rates increased (1.16plusmn0.16 vs. 1.03plusmn0.11, P<0.0001), their corrected QT intervals increased (1.09plusmn0.09 vs. 1.02plusmn0.07, P<0.0001) and their skin impedances reduced significantly (0.66plusmn0.19 vs. 0.82plusmn0.21, P<0.0001). The overall data were obtained and grouped into a training set, a validation set and a test set, each with 7 patients randomly selected. Using a feedforward multi-layer neural network with 9 hidden nodes, and an algorithm developed from the training set and the validation set, a sensitivity of 0.9516 and specificity of 0.4142 were achieved for the test set. A more advanced neural network algorithm will be developed to improve the specificity of test sets in the near future
King, L.M., Nguyen, H.T. & Lal, S. 2006, 'Early driver fatigue detection from electroncephalography signals using artificial neural networks', Proceedings of the 28th IEEE EMBS Annual International Conference, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, New York, USA, pp. 2187-2190.
View/Download from: UTS OPUS or Publisher's site
This paper describes a driver fatigue detection system using an artificial neural network (ANN). Using electroencephalogram (EEG) data sampled from 20 professional truck drivers and 35 non professional drivers, the time domain data are processed into alpha, beta, delta and theta bands and then presented to the neural network to detect the onset of driver fatigue. The neural network uses a training optimization technique called the magnified gradient function (MGF). This technique reduces the time required for training by modifying the standard back propagation (SBP) algorithm. The MGF is shown to classify professional driver fatigue with 81.49% accuracy (80.53% sensitivity, 82.44% specificity) and non-professional driver fatigue with 83.06% accuracy (84.04% sensitivity and 82.08% specificity)
Nguyen Thanh, S., Nguyen, H.T. & Taylor, P.W. 2006, 'Bayesian Neural Network Classification of Head Movement Direction Using Various Advanced Optimisation Training Algorithms', Proceedings of the 1st IEEE/RAS-EMBS 2006 International Conference on Biomedical Robotics and Biomechatronics, International Conference on Biomedical Robotics and Biomechatronics, IEEE, Pisa, Italy, pp. 1-6.
View/Download from: UTS OPUS or Publisher's site
Head movement is one of the most effective hands-free control modes for powered wheelchairs. It provides the necessary mobility assistance to severely disabled people and can be used to replace the joystick directly. In this paper, we describe the development of Bayesian neural networks for the classification of head movement commands in a hands-free wheelchair control system. Bayesian neural networks allow strong generalisation of head movement classifications during the training phase and do not require a validation data set. Various advanced optimisation training algorithms are explored. Experimental results show that Bayesian neural networks can be developed to classify head movement commands by abled and disabled people accurately with limited training data
Ghevondian, N., Nguyen, H.T., Jones, T.W., Siafarikas, A. & Ratnam, N. 2006, 'Predicting Hypoglycemia Non-invasively in Type 1 Adolescent Diabetes Using the HypoMon', The American Diabetes Association's 66th Scientific Session, The American Diabetes Association Scientific Session, ADA, Washington, USA, pp. 1-1.
View/Download from: UTS OPUS
Nguyen, H.T., Ghevondian, N. & Jones, T.W. 2006, 'Non-invasive neural network detection of hypoglycemia in children with Type 1 Diabetes', The American Diabetes Association's 66th Scientific Session, The American Diabetes Association's 66rh Scientific Session, ADA, Washington, USA, pp. Paper 404-P.
Ghevondian, N., Nguyen, H.T., Jones, T.W., Skladnev, V., Siafarikas, A. & Ratnam, N. 2006, 'Detecting Hypoglycemia Qualitatively - is it possible?', Diabetes Technology Meeting, Diabetes Technology Meeting, Atlanta, USA.
Craig, D.A., Nguyen, H.T. & Burchey, H.A. 2006, 'Two Channel EEG thought pattern classifier', Proceedings of the 28th IEEE EMBS Annual International Conference, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, New York, USA, pp. 1291-1294.
View/Download from: UTS OPUS or Publisher's site
This paper presents a real-time electro-encephalogram (EEG) identification system with the goal of achieving hands free control. With two EEG electrodes placed on the scalp of the user, EEG signals are amplified and digitised directly using a ProComp+ encoder and transferred to the host computer through the RS232 interface. Using a real-time multilayer neural network, the actual classification for the control of a powered wheelchair has a very fast response. It can detect changes in the user's thought pattern in 1 second. Using only two EEG electrodes at positions O1 and C4 the system can classify three mental commands (forward, left and right) with an accuracy of more than 79 %
Nguyen Thanh, S., Nguyen, H.T., Taylor, P.W. & Middleton, J.W. 2006, 'Improved Head Direction Command Classification Using An Optimised Bayesian Neural Network', Proceedings of the 28th IEEE EMBS Annual International Conference, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, New York, USA, pp. 5679-5682.
View/Download from: UTS OPUS or Publisher's site
Assistive technologies have recently emerged to improve the quality of life of severely disabled people by enhancing their independence in daily activities. Since many of those individuals have limited or non-existing control from the neck downward, alternative hands-free input modalities have become very important for these people to access assistive devices. In hands-free control, head movement has been proved to be a very effective user interface as it can provide a comfortable, reliable and natural way to access the device. Recently, neural networks have been shown to be useful not only for real-time pattern recognition but also for creating user-adaptive models. Since multi-layer perceptron neural networks trained using standard back-propagation may cause poor generalisation, the Bayesian technique has been proposed to improve the generalisation and robustness of these networks. This paper describes the use of Bayesian neural networks in developing a hands-free wheelchair control system. The experimental results show that with the optimised architecture, classification Bayesian neural networks can detect head commands of wheelchair users accurately irrespective to their levels of injuries
Nguyen, H.T., Ghevondian, N. & Jones, T.W. 2006, 'Neural-network detection of hypoglycemic episodes in children with type 1 diabetes using physiological parameters', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 6053-6056.
View/Download from: Publisher's site
The most common and highly feared adverse effect of intensive insulin therapy in patients with diabetes is the increased risk of hypoglycemia. Symptoms of hypoglycemia arise from the activation of the autonomous central nervous systems and from reduced cerebral glucose consumption. HypoMon is a non-invasive monitor that measures some physiological parameters continuously to provide detection of hypoglycemic episodes in Type 1 diabetes mellitus patients (T1DM). Based on heart rate, corrected QT interval of the ECG signal and skin impedance, a neural network detection algorithm has been developed to recognize the presence of hypoglycemic episodes. From a clinical study of 21 children with T1DM, associated with hypoglycemic episodes, their heart rates increased (1.16&plusmn;0.16 vs. 1.03&plusmn;0.11, P<0.0001), their corrected QT intervals increased (1.09&plusmn;0.09 vs. 1.02&plusmn;0.07, P<0.0001) and their skin impedances reduced significantly (0.66&plusmn;0.19 vs. 0.82&plusmn;0.21, P<0.0001). The overall data were obtained and grouped into a training set, a validation set and a test set, each with 7 patients randomly selected. Using a feed-forward multi-layer neural network with 9 hidden nodes, and an algorithm developed from the training set and the validation set, a sensitivity of 0.9516 and specificity of 0.4142 were achieved for the test set. A more advanced neural network algorithm will be developed to improve the specificity of test sets in the near future. &copy; 2006 IEEE.
King, L.M., Nguyen, H.T. & Lal, S.K.L. 2006, 'Early driver fatigue detection from electroencephalography signals using artificial neural networks', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 2187-2190.
View/Download from: Publisher's site
This paper describes a driver fatigue detection system using an Artificial Neural Network (ANN). Using electroencephalogram (EEG) data sampled from 20 professional truck drivers and 35 non professional drivers, the time domain data are processed into alpha, beta, delta and theta bands and then presented to the neural network to detect the onset of driver fatigue. The neural network uses a training optimization technique called the Magnified Gradient Function (MGF). This technique reduces the time required for training by modifying the Standard Back Propagation (SBP) algorithm. The MGF is shown to classify professional driver fatigue with 81.49% accuracy (80.53% sensitivity, 82.44% specificity) and non-professional driver fatigue with 83.06% accuracy (84.04% sensitivity and 82.08% specificity). &copy; 2006 IEEE.
Nguyen, S.T., Nguyen, H.T., Taylor, P.B. & Middleton, J. 2006, 'Improved head direction command classification using an optimised Bayesian neural network', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 5679-5682.
View/Download from: Publisher's site
Assistive technologies have recently emerged to improve the quality of life of severely disabled people by enhancing their independence in daily activities. Since many of those individuals have limited or non-existing control from the neck downward, alternative hands-free input modalities have become very important for these people to access assistive devices. In hands-free control, head movement has been proved to be a very effective user interface as it can provide a comfortable, reliable and natural way to access the device. Recently, neural networks have been shown to be useful not only for real-time pattern recognition but also for creating user-adaptive models. Since multi-layer perceptron neural networks trained using standard back-propagation may cause poor generalisation, the Bayesian technique has been proposed to improve the generalisation and robustness of these networks. This paper describes the use of Bayesian neural networks in developing a hands-free wheelchair control system. The experimental results show that with the optimised architecture, classification Bayesian neural networks can detect head commands of wheelchair users accurately irrespective to their levels of injuries. &copy; 2006 IEEE.
Tran, T., Ha, Q.P. & Nguyen, H.T. 2005, 'A Cascade Sliding Mode-PID Controller for Non-overshoot Time Responses', Proceedings of the 6th International Symposium on Intelligent Technologies, International Symposium on Intelligent Technologies in Tech'05, Faculty of Science and Technology, Assumption University, Phuket, Thailand, pp. 27-33.
View/Download from: UTS OPUS
Craig, D.A. & Nguyen, H.T. 2005, 'Wireless Real-time Head Movement System using a Personal Digital Assistant (PDA) for Control of a Power Wheelchair', Proceedings of the 27th Annual International Conference of the Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Shanghai, China, pp. 6235-6238.
View/Download from: UTS OPUS or Publisher's site
Loss of mobility can occur for a variety of reasons, such as spinal cord injury or motor neurone disease. The onset of these conditions often brings with it an associated loss of personal independence, which is primarily due to the fact that the sufferer is no longer able to control their mobility. This project aims to address this problem through the creation of a head movement based wheelchair control system. Using a personal digital assistant (PDA) artificial intelligence techniques on an embedded LINUX operating system, a wireless head movement wheelchair control system has been designed and implemented. This system provides relief for sufferers of conditions which inhibit mobility through a method of wheelchair control which offers enhanced ease of use, attractiveness and independence.
King, L.M., Nguyen, H.T. & Taylor, P.W. 2005, 'Hands-free Head-movement Gesture Recognition Using Artificial Neural Networks and the Magnified Gradient Function', Proceedings of the 27th Annual International Conference of the Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Shanghai, China, pp. 2063-2066.
View/Download from: UTS OPUS or Publisher's site
This paper presents a hands-free head-movement gesture classification system using a neural network employing the magnified gradient function (MGF) algorithm. The MGF increases the rate of convergence by magnifying the first order derivative of the activation function, whilst guaranteeing convergence. The MGF is tested on able-bodied and disabled users to measure its accuracy and performance. It is shown that for able-bodied users, a classification improvement from 98.25% to 99.85% is made, and 92.08% to 97.50% for disabled users
Nguyen, H.T., Ghevondian, N. & Colagiuri, S. 2005, 'Non-invasive Detection of Hypoglycemia in Type 1 Diabetes', The American Diabetes Association's 65th Scientific Session, The American Diabetes Association's 65th Scientific Session, ADA, San Diego, USA, pp. 153-153.
Nguyen, H.T., Ghevondian, N. & Colagiuri, S. 2005, 'Evaluation of the HypoMon as a Non-invasive Hypoglycemia Monitor for Type 1 Diabetic Patients', The American Diabetes Association's 65th Scientific Session, The American Diabetes Association's 65th Scientific Session, ADA, Sandiego, USA, pp. 95-95.
Craig, D.A. & Nguyen, H.T. 2005, 'Wireless real-time head movement system using a personal digital assistant (PDA) for control of a power wheelchair', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 772-775.
Loss of mobility can occur for a variety of reasons,such as spinal cord injury or motor neurone disease. The onset of these conditions often brings with it an associated loss of personal independence, which is primarily due to the fact that the sufferer is no longer able to control their mobility. This project aims to address this problem through the creation of a head movement based wheelchair control system. Using a personal digital assistant (PDA) artificial intelligence techniques on an embedded LINUX operating system, a wireless head movement wheelchair control system has been designed and implemented. This system provides relief for sufferers of conditions which inhibit mobility through a method of wheelchair control which offers enhanced ease of use, attractiveness and independence. &copy; 2005 IEEE.
Nguyen, H.T., King, L.M. & Knight, G. 2004, 'Real-Time Head Movement System and Embedded Linux Implementation for the Control of Power Wheelchairs', Proceedings of the 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, The Institute of Electrical and Electronics Engineers, San Francisco, USA, pp. 4892-4895.
View/Download from: UTS OPUS or Publisher's site
Mobility has become very important for our quality of life. A loss of mobility due to an injury is usually accompanied by a loss of self-confidence. For many individuals, independent mobility is an important aspect of self-esteem. Head movement is a natural form of pointing and can be used to directly replace the joystick whilst still allowing for similar control. Through the use of embedded LINUX and artificial intelligence, a hands-free head movement wheelchair controller has been designed and implemented successfully. This system provides for severely disabled users an effective power wheelchair control method with improved posture, ease of use and attractiveness
Mitchell, R.A., Nguyen, H.T., Thornton, B.S., Hung, A., Lee, W.B. & Rickard, M.T. 2004, 'Mammogram Object Detection Using Dendronic Image Analysis', Proceedings of the 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, The Institute of Electrical and Electronics Engineers, San Francisco, USA, pp. 1763-1765.
View/Download from: UTS OPUS or Publisher's site
Breast cancer can be treated with better patient outcomes and significantly lower costs if detected early. Using the spatial dendronic structure, image masks can be obtained, showing regions in the mammogram image corresponding to the breast and lead marker. The technique is robust to noise and placement of the breast within the image. The technique not only reduces the size of the region to be analysed, but also provides the dendronic structure of the breast in which stealth-like masses can be found more easily.
Nguyen Thanh, S., Nguyen, H.T. & Taylor, P.W. 2004, 'Hands-Free Control of Power Wheelchairs Using Bayesian Neural Network Classification', Proceedings of the 2004 IEEE Conference on Cybernetics and Intelligent Systems (CIS2004), IEEE International Conference on Cybernetics and Intelligent Systems, IEEE, Singapore, pp. 745-749.
View/Download from: UTS OPUS or Publisher's site
This paper describes the formulation and implementation of Bayesian neural networks for head-movement classification in a hands-free wheelchair navigation system. Bayesian neural network training adjusts the weight decay parameters automatically to their near-optimal values that give the best generalisation. Moreover, no separate validation set is used so all available data can be used for training. Experimental results are presented showing that Bayesian neural network can classify the head movement accurately
Nguyen, V., Nguyen, H.T. & Ha, Q.P. 2004, 'Sliding Mode Neural Controller for Nonlinear Systems with Higher-Order and Uncertainties', Proceedings of the 2004 IEEE Conference on Robotics, Automation and Mechatronics (RAM), IEEE Conference on Robotics, Automation and Mechatronics, IEEE, Singapore, pp. 1026-1031.
View/Download from: UTS OPUS
In this paper, we propose a new neural controller architecture which is derived from an adaptive sliding mode control framework for a SISO nonlinear system with higher-order and uncertainties. This neural controller can overcome some disadvantages inherent in sliding mode controllers such as the chattering problem, complex calculation of the equivalent control term and unavailable knowledge of the upper bounds of system uncertainties. Experimental results for a coupled drives CE8 system show that a real-time neural controller has been implemented successfully.
Skinner, B., Nguyen, H.T. & Liu, D. 2004, 'Performance Study of a Multi-Deme Parallel Genetic Algorithm with Adaptive Mutation', Proceedings of the 2nd International Conference on Autonomous Robots and Agents (ICARA'04), International Conference on Autonomous Robots and Agents, Massey University, Palmerston North, New Zealand, pp. 88-94.
View/Download from: UTS OPUS
Nguyen, H.T., Ghevondian, N. & Colagiuri, S. 2004, 'Early Detection of Hypoglycemia Using Physiological Parameters', Proceedings of the American Diabetes Association's 64th Scientific Session 2004, The American Diabetes Association's 64th Scientific Session 2004, American Diabetes Association, Orlando, Florida, USA, pp. 463-463.
Ghevondian, N., Nguyen, H.T. & Colagiuri, S. 2004, 'The HypoMon®: A Novel Non-Invasive Hypoglycemia Monitor Using Machine Intelligence', Proceedings of the American Diabetes Association's 64th Scientific Session 2004, The American Diabetes Association's 64th Scientific Session 2004, American Diabetes Association, Orlando, Florida, USA, pp. 437-437.
Ghevondian, N., Nguyen, H.T. & Colagiuri, S. 2004, 'A Novel Non-Invasive Methodology For The Detection of Hypoglycaemia: The HypoMon®', Proceedings of the ADS & ADEA Annual Scientific Meeting 2004, ADS &ADEA Annual Scientific Meeting 2004, EPSM 2004 Conference Handbook, Sydney, Australia, pp. 372-372.
Nguyen, H.T., Ghevondian, N. & Colagiuri, S. 2004, 'Detection of Hypoglycaemia Using Physiological Parameters and A Neural Network Classifer', Proceedings of the ADS and ADEA Annual Scientific Meeting 2004, ADS and ADEA Annual Scientific Meeting 2004, Australian Diabetes Society and Australian Diabetes Educators Association, Sydney, Australia, pp. 368-368.
Craig, D.A. & Nguyen, H.T. 2004, 'Hands-free Power Wheelchair Control Using a Linux Bases Personal Digital Assistant (PDA)', Engineering and Physical Sciences in Medicine 2004, Engineering and Physical Sciences in Medicine 2004, Australian College of Physical Scientists and Engineers in Me, Geelong, Victoria, Australia, pp. 101-101.
Taylor, P.W. & Nguyen, H.T. 2004, 'Adaptive Training of Neural Network Classifiers for Power Wheelchair Control', Engineering and Physical Sciences in Medicine 2004, Engineering and Physical Sciences in Medicine 2004, EPSM 2004 Conference Handbook, Geelong, Victoria, Australia, pp. 128-128.
King, L.M. & Nguyen, H.T. 2004, 'Hands-free Control of Wheelchair Using Embedded Linux', Engineering and Physical Sciences in Medicine 2004, Engineering and Physical Sciences in Medicine 2004, EPSM 2004 Conference Handbook, Geelong, Victoria, Australia, pp. 129-129.
Poudel, G.R. & Nguyen, H.T. 2004, 'Bioimpedance Spectrometer for Tissue Impedance Analysis', Engineering and Physical Sciences in Medicine 2004, Engineering and Physical Sciences in Medicine 2004, EPSM 2004 Conference Handbook, Geelong, Victoria, Australia, pp. 157-157.
Patwardhan, V., Nguyen, H., Zhang, L., Kelkar, N. & Nguyen, L. 2004, 'Constrained collapse solder joint formation for wafer-level-chip-scale packages to achieve reliability improvement', Proceedings - Electronic Components and Technology Conference, pp. 1479-1485.
Wafer-Level-Chip-Scale-Packages (WLCSP) are rapidly proving to be the package of choice for portable electronics applications. National Semiconductor's micro SMD package family has been a front-runner in the development of this package type. These packages have a proven reliability in the lower pin-count range (up to 36 I/O) when used in conjunction with standard surface mount assembly (SMT). However, extending this technology to higher pin-counts is a significant challenge. Since the preferred assembly method is to not employ an additional underfill step after reflow soldering, the options available to enhance the package reliability are limited. Several options including a pre-applied epoxy layer that will flow and form the underfill layer during solder reflow are under investigation as a potential solution. This approach has constraints in terms of compatibility with flux type used and the reflow profile used. Another approach involves creating a non-reflow-able underfill layer. This is the approach described in this paper, and it has proven to work with all commercial assembly processes and to all extents and purposes is transparent to the surface mount assembly method used. This approach is based on the creation of an epoxy layer in either a film or paste layer form that acts as a layer surrounding and partially submerging the solder bumps. This layer achieves two results that directly impact the reliability of the WLCSP assembly. The primary advantage is the increase in solder joint height achieved, which improves the fatigue life when subjected to thermal excursions. The other major advantage is that with the solder bump being constrained from collapsing completely, the angle of wetting formed on the die side is increased, resulting in a more 'cylindrical' or barrel-shaped joint rather than a shape like a truncated sphere. Finite element modeling [1] has also borne out that a higher wetting angle results in higher reliability. There also appears to be an i...
Taylor, P.W. & Nguyen, H.T. 2003, 'Performance of a Head-Movement Interface for Wheelchair Control', Proceedings of the 25th Annual International Conference of The IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Cancun, Mexico, pp. 1590-1593.
View/Download from: UTS OPUS or Publisher's site
Head movement has been used as a control interface for people with motor impairments in a range of applications. Chin operated joysticks and switch arrays have been incorporated in control systems for electric wheelchairs but have several disadvantages, including being difficult to operate and aesthetically unattractive. A prototype wheelchair control interface has been developed that makes use of an artificial neural network (ANN) to recognize commands given by head movement. This paper presents the results of an experimental investigation of the ANN's performance in terms of classification accuracy and delay. It goes on to compare the results of disabled with able-bodied users, and assesses the effect of providing real-time feedback to the user. The results obtained indicate that ANN techniques can be used to classify head movements sufficiently quickly and accurately to be used in a practical interface. The provision of graphical real-time feedback does not appear to be crucial, but may be of benefit for particular cases.
Martinez-Coll, A., Papacosta, C. & Nguyen, H.T. 2003, 'Surface Electromyography (sEMG) of the Sterocleidomastoid (SCM) Muscle for Variable Control Using Head Movement Technology', Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Cancun, Mexico, pp. 1598-1601.
View/Download from: UTS OPUS or Publisher's site
We have explored the feasibility of an alternative strategy using biological signals such as sEMG of the sternocleidomastoid muscle (SCM) for variable control of our head movement system. Seven volunteers were instrumented with bilateral sEMG sensors on the SCM. Basic neck movements of lateral tilts and graded head rotations were performed. Data were normalized as a percentage of maximum voluntary contractions (MVC) for right and left sides, respectively. The contribution from ipsilateral sEMG signal as percentage of full-range was ?75% for left and 55% for right head tilts. During head rotations at 30, 45, and 60&deg; to both sides, results for sEMG signal amplitude as a percentage of MVC showed excellent reproducibility of the contralateral SCM at approximately 10%, 18%, and 32% on both sides. Despite the small number of subjects for a thorough statistical analysis, no differences exist in t-tests between sEMG (as % of MVC) right and left sides during head rotation; however, differences do exist for each level of rotation (p<0.01). Head rotation provided the most consistent sEMG signal correlation with the degree of motion in all subjects, allowing for reproducible proportional control for our head movement technology.
Mitchell, R.A., Nguyen, H.T., Thornton, B.S., Hung, A., Lee, W.B. & Rickard, M.T. 2003, 'Faster Image Dendrogram Creation: An Efficient Algorithm for the Detection of Tumours in Digital Mamography', Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Cancun, Mexico, pp. 714-716.
View/Download from: UTS OPUS or Publisher's site
Dendronic image analysis has been shown to provide a robust technique in the detection of tumours within digital mammograms. It provides the capability of fully automated image analysis through hierarchical segmentation. However, its general acceptance in image analysis has not been realised due to computational intensity in creating the image dendrogram. We have developed an efficient technique that can create image dendrograms a great deal faster than traditional repetitive segmentation algorithms, making dendronic analysis of digital mammograms a viable tool in the detection of breast cancer.
Martinez-Coll, A., Morgan, M. & Nguyen, H.T. 2003, 'Near Infrared Spectroscopy (NIRS) Measurements During Global Cerebral Ischemia in Sheep', Advances in Experimental Medicine and Biology: Oxygen Transport to Tissue XXIII, Oxygen Transport to Tissue, Kluwer Academic/Plenum Publishers, Philadelphia, USA, pp. 349-354.
View/Download from: UTS OPUS
Nguyen, H.T., Knight, G. & Ekanayake, S.R. 2003, 'Telemetric Head Movement Control of Powered Wheelchair', Proceedings of the World Congress on Medical Physics and Biomedical Engineering, World Congress on Medical Physics and Biomedical Engineering, World Congress on Medical Physics & Biomedical, Sydney, Australia, pp. 0-0.
Taylor, P.W. & Nguyen, H.T. 2003, 'Neural-Nework Classification of Head Control for Wheelchair Control', Proceedings of the World Congress on Medical Physics and Biomedical Engineering, World Congress on Medical Physics and Biomedical Engineering, IEAust, Sydney, Australia, pp. 0-0.
Martinez-Coll, A., Papacosta, C. & Nguyen, H.T. 2003, 'Feasibility of Bilateral Sternoceleidomastoid (SCM) Surface Electromyography (sEMG) for Variable Control of Powered Wheelchair Using Head Movement Technology', Proceedings of the World Congress on Medical Physics and Biomedical Engineering, World Congress on Medical Physics and Biomedical Engineering, World Congress on Medical Physics and Biomedical Engineering, Sydney, Australia, pp. 0-0.
Nguyen, V., Ha, Q.P. & Nguyen, H.T. 2003, 'A Chattering-Free Variable Structure Controller for Tracking of Robotic Manipulators', Proceedings of The Australian Conference on Robotics and Automation (ACRA 2003), Australasian Conference on Robotics and Automation, ARAA Australian Robotics and Automation Association, Brisbane, Australia, pp. 1-6.
View/Download from: UTS OPUS
Samali, B., Djajakesukma, S., Nguyen, H.T. & Li, J. 2003, 'An Experimental Study of a Five Storey Steel Frame Using Semi-active Control System', Proceedings of the 10th Asia Pacific Vibration Conference, Asia Pacific Vibration Conference, Queensland University of Technology, Gold Coast, Queensland, Australia, pp. 604-609.
View/Download from: UTS OPUS
Djajakesukma, S., Samali, B. & Nguyen, H.T. 2002, 'Vibration control of five storey model with semi-active stiffness damper', Applied Mechanics: Progress and Applications, The Third Australasian Congress on Applied mechanics, World Scientific, Sydney, Australia, pp. 653-658.
View/Download from: UTS OPUS
Martinez-Coll, A., Nguyen, H.T., Huang, Y., Plekhanov, S. & Hunyor, S.N. 2002, 'Time-varying stroke volume using sonomicrometry with direct cardiac compression (DOC)', EMBS 2002 BMES, 24th Annual International of the Engineering in Medicine and Biology Society, Institute of Electrical and Electronic Engineering, Houston, Texas, USA, pp. 1567-1568.
View/Download from: UTS OPUS
Nguyen, H.T., Mitchell, R.A., Thornton, B.S., Hung, A., Lee, W.B. & Rickard, M.T. 2002, 'Detection of masses in digitised mammograms using dendronic image analysis', EMBS 2002 BMES, 24th Annual International of the Engineering in Medicine and Biology Society, Institute of Electrical and Electronic Engineering, Houston, Texas, USA, pp. 1051-1052.
View/Download from: UTS OPUS
Samali, B., Djajakesukma, S. & Nguyen, H.T. 2002, 'Robustness of semi-active stiffness damper with system uncertainty', Advances in Mechanics of Structures and Materials, The 17th Australasian Conference on the Mechanics of Structures and Materials, A.A. Balkema Publishers, Gold Coast, Australia, pp. 763-768.
View/Download from: UTS OPUS
Li, J., Djajakesukma, S., Samali, B. & Nguyen, H.T. 2002, 'Modeling and Identificaion of MR Damper for Semi-Active Control Devices', The 6th International Conference on Motion and Vibration Control MOVIC 2002, MOVIC, Japan.
Tong, Q., Ma, B., Hong, S., Nguyen, L., Nguyen, H. & Negasi, A. 2002, 'Encapsulant materials and processes for wafer level-chip scale packaging (WL-CSP)', Proceedings - Electronic Components and Technology Conference, pp. 1366-1372.
View/Download from: Publisher's site
Wafer Level-Chip Scale Packaging (WL-CSP) has become a popular packaging option in recent years due to its lower profile, faster signal transfer, and smaller size. These features represent the current industry trend toward high performance and miniaturization. Encapsulant materials are usually required to enhance CSP package reliability for thermal cycling and drop resistance. In addition, the encapsulant also provides a certain measure of environmental protection. Among current CSP packaging options such as standard underfill wicking and the so-called no-flow process, the wafer pre-apply process is the most cost-effective packaging method. The wafer level process increases production output and reduces the overall assembly cost significantly, while achieving comparable or better reliability. This paper provides details on the requirements of underfills applied to WL-CSPs, the properties of the new class of materials developed, the optimal wafer process and assembly conditions, and the reliability data obtained to date on WL-CSPs.
Nguyen, L., Nguyen, H., Negasi, A., Tong, Q. & Hong, H. 2002, 'Wafer level underfill-processing and reliability', Proceedings of the IEEE/CPMT International Electronics Manufacturing Technology (IEMT) Symposium, pp. 53-62.
Underfill materials play a major role in the reliability of flip chip packages. These adhesives have been the subject of much research and development in the last few years, and improvement in material performance has been obtained. However, the assembly method still remains unchanged, with the underfill being dispensed at the individual die level after flip chip reflow. Even with the arrival of "no-flow" underfills, assembly still requires depositing the underfill material onto the flip chip site prior to positioning the flip chip die. Processing underfill at the wafer level brings in a new paradigm shift to the area of flip chip packaging. Precoating the wafer with the underfill will create significant savings in both time and money. The application cycle time of the wafer level process becomes equivalent to one single dispensing operation. This paper will present and discuss the latest results obtained with stencil printing used as the application method for the wafer level process. Several experimental underfill formulations were tested as a function of various printing conditions. With the optimal process conditions, the desired coating thickness can be applied without damage to bumped wafers. Assembly challenges together with reliability data are presented.
Nguyen, L. & Nguyen, H. 2002, 'Effect of underfill fillet configuration on flip chip package reliability', Proceedings of the IEEE/CPMT International Electronics Manufacturing Technology (IEMT) Symposium, pp. 291-303.
With flip chip processing, sufficient underfill material needs to be present during assembly to ensure a fillet around the die. The volume of underfill used governs the fillet shape, regardless of the application method, e.g., standard capillary deposition, no-flow, or wafer level underfill. There has been more interest with the latter method due to the paradigm shift in processing. Advantages and challenges exist with wafer level underfill. One concern is the fillet shape obtainable for a given pre-applied film thickness and flow characteristics, which are governed by the curing mechanisms. This paper will present experimental and modeling results of the effects of fillet configurations on flip chip reliability. Configurations with and without fillets were made with different underfills on flip chip dies on ceramic substrates. The packages were thermally cycled, electrically tested, and scanned with acoustic microscopy to check for interfacial delamination. Finite element models were also generated for the different configurations and materials to provide relative merits on the material/configuration aspects. The results indicated that the presence of fillets is as equally important as the selection of the underfill material for the best thermal cycling performance. Thus, ensuring that the proper coating thickness is obtained will be critical to good die filleting and package reliability in wafer level underfill processing.
Nguyen, H.T., Hung, A., Thornton, B.S., Lee, W.B., Rickard, M.T. & Berry, M. 2001, 'Detection of stellates and masses in digitised mammograms', Proceedings of 23th Annual International Conference, IEEE Engineering in Medicine and Biology Society, 23th Annual International Conference, IEEE Engineering in Medicine and Biology Society, IEEE, Istanbul, Turkey, pp. 0-0.
View/Download from: UTS OPUS
Ghevondian, N., Nguyen, H.T. & Colagiuri, S. 2001, 'A novel fuzzy neural network estimator for predicting hypoglycaemia in insulin-induced subjects', Proceedings of 23th Annual International Conference, IEEE Engineering in Medicine and Biology Society, 23th Annual International Conference, IEEE Engineering in Medicine and Biology Society, IEEE, Istanbul, Turkey, pp. 0-0.
View/Download from: UTS OPUS
Samali, B., Djajakesukma, S. & Nguyen, H.T. 2001, 'Effectiveness of semi-active stiffness damper in five-storey model', Proceedings of Computational Mechanics, Computational Mechanics, Elservier Science Ltd., Sydney, pp. 1425-1430.
View/Download from: UTS OPUS
Samali, B., Djajakesukma, S. & Nguyen, H.T. 2001, 'A four-node hybrids stress finite element with penalized functions', Proceedings of Computational Mechanics, Computational Mechanics, Elservier Science Ltd., Sydney, pp. 1697-1702.
View/Download from: UTS OPUS
Ha, Q.P., Trinh, H.M., Zhu, J. & Nguyen, H.T. 2001, 'Dynamic output feedback on single link flexible manipulators', Proceedings of the Australian Conference on Robotics and Automation ACRA'01, Australasian Conference on Robotics and Automation, Australian Robotics & Automation Association, Sydney, pp. 7-12.
View/Download from: UTS OPUS
Martinez-Coll, A. & Nguyen, H.T. 2001, 'Comparison of near infrared spectroscopy(NIRS) signal quantitation by multilinear regression and neural networks', Proceedings of 23th Annual International Conference, IEEE Engineering in Medicine and Biology Society, 23th Annual International Conference, IEEE Engineering in Medicine and Biology Society, IEEE, Istanbul, Turkey, pp. 0-0.
View/Download from: UTS OPUS
Nguyen, H.T., Hung, W.T., Thornton, B.S., Lee, W., Rickard, M., Berry, M.W., IEEE, IEEE & IEEE 2001, 'Detection of stellates and masses in digitised mammograms', PROCEEDINGS OF THE 23RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-4, pp. 2709-2711.
Ghevondian, N., Nguyen, H.T. & Colagiuri, S. 2001, 'A novel fuzzy neural network estimator for predicting hypoglycaemia in insulin-induced subjects', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 1657-1660.
Predicting the onset of hypoglycaemia can avoid major health complications in Type 1 insulin-dependent-diabetes-mellitus (IDDM) patients. This paper describes the design of a novel fuzzy neural network estimator algorithm (FNNE) for predicting the glycaemia profile and onset of hypoglycaemia in insulin-induced subjects, by modelling the changes in heart rate and skin impedance parameters. Hypoglycaemia was induced briefly in 12 volunteers (group A: 6 non-diabetic subjects and group B: 6 Type 1 IDDM patients) using insulin infusion. Their skin impedances, heart rates and actual blood glucose levels (BGL) were monitored at regular intervals. The FNNE algorithm was trained using all subjects from group A and validated/tested on the remaining subjects from group B. The mean error of estimation of BGL profile for the training data set (group A) was 0.107 ( < 0.05) and for the validation/test data set (group B) was 0.139 ( < 0.05). Furthermore, the FNNE algorithm was able to predict the onset of hypoglycemia episodes in group A and group B with a mean error of 0.071 ( < 0.03) and 0.176 ( < 0.05) respectively.
Martinez-Coll, A. & Nguyen, H.T. 2001, 'Comparison of near infrared spectroscopy (NIRS) signal quantitation by multilinear regression and neural networks', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 1625-1628.
Signal quantitation in most near infrared spectroscopy (NIRS) instruments is achieved through solving simultaneous equations or multiple regression analysis. The aim of this study was to compare NRIS signal quantitation by conventional multiple regression to artificial neural networks. Sixteen adult sheep were used in the study of the effects of changes in cerebral blood flow and metabolism through induction of seizures, ischemia, and hypercapnia. NIRS-derived signal attenuation for relative blood volume (BV) and oxygen desaturation (DESAT) were compared to simultaneous blood flow values measured by laser Doppler flowmetry and venous oxygen saturation (SvO2) determined from direct blood gas analysis. The regression for flow provided a zero p-value, a variance S=17.57 and F statistic=50.49. The residuals vs. fits plots suggest that the current model would underestimate values below the mean and overestimate those above the mean. An improved regression model for SvO2 provided a zero p-value, a variance S=14.1 and F statistic=4.26. Two different neural networks were implemented for flow and oxygen saturation. Both networks "tracked" their values closely and with low cycle errors. Neural networks are powerful tools for evaluation of rapidly changing, variance environments.
Nguyen, H.T., Ha, Q.P., Rye, D. & Durrant-Whyte, H. 2000, 'Low level control of electrohydraulic systems', Japan-USA-Vietnam Workshop on research and education in systems, computation and control engineering, Institute of Applied Mechanics NCSR Vietnam, HochiMinh City Vietnam, pp. 281-291.
Nguyen, H.T. & Zadrozny, S. 2000, 'Robust Neural Network Controller with an Optimal Architecture determined by Genetic Algorithms', International Conference on Advances in Intelligent Systems: Theory and Applications - AISTA 2000, International Conference on Advances in Intelligent Systems: Theory and Applications, N/A, Canberra, pp. 357-362.
Nguyen, H.T. & Smith, D. 2000, 'Real-time Playing Robot using Neural Network Algorithms', Proceedings of the International Conference on Advances in Intelligent Systems: Theory and Applications, International Conference on Advances in Intelligent Systems: Theory and Applications, M. Mohammadian, Canberra, pp. 13-18.
Nguyen, H.T. 2000, 'Robust Controllers for Uncertain Dynamical Systems, with Applications to Offshore and Overhead Cranes', Proceedings of the 5th International Conference on Motion and Vibration Control '2000, International Conference on Motion and Vibration Control, UTS, Sydney, pp. 39-50.
Samali, B., Djajakesukma, S. & Nguyen, H.T. 2000, 'A Comparison of Control Laws for a Semi-Active Stiffness Damper', Proceedings of the 5th International Conference on Motion and Vibration Control '2000, UTS, Sydney, pp. 737-742.
Samali, B., Al-Dawod, M., Nguyen, H.T. & Murphy, G. 2000, 'Design and Performance Verification of an Active Mass Damper', Proceedings of the 5th International Conference on Motion and Vibration Control '2000, International Conference on Motion and Vibration Control, UTS, Sydney, pp. 837-842.
Wu, H., Samali, B. & Nguyen, H.T. 2007, 'Shake Table Tests on the Seismic Response of a Five Storey Benchmark Model Isolated with Rubber Bearing', Proceedings of the 5th International Conference on Motion and Vibration Control '2000, International Conference on Motion and Vibration Control, UTS, Sydney, pp. 353-358.
Samali, B., Wu, H. & Nguyen, H.T. 2007, 'Analytical Study of the Seismic Response of a Base Isolated Five-Storey Benchmark Model', Proceedings of the 5th International Conference on Motion and Vibration Control '2000, International Conference on Motion and Vibration Control, UTS, Sydney, pp. 463-468.
Djajakesukma, S., Samali, B. & Nguyen, H.T. 2000, 'Application of a Semi Active Stiffness Damper to a Five Storey Benchmark Model', Proceedings of the 5th International Conference on Motion and Vibration Control '2000, International Conference on Motion and Vibration Control, UTS, Sydney, pp. 569-574.
Nguyen, L. & Nguyen, H. 2000, 'Solder joint shape formation under constrained boundaries in wafer level underfill', Proceedings - Electronic Components and Technology Conference, pp. 1320-1325.
Standard underfill processing occurs at the package level and is slow since it relies on the capillary flow of the resin. The dispensing operation requires from 30 to 120 seconds depending on the die geometry, bump pattern, standoff, and material characteristics. Even with the 'no-flow' materials introduced recently in the market, processing is still carried out at the unit level. Upon completion of the underfill operation, batch curing is done for an additional amount of time. Thus, when multiplied by the number of dies on a wafer, the total process time can be quite substantial. Wafer level deposition of underfill is the next paradigm shift in flip chip packaging, offering both cost savings and higher throughput than with the conventional process. The resin is applied to the wafer and soft-cured prior to singulation. Final cure of the film is achieved during assembly reflow. A number of challenges do exist in this new process relating to material formulation and processing. This paper discusses the issue of solder wettability during reflow, while the solder balls are being constrained by a polymeric underfill layer.
Wu, Y., Samali, B., Li, J. & Nguyen, H.T. 1999, 'Modal Analysis of XBJ2 Automobile', International Conference on Application of Modal Analysis '99, The University of Queensland, Queensland, Australia.
Ghevondian, N. & Nguyen, H. 1999, 'Modelling of blood glucose profiles non-invasively using a neural network algorithm', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, p. 928.
Monitoring blood glucose levels of Insulin-Dependent-Diabetes-Mellitus (IDDM) is essential for detecting onset of hypoglycaemia and hyperglycaemia. We have developed a method based on neural network algorithm for estimating blood glucose levels non-invasively using only physiological parameters such as skin impedance and heart rate. Results have shown that an accuracy of 10% can be achieved.
Martinez-Coll, A., Morgan, M.K., Nguyen, H. & Hunyor, S.N. 1999, 'Near infrared spectroscopy (NIRS) measurements following subarachnoid hemorrhage (SAH): Potential for the detection of vasospasm', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, p. 826.
Bilateral NIRS measurements of relative blood volume (BV) and oxygen saturation (DESAT) from frontal, temporal and parietal regions were acquired daily (n = 42) in 4 SAH patients (supine and with the head elevated 30 degrees) and compared with subtraction angiography for the detection of vasospasm. Significant differences in NIRS signals were found exclusively in one patient who developed vasospasm. There were significant differences in DESAT (right vs. left temporal region [supine], p = .003); while head elevated data revealed side to side differences for individual wavelengths as well as for BV and DESAT in the temporal and frontal regions, respectively. Differences were also found between periods of spasm and non-spasm for BV in the left parietal (p = .035) and left frontal (p = .023) region. Angiographically confirmed vasospasm was confined to the internal carotid and middle cerebral arteries on the left side. NIRS showed differences only in the affected side, and although not able to identify the location of the spasm, the technique may prove useful in the routine, daily assessment, of these patients.
Martinez-Coll, A., Morgan, M.K., Cooper, P.G., Nguyen, H.T. & Hunyor, S.N. 1999, 'Cerebral tissue oxygen saturation (SrO2) from near infrared spectroscopy (NIRS) measurements following 90 degrees-head-up tilt.', Advances in experimental medicine and biology, pp. 125-131.
Joseph, T. & Nguyen, H. 1998, 'Neural network control of wheelchairs using telemetric head movement', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 2731-2733.
Powered wheelchairs are traditionally used by people with insufficient upper body strength and dexterity to operate a manual wheelchair. However, the operation of these wheelchairs can still be a difficult and stressful task. Head movement is a natural form of pointing and can be used to directly replace the joystick whilst still allowing for similar control. Through the use of artificial intelligence, a trainable wheelchair controller can be designed which provides an alternative control method with improved posture, ease of use and attractiveness. A computer simulation of this head-controlled wheelchair has been successfully designed and tested. It consists of a motion detector for head motion measurement, a telemetry system for the elimination of wiring, and neural networks to provide the system with the ability to be trained for each individual operator irrespectively of their disability.
Nguyen, H.T., Butler, M., Roychoudhry, A., Shannon, A.G., Flack, J. & Mitchell, P. 1997, 'Classification of diabetic retinopathy using neural networks', PROCEEDINGS OF THE 18TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOL 18, PTS 1-5, pp. 1548-1549.
Nguyen, H.T., Coates, P., Luzio, S. & Owens, D.R. 1996, 'Reduced sampling protocol for the identification of insulin sensitivity', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 2028-2029.
Recent prospective studies have demonstrated that low insulin sensitivity is highly predictive for the eventual development of non-insulin dependent diabetes mellitus (NIDDM). In this paper, we propose an new 13-sample protocol for the efficient estimation of insulin sensitivity in normal subjects and NIDDM patients. Compared to other reduced sampling protocols, the new protocol estimates insulin sensitivity and glucose effectiveness with better correlation and lower bias.
Nguyen, H.T. & Sands, D. 1993, 'Real-time self-organized fuzzy logic controller for DC servo', IEE Conference Publication, pp. 174-179.
Fuzzy logic controllers (FLC) have been used to provide solutions to control systems which are either ill-defined or too complex to model. For better control quality, self-organizing fuzzy logic controllers (SOFLC) have been developed recently to include a self-learning process within the fuzzy logic network. A major disadvantage of a self-organizing fuzzy logic controller is that it is highly computational intensive. In this paper, we concentrate on the development of a real-time implementation of a self-organizing fuzzy logic controller for a DC servo. In particular, we propose an efficient algorithm for implementation of the essential rule reinforcer module of the self-organising process. Experimental results show that even with limited knowledge on the system plane, the controller is able to yield good performance with strong robustness.
Nguyen, H.T. & Bartolo, F. 1993, 'Torque control strategy for motor starters', IEE Conference Publication, pp. 480-484.
In heavy industries such as coal mining or quarry products, solid-state motor starters for induction motors have been used extensively to bring conveyor systems to full speed because of their softstart capability. A major problem for industrial motor starters using the standard voltage ramping technique is that they usually experience inconsistent overall motor run-up time and instability near full speed. Current industrial solutions for this problem require the use of current feedback or tacho feedback. In this paper, we show that the standard voltage ramp currently used in industrial motor starters does not correlate to the run-up time, nor guarantees substantial reduction of torque and current surges. Digital implementation of a voltage ramping power starter indeed confirms the validity of these results. A torque-control strategy is then proposed for motor starter which would provide substantial reduction of torque and current surges, at the same time would guarantee the required run-up time of the induction motor without the use of a tacho-generator. Experimental results show that an effective torque-controlled power starter can be implemented successfully.
Tao, Z. & Nguyen, H.T. 1993, 'Fuzzy control for tracking and handling of moving objects', IEEE Pac Rim Conf Commun Comput Signal Process, pp. 35-38.
A robot system equipped with an overhead CCD camera which is able to recognize, track and handle objects on a moving conveyor belt has been built. For image processing, a line segment-coded description based on chain coded technique is proposed to recognize the unknown objects in different shapes. In the robot control part, a fuzzy logic controller is designed to control the end-effector tracking and handling of moving objects. The whole system is controlled by a 16-bit personal computer, and works in real time. The advantage of the fuzzy control method is that it is easy to implement with high tracking quality without the need for accurate modelling of the robot dynamics.

Journal articles

Wang, C., Matveev, A.S., Savkin, A.V., Clout, R. & Nguyen, H.T. 2016, 'A semi-autonomous motorized mobile hospital bed for safe transportation of head injury patients in dynamic hospital environments without bed switching', Robotica.
View/Download from: UTS OPUS or Publisher's site
We present a novel motorized semi-autonomous mobile hospital bed guided by a human operator and a reactive navigation algorithm. The proposed reactive navigation algorithm is launched when the sensory device detects that the hospital bed is in the potential danger of collision. The semi-autonomous hospital bed is able to safely and quickly deliver critical neurosurgery (head trauma) patients to target locations in dynamic uncertain hospital environments such as crowded hospital corridors while avoiding en-route steady and moving obstacles. We do not restrict the nature or the motion of the obstacles, meaning that the shapes of the obstacles may be time-varying or deforming and they may undergo arbitrary motions. The only information available to the navigation system is the current distance to the nearest obstacle. Performance of the proposed navigation algorithm is verified via theoretical studies. Simulation and experimental results also confirm the performance of the reactive navigation algorithm in real world scenarios.
Ling, S.H., Chan, K.Y., Leung, F.H.F., Jiang, F. & Nguyen, H. 2016, 'Quality and robustness improvement for real world industrial systems using a fuzzy particle swarm optimization', Engineering Applications of Artificial Intelligence, vol. 47, pp. 68-80.
View/Download from: UTS OPUS or Publisher's site
&copy; 2015 Elsevier Ltd. This paper presents a novel fuzzy particle swarm optimization with cross-mutated (FPSOCM) operation, where a fuzzy logic system developed based on the knowledge of swarm intelligence is proposed to determine the inertia weight for the swarm movement of particle swarm optimization (PSO) and the control parameter of a newly introduced cross-mutated operation. Hence, the inertia weight of the PSO can be adaptive with respect to the search progress. The new cross-mutated operation intends to drive the solution to escape from local optima. A suite of benchmark test functions are employed to evaluate the performance of the proposed FPSOCM. Experimental results show empirically that the FPSOCM performs better than the existing hybrid PSO methods in terms of solution quality, robustness, and convergence rate. The proposed FPSOCM is evaluated by improving the quality and robustness of two real world industrial systems namely economic load dispatch system and self-provisioning systems for communication network services. These two systems are employed to evaluate the effectiveness of the proposed FPSOCM as they are multi-optima and non-convex problems. The performance of FPSOCM is found to be significantly better than that of the existing hybrid PSO methods in a statistical sense. These results demonstrate that the proposed FPSOCM is a good candidate for solving product or service engineering problems which have multi-optima or non-convex natures.
Naik, G., Selvan, S. & Nguyen, H. 2016, 'Single-Channel EMG Classification With Ensemble-Empirical-Mode-Decomposition-Based ICA for Diagnosing Neuromuscular Disorders.', IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.
View/Download from: UTS OPUS or Publisher's site
An accurate and computationally efficient quantitative analysis of electromyography (EMG) signals plays an inevitable role in the diagnosis of neuromuscular disorders, prosthesis, and several related applications. Since it is often the case that the measured signals are the mixtures of electric potentials that emanate from surrounding muscles (sources), many EMG signal processing approaches rely on linear source separation techniques such as the independent component analysis (ICA). Nevertheless, naive implementations of ICA algorithms do not comply with the task of extracting the underlying sources from a single-channel EMG measurement. In this respect, the present work focuses on a classification method for neuromuscular disorders that deals with the data recorded using a singlechannel EMG sensor. The ensemble empirical mode decomposition algorithm decomposes the single-channel EMG signal into a set of noise-canceled intrinsic mode functions, which in turn are separated by the FastICA algorithm. A reduced set of five time domain features extracted from the separated components are classified using the linear discriminant analysis, and the classification results are fine-tuned with a majority voting scheme. The performance of the proposed method has been validated with a clinical EMG database, which reports a higher classification accuracy (98%). The outcome of this study encourages possible extension of this approach to real settings to assist the clinicians in making correct diagnosis of neuromuscular disorders.
Ling, S.H., San, P.P., Lam, H.K. & Nguyen, H.T. 2016, 'Hypoglycemia detection: multiple regression-based combinational neural logic approach', Soft Computing.
View/Download from: UTS OPUS or Publisher's site
&copy; 2015 Springer-Verlag Berlin Heidelberg Hypoglycemia is a common and serious side effect of type 1 diabetes. We measure physiological parameters continuously to provide detection of hypoglycemic episodes in type 1 diabetes mellitus patients using a multiple regression-based combinational neural logic approach. In this work, a neural logic network with multiple regression is applied to the development of non-invasive hypoglycemia monitoring system. It is an alarm system which measures the physiological parameters of electrocardiogram signal (heart rate and corrected QT interval) and determine the onset of hypoglycemia by the use of proposed hybrid neural logic approach. In this clinical application, a combinational neural logic network with multiple regression is systematically designed to hypoglycemia detection based on the characteristic of this application. To optimize the parameter of the hybrid combinational neural logic system, hybrid particle swarm optimization with wavelet mutation is applied to tuned the parameters of the system. To illustrate the effectiveness of the proposed method, hypoglycemia monitoring system which will be practically analyzed using real data sets collected from 15 children ((Formula presented.) years) with type 1 diabetes at the Department of Health, Government of Western Australia. With the use of proposed method, the best testing sensitivity of 79.07 % and specificity of 53.64 % were obtained.
Naik, G., Al-Timemy, A. & Nguyen, H. 2016, 'Transradial Amputee Gesture Classification Using an Optimal Number of sEMG Sensors: An Approach Using ICA Clustering.', IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.
View/Download from: UTS OPUS
Surface electromyography (sEMG) based pattern recognition studies have been widely used to improve the classification accuracy of upper limb gestures. Information extracted from multiple sensors of the sEMG recording sites can be used as inputs to control powered upper limb prostheses. However, usage of multiple EMG sensors on the prosthetic hand is not practical and makes it difficult for amputees due to electrode shift/movement, and often amputees feel discomfort in wearing sEMG sensor array. Instead, using fewer numbers of sensors would greatly improve the controllability of prosthetic devices and it would add dexterity and flexibility in their operation. In this paper, we propose a novel myoelectric control technique for identification of various gestures using the minimum number of sensors based on Independent Component Analysis (ICA) and Icasso clustering. The proposed method is a model based approach where a combination of source separation and Icasso clustering was utilized to improve the classification performance of independent finger movements for transradial amputee subjects. Two sEMG sensor combinations were investigated based on the muscle morphology and Icasso clustering and compared to Sequential Forward Selection (SFS) and greedy search algorithm. The performance of the proposed method has been validated with 5 transradial amputees, which reports a higher classification accuracy (>95%). The outcome of this study encourages possible extension of the proposed approach to real time prosthetic applications.
Savkin, A.V., Wang, C., Baranzadeh, A., Xi, Z. & Nguyen, H.T. 2016, 'Distributed formation building algorithms for groups of wheeled mobile robots', Robotics and Autonomous Systems, vol. 75, pp. 463-474.
View/Download from: UTS OPUS or Publisher's site
&copy; 2015. The paper presents a method for decentralized flocking and global formation building for a network of unicycle-like robots described by the standard kinematics equations with hard constraints on the robots linear and angular velocities. We propose decentralized motion coordination control algorithms for the robots so that they collectively move in a desired geometric pattern from any initial position. There are no predefined leaders in the group and only local information is required for the control. The effectiveness of the proposed control algorithms is illustrated via computer simulations and experiments with real robots.
Chai, R., Naik, G., Nguyen, T.N., Ling, S., Tran, Y., Craig, A. & Nguyen, H. 2016, 'Driver Fatigue Classification with Independent Component by Entropy Rate Bound Minimization Analysis in an EEG-based System.', IEEE journal of biomedical and health informatics.
View/Download from: UTS OPUS
This paper presents a two-class electroencephalography (EEG)-based classification for classifying of driver fatigue (fatigue state vs. alert state) from 43 healthy participants. The system uses independent component by entropy rate bound minimization analysis (ERBM-ICA) for the source separation, autoregressive (AR) modeling for the features extraction and Bayesian neural network for the classification algorithm. The classification results demonstrate a sensitivity of 89.7%, a specificity of 86.8% and an accuracy of 88.2%. The combination of ERBM-ICA (source separator), AR (feature extractor) and Bayesian neural network (classifier) provides the best outcome with a p-value < 0.05 with the highest value of area under the receiver operating curve (AUC-ROC=0.93) against other methods such as power spectral density (PSD) as feature extractor (AUC-ROC=0.81). The results of this study suggest the method could be utilized effectively for a countermeasure device for driver fatigue identification and other adverse event applications.
Ling, S.H., San, P.P. & Nguyen, H.T. 2016, 'Non-invasive hypoglycemia monitoring system using extreme learning machine for Type 1 diabetes.', ISA transactions.
View/Download from: UTS OPUS
Hypoglycemia is a very common in type 1 diabetic persons and can occur at any age. It is always threatening to the well-being of patients with Type 1 diabetes mellitus (T1DM) since hypoglycemia leads to seizures or loss of consciousness and the possible development of permanent brain dysfunction under certain circumstances. Because of that, an accurate continuing hypoglycemia monitoring system is a very important medical device for diabetic patients. In this paper, we proposed a non-invasive hypoglycemia monitoring system using the physiological parameters of electrocardiography (ECG) signal. To enhance the detection accuracy, extreme learning machine (ELM) is developed to recognize the presence of hypoglycemia. A clinical study of 16 children with T1DM is given to illustrate the good performance of ELM.
Argha, A., Li, L.I., Su & Nguyen 2016, 'Stabilising the networked control systems involving actuation and measurement consecutive packet losses', IET Control Theory & Applications, vol. 10, no. 11.
View/Download from: UTS OPUS
This study is devoted to the problem of designing a robust output-feedback discrete-time sliding mode control (ODSMC) for the networked systems involving both measuring and actuating data packet losses. Packet losses in the networked control systems (NCSs) have been modelled by utilising the probability and the characteristics of the sources and the destinations. Here, the well-known Bernoulli random binary distribution is used to model consecutive packet losses in the NCSs. In this study, first, a robust observer-based discrete-time sliding mode control is proposed for the NCSs including random packet losses. The packet losses occur in the channels from the sensors to the controller and the channels from the controller to the actuators. Then, using the notion of exponential mean square stability, the boundedness of the obtained closed-loop system is analysed with a linear matrix inequality approach. Our proposed robust ODSMC can be applied to unstable NCSs, and there is no need to stabilise the underlying system in advance. Illustrative examples are presented to show the effectiveness of the proposed approach.
Su, S.W., Savkin, A.V., Guo, Y., Celler, B.G. & Nguyen, H.T. 2015, 'Decentralized Integral Controllability Analysis Based on a New Unconditional Stability Criterion', IEEE Transactions on Automatic Control, vol. 60, no. 1, pp. 211-215.
View/Download from: UTS OPUS or Publisher's site
Decentralized integral control is one of the most popular control strategies used in practice. An important issue associated with this strategy is the analysis of Decentralized Integral Controllability (DIC). Campo and Morari showed that for a given process, if its steady state gain matrix is not critically D-stable, its DIC can be determined by using its steady state gain matrix. This technical note investigates decentralized integral control with a special focus on the DIC analysis of processes whose steady state gain matrices are critically D-stable. First, we introduce a new unconditional stability criterion. Then, by using the proposed criterion, it is proved that for up to four-channel processes, their DIC can be totally determined by their steady state gain matrices. We also present a multi-loop PI control design method, which provides an explicit lower bound of the proportional coefficient to achieve decentralized unconditional stability for low dimensional processes. For higher dimensional processes, this technical note presents a six-channel process whose DIC property cannot be determined only by its steady state gain matrix, contradicting the view of some other researchers.
Naik, G. & Nguyen, H. 2015, 'Nonnegative Matrix Factorization for the Identification of EMG finger movements: Evaluation using matrix analysis.', IEEE Journal of Biomedical and Health Informatics, vol. 19, no. 2, pp. 478-485.
View/Download from: UTS OPUS or Publisher's site
Surface Electromyography (sEMG) is widely used in evaluating the functional status of the hand to assist in hand gesture recognition, prosthetics and rehabilitation applications. The sEMG is a non-invasive, easy to record signal of superficial muscles from the skin surface. Considering the non-stationary characteristics of sEMG, recent feature selection of hand gesture recognition using sEMG signals necessitate designers to use Nonnegative Matrix factorization (NMF) based methods. This method exploits both the additive and sparse nature of signals by extracting accurate and reliable measurements of sEMG features using a minimum number of sensors. The testing has been conducted for simple and complex finger flexions using several experiments with Artificial Neural Network (ANN) classification scheme. It is shown, both by simulation and experimental studies, that the proposed algorithm is able to classify ten finger flexions (five simple and five complex finger flexions) recorded from two sEMG sensors up to 92% (95% for simple and 87% for complex flexions) accuracy. The recognition performances of simple and complex finger flexions are also validated with NMF permutation matrix analysis.
Handojoseno, A.M., Shine, J.M., Nguyen, T.N., Tran, Y., Lewis, S.J. & Nguyen, H.T. 2015, 'Analysis and Prediction of the Freezing of Gait Using EEG Brain Dynamics.', IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society, vol. 23, no. 5, pp. 887-896.
View/Download from: UTS OPUS or Publisher's site
Freezing of Gait (FOG) is a common symptom in the advanced stages of Parkinson's disease (PD), which significantly affects patients' quality of life. Treatment options offer limited benefit and there are currently no mechanisms able to effectively detect FOG before it occurs, allowing time for a sufferer to avert a freezing episode. Electroencephalography (EEG) offers a novel technique that may be able to address this problem. In this paper, we investigated the univariate and multivariate EEG features determined by both Fourier and wavelet analysis in the confirmation and prediction of FOG. The EEG power measures and network properties from 16 patients with PD and FOG were extracted and analyzed. It was found that both power spectral density and wavelet energy could potentially act as biomarkers during FOG. Information in the frequency domain of the EEG was found to provide better discrimination of EEG signals during transition to freezing than information coded in the time domain. The performance of the FOG prediction systems improved when the information from both domains was used. This combination resulted in a sensitivity of 86.0%, specificity of 74.4%, and accuracy of 80.2% when predicting episodes of freezing, outperforming current accelerometry-based tools for the prediction of FOG.
Tuan, H.D., Savkin, A., Nguyen, T.N. & Nguyen, H.T. 2015, 'Decentralised model predictive control with stability constraints and its application in process control', Journal of Process Control, vol. 26, pp. 73-89.
View/Download from: UTS OPUS or Publisher's site
This paper presents a novel decentralised model predictive control for a plant consisting of interconnected systems. A constructive technique for online stabilisation that is applicable to the model predictive controllers (MPC) is developed. The plant-wise stability is achievable by the newly introduced asymptotically positive realness constraint (APRC) for MPC. Simulations are provided to demonstrate the efficiency of the presented APRC.
Truong, B.C., Tuan, H.D., Fitzgerald, A.J., Wallace, V.P. & Nguyen, H.T. 2015, 'A dielectric model of human breast tissue in terahertz regime.', IEEE transactions on bio-medical engineering, vol. 62, no. 2, pp. 699-707.
View/Download from: UTS OPUS
The double Debye model has been used to understand the dielectric response of different types of biological tissues at terahertz (THz) frequencies but fails in accurately simulating human breast tissue. This leads to limited knowledge about the structure, dynamics, and macroscopic behavior of breast tissue, and hence, constrains the potential of THz imaging in breast cancer detection. The first goal of this paper is to propose a new dielectric model capable of mimicking the spectra of human breast tissue's complex permittivity in THz regime. Namely, a non-Debye relaxation model is combined with a single Debye model to produce a mixture model of human breast tissue. A sampling gradient algorithm of nonsmooth optimization is applied to locate the optimal fitting solution. Samples of healthy breast tissue and breast tumor are used in the simulation to evaluate the effectiveness of the proposed model. Our simulation demonstrates exceptional fitting quality in all cases. The second goal is to confirm the potential of using the parameters of the proposed dielectric model to distinguish breast tumor from healthy breast tissue, especially fibrous tissue. Statistical measures are employed to analyze the discrimination capability of the model parameters while support vector machines are applied to assess the possibility of using the combinations of these parameters for higher classification accuracy. The obtained analysis confirms the classification potential of these features.
Argha, A., Li, L., Su, S. & Nguyen, H. 2015, 'Controllability Analysis of Two-dimensional Systems Using 1D Approaches', IEEE Transactions on Automatic Control, vol. 60, no. 11, pp. 2977-2982.
View/Download from: UTS OPUS or Publisher's site
Working with the 1D form of 2D systems is an alternative strategy to reduce the inherent complexity of 2D systems and their applications. To achieve the 1D form of 2D systems, different from the so-called WAM model, a new row (column) process was proposed recently. The controllability analysis of this new 1D form is explored in this paper. Two new notions of controllability namedWAM-controllability and directional controllability for the underlying 2D systems are defined. Corresponding conditions on the WAM-controllability and directional controllability are derived, which are particularly useful for the control problems of 2D systems via 1D framework. According to the presented directional controllability, a directional minimum energy control input is derived for 2D systems. A numerical example demonstrates the applicability of the analysis presented in this note.
Zhou, J., Guo, A., T. Nguyen, H. & Su, S. 2015, 'Intelligent Management of Multiple Access Schemes in Wireless Body Area Network', Journal of Networks, vol. 10, no. 2.
View/Download from: UTS OPUS or Publisher's site
Naik, G.R., Baker, K.G. & Nguyen, H.T. 2015, 'Dependence Independence Measure for Posterior and Anterior EMG Sensors Used in Simple and Complex Finger Flexion Movements: Evaluation Using SDICA', IEEE Journal of Biomedical and Health Informatics, vol. 19, no. 5, pp. 1689-1696.
View/Download from: UTS OPUS or Publisher's site
Identification of simple and complex finger flexion movements using surface electromyography (sEMG) and a muscle activation strategy is necessary to control human&#8211;computer interfaces such as prosthesis and orthoses. In order to identify these movements, sEMG sensors are placed on both anterior and posterior muscle compartments of the forearm. In general, the accuracy of myoelectric classification depends on several factors, which include number of sensors, features extraction methods, and classification algorithms. Myoelectric classification using a minimum number of sensors and optimal electrode configuration is always a challenging task. Sometimes, using several sensors including high density electrodes will not guarantee high classification accuracy. In this research, we investigated the dependence and independence nature of anterior and posterior muscles during simple and complex finger flexion movements. The outcome of this research shows that posterior parts of the hand muscles are dependent and hence responsible for most of simple finger flexion. On the other hand, this study shows that anterior muscles are responsible for most complex finger flexion. This also indicates that simple finger flexion can be identified using sEMG sensors connected only on anterior muscles (making posterior placement either independent or redundant), and vice versa is true for complex actions which can be easily identified using sEMG sensors on posterior muscles. The result of this study is beneficial for optimal electrode configuration and design of prosthetics and other related devices using a minimum number of sensors.
Guo, Y., Naik, G.R., Huang, S., Abraham, A. & Nguyen, H.T. 2015, 'Nonlinear multiscale Maximal Lyapunov Exponent for accurate myoelectric signal classification', Applied Soft Computing Journal, vol. 36, pp. 633-640.
View/Download from: UTS OPUS or Publisher's site
&copy; 2015 Elsevier B.V. All rights reserved. Surface Electromyography (sEMG) is a non-invasive, easy to record signal of superficial muscles from the skin surface. The sEMG is widely used in evaluating the functional status of the hand to assist in hand gesture recognition, prosthetics and rehabilitation applications. Considering the nonlinear and non-stationary characteristics of sEMG, hand gesture recognition using sEMG signals necessitate designers to use Maximal Lyapunov Exponent (MLE) or ensemble Empirical Mode Decomposition (EMD) based MLEs. In this research, we propose a hand gesture recognition method of sEMG based on nonlinear multiscale MLE. The aim is to increase the classification accuracy of sEMG features while reducing the complexity of EMD. The nonlinear MLE features are classified using Flexible Neural Tree (FNT), which can solve highly structured dependent problems of the Artificial Neural Network (ANN). The testing has been conducted using several experiments with five participants. The classification performance of nonlinear multiscale MLE method is compared with MLE and EMD-based MLE through simulations. Experimental results demonstrate that the former algorithm outperforms the two latter algorithms and can classify six different hand gestures up to 97.6% accuracy.
Truong, B.C.Q., Tuan, H.D., Wallace, V.P., Fitzgerald, A.J. & Nguyen, H.T. 2015, 'The Potential of the Double Debye Parameters to Discriminate Between Basal Cell Carcinoma and Normal Skin', IEEE Transactions on Terahertz Science and Technology, vol. 5, no. 6, pp. 990-998.
View/Download from: UTS OPUS or Publisher's site
The potential of terahertz imaging for improving the efficiency of Mohs's micrographic surgery in terms of tumor margin detection was previously studied. Thanks to high water content of human skin, its dielectric response to terahertz radiation can be described by the double Debye model which uses five parameters to fit experimental data. Skin tumors typically have a higher water content than normal tissues do, and this should be apparent in the parameters. The goal of this paper is to apply statistical methods to these parameters to test their power to differentiate skin cancer from normal tissue. Based on the prediction accuracy estimated using a cross-validation method, we found the best classifier was the static permittivity at low frequency [Formula: see text] . By combining the most relevant parameters, we obtained a classification accuracy of 95.7%, confirming the classification capability of the parameters, thereby supporting their application to improve terahertz imaging for the purpose of skin cancer delineation.
Wang, C., Savkin, A.V., Clout, R. & Nguyen, H.T. 2015, 'An intelligent robotic hospital bed for safe transportation of critical neurosurgery patients along crowded hospital corridors', IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 23, no. 5, pp. 744-754.
View/Download from: UTS OPUS or Publisher's site
&copy; 2014 IEEE. We present a novel design of an intelligent robotic hospital bed, named Flexbed, with autonomous navigation ability. The robotic bed is developed for fast and safe transportation of critical neurosurgery patients without changing beds. Flexbed is more efficient and safe during the transportation process comparing to the conventional hospital beds. Flexbed is able to avoid en-route obstacles with an efficient easy-to-implement collision avoidance strategy when an obstacle is nearby and to move towards its destination at maximum speed when there is no threat of collision. We present extensive simulation results of navigation of Flexbed in the crowded hospital corridor environments with moving obstacles. Moreover, results of experiments with Flexbed in the real world scenarios are also presented and discussed.
Yuwono, M., Su, S.W., Moulton, B.D. & Nguyen, H.T. 2014, 'Data Clustering Using Variants of Rapid Centroid Estimation', IEEE Transactions on Evolutionary Computation, vol. 18, no. 3, pp. 366-377.
View/Download from: UTS OPUS or Publisher's site
Prior work suggests that Particle Swarm Clustering (PSC) can be a powerful tool for solving clustering problems. This paper reviews parts of the PSC algorithm, and shows how and why a new class of algorithm is proposed in an attempt to improve on the ef?ciency and repeatability of PSC. This new implementation is referred to as Rapid Centroid Estimation (RCE). RCE simpli?es the update rules of PSC, and greatly reduces computational complexity by enhancing the ef?ciency of the particle trajectories. On benchmark evaluations with an arti?cial dataset that has 80 dimensions and a volume of 5000, the RCE variants have iteration times of less than 0.1 seconds, which compares to iteration times of 2 seconds for PSC and modi?ed PSC (mPSC). On UC Irvine (UCI) machine learning benchmark datasets, the RCE variants are much faster than PSC and mPSC, and produce clusters with higher purity and greatly improved optimization speeds. For example, the RCE variants are more than 100 times faster than PSC and mPSC on the UCI breast cancer dataset. It can be concluded that the RCE variants are leaner and faster than PSC and mPSC, and that the new optimization strategies also improve clustering quality and repeatability.
Su, S.W., Celler, B.G. & Nguyen, H.T. 2014, 'A new unconditionally stable condition based on singular perturbation analysis', International Journal of Control, vol. 87, no. 3, pp. 464-472.
View/Download from: UTS OPUS or Publisher's site
Decentralised configuration with integral control action is the most commonly used control strategy in engineering practice. For decentralised integral control, a desired design target is to achieve closed-loop unconditional stability. Campo and Morari presented steady-state conditions, which can be applied to analyse unconditional stability for most multivariable processes. However, they also showed some processes for which the unconditional stability cannot be determined by only investigating the steady-state gain matrices of the processes. This paper presented an easy to use criterion to determine unconditional stability by using singular perturbation analysis and eigen-value sensitivity analysis. Based on the proposed criterion, the unconditional stability of all the examples presented by Campo and Morari can be easily determined. In the meantime, we proved a conjecture proposed by Campo and Morari (a necessary and sufficient condition for Integral Controllability) for up to all Three-Input and Three-Output systems. For higher dimensional systems, we proposed a new conjecture to simplify the verification of Campo and Moraris conjecture.
Haddad, A., Zhang, Y., Su, S.W., Celler, B.G. & Nguyen, H.T. 2014, 'Modelling and Regulating of Cardio-Respiratory Response for the Enhancement of Interval Training', Biomedical Engineering Online, vol. 13, no. 9, pp. 1-14.
View/Download from: UTS OPUS or Publisher's site
Yuwono, M., Su, S.W., Guo, Y., Moulton, B.D. & Nguyen, H.T. 2014, 'Unsupervised nonparametric method for gait analysis using a waist-worn inertial sensor', Applied Soft Computing, vol. 14, no. A, pp. 72-80.
View/Download from: UTS OPUS or Publisher's site
This paper describes a nonparametric approach for analyzing gait and identifying bilateral heel-strike events in data from an inertial measurement unit worn on the waist. The approach automatically adapts to variations in gait of the subjects by including a classifier that continuously evolves as it "learns" aspects of each individuals gait profile. The novel data-driven approach is shown to be capable of adapting to different gait profiles without any need for supervision. The approach has several stages. First, cadence episode is detected using Hidden Markov Model. Second, discrete wavelet transforms are applied to extract peak features from accelerometers and gyroscopes. Third, the feature dimensionality is reduced using principal component analysis. Fourth, Rapid Centroid Estimation (RCE) is used to cluster the peaks into 3 classes: (a) left heel-strike, (b) right heel-strike, and (c) artifacts that belongs to neither (a) nor (b). Finally, a Bayes filter is used, which takes into account prior detections, model predictions, and step timings at time segments of interest. Experimental results involving 15 participants suggest that the system is capable of detecting bilateral heel-strikes with greater than 97% accuracy.
Nguyen, N., Su, S.W. & Nguyen, H.T. 2014, 'Neural Network Based Diagonal Decoupling Control of Powered Wheelchair Systems', IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 22, no. 2, pp. 371-378.
View/Download from: UTS OPUS or Publisher's site
This paper proposes an advanced diagonal decou- pling control method for powered wheelchair systems. This control method is based on a combination of the systematic diagonaliza- tion technique and the neural network control design. As such, this control method reduces coupling effects on a multivariable system, leading to independent control design procedures. Using an obtained dynamic model, the problem of the plants Jacobian calculation is eliminated in a neural network control design. The effectiveness of the proposed control method is verified in a real-time implementation on a powered wheelchair system. The obtained results confirm that robustness and desired performance of the overall system are guaranteed, even under parameter uncertainty effects.
Shine, J.M., Handojoseno, A.M., Nguyen, N., Tran, Y.H., Naismith, S., Nguyen, H.T. & Lewis, S. 2014, 'Abnormal patterns of theta frequency oscillations during the temporal evolution of freezing of gait in Parkinson's disease', Clinical Neurophysiology, vol. 125, pp. 569-576.
View/Download from: UTS OPUS or Publisher's site
Objective: We sought to characterize the electrophysiological signature of Freezing of gait in Parkinson's disease. Methods: We examined 24 patients with idiopathic Parkinson's disease and significant freezing of gait as they performed a series of timed up-and-go tasks in their 'off' state while electroencephalographic data was collected from four scalp leads. Fast Fourier Transformation was utilized to explore the power spectral density between periods of normal walking and periods of freezing, as well as during the tran- sition between the two states. In addition, Cross Spectrum and Cross Frequency analyses were used to explore the role of impaired temporal and spatial connectivity. Results: When compared to walking, episodes of freezing were associated with a significant increase in theta band power within the central and frontal leads. The transition from normal walking to freezing of gait was also associated with increased theta frequency coupling between the central and frontal leads, along with an increase in cross-frequency coupling in the central lead. Conclusions: Episodes of freezing of gait in Parkinson's disease are associated with abnormal oscillatory activity in the brain. Significance: These results provide novel insights into the pattern of spatiotemporal dynamics underlying freezing of gait and may provide a potential means for therapeutic prediction and alleviation of freezing episodes in susceptible patients.
Pendharkar, G., Naik, G. & Nguyen, H.T. 2014, 'Using Blind Source Separation on accelerometry data to analyze and distinguish the toe walking gait from normal gait in ITW children', Biomedical Signal Processing and Control, vol. 13, pp. 41-49.
View/Download from: UTS OPUS or Publisher's site
Gait analysis is an important aspect of Biomedical Engineering. In the recent past, researchers have applied several signal processing methods for the analysis of gait activities. Sensors such as accelerometers, gyroscopes and pressure sensors are more commonly used to identify gait activities remotely. Most of the applications have multiple sensors placed on a single board which is used for gait assessment. However, the problem with multiple sensors is the cross talk introduced by one sensor due to another sensor. Some of the applications use a single sensor such as accelerometer with dual axis measuring the gait activity in horizontal and vertical planes. Depending on the orientation of the accelerometer, the two axial outputs could have overlapping spectra which is very difficult to observe. Spectral and temporal filtering is not suitable for this because of overlapping spectra due to simultaneous movements of the foot in the horizontal and vertical planes. To reliably identify the gait activities, there is a need to decompose and separate the two vertical and horizontal acceleration signals. The earlier research has described a novel method which can be used remotely to identify the gait in ITW children. This paper discusses a lab based automated classification method using Blind Source Separation (BSS) technique to identify toe walking gait from normal gait in Idiopathic Toe Walkers (ITW) children. The outcome of the research study reveals that the BSS techniques in association with K-means classifier can suitably distinguish toe-walking gait from normal gait in ITW children with 97.9 &plusmn; 0.2% accuracy.
San, P., Ling, S.S., Nuryani, N. & Nguyen, H.T. 2014, 'Evolvable rough-block-based neural network and its biomedical application to hypoglycemia detection system', IEEE Transactions on Cybernetics, vol. 44, no. 8, pp. 1338-1349.
View/Download from: UTS OPUS or Publisher's site
Zhao, L., Hoi, S.C., Li, Z., Wong, L., Nguyen, H. & Li, J. 2014, 'Coupling Graphs, Efficient Algorithms and B-cell Epitope Prediction', IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 11, no. 1, pp. 7-16.
View/Download from: UTS OPUS or Publisher's site
Chai, R., Ling, S.S., Hunter, G., Tran, Y.H. & Nguyen, H.T. 2014, 'Brain-Computer Interface Classifier for Wheelchair Commands Using Neural Network With Fuzzy Particle Swarm Optimization', IEEE Journal of Biomedical and Health Informatics, vol. 18, no. 5, pp. 1614-1624.
View/Download from: UTS OPUS or Publisher's site
This paper presents the classification of a three-class mental task-based braincomputer interface (BCI) that uses the Hilbert-Huang transform for the features extractor and fuzzy particle swarm optimization with cross-mutated-based artificial neural network (FPSOCM-ANN) for the classifier. The experiments were conducted on five able-bodied subjects and five patients with tetraplegia using electroencephalography signals from six channels, and different time-windows of data were examined to find the highest accuracy. For practical purposes, the best two channel combinations were chosen and presented. The three relevant mental tasks used for the BCI were letter composing, arithmetic, and Rubiks cube rolling forward, and these are associated with three wheelchair commands: left, right, and forward, respectively. An additional eyes closed task was collected for testing and used for onoff commands. The results show a dominant alpha wave during eyes closure with average classification accuracy above 90%. The accuracies for patients with tetraplegia were lower compared to the able-bodied subjects; however, this was improved by increasing the duration of the time-windows.TheFPSOCM-ANNprovides improved accuracies compared to genetic algorithm-based artificial neural network (GA-ANN) for three mental tasks-based BCI classifications with the best classification accuracy achieved for a 7-s time-window: 84.4% (FPSOCM-ANN) compared to 77.4% (GA-ANN).More comparisons on feature extractors and classifiers were included. For two-channel classification, the best two channels were O1 and C4, followed by second best at P3 and O2, and third best at C3 and O2. Mental arithmetic was the most correctly classified task, followed by mental Rubik's cube rolling forward and mental letter composing.
Zhang, Y., Haddad, A., Su, S.W., Celler, B.G., Coutts, A.J., Duffield, R., Donges, C.E. & Nguyen, H.T. 2014, 'An equivalent circuit model for onset and offset exercise response', BIOMEDICAL ENGINEERING ONLINE, vol. 13.
View/Download from: UTS OPUS or Publisher's site
Song, R., Liu, Q., Hutvagner, G., Nguyen, H., Ramamohanarao, K., Wong, L. & Li, J. 2014, 'Rule discovery and distance separation to detect reliable miRNA biomarkers for the diagnosis of lung squamous cell carcinoma', BMC GENOMICS, vol. 15.
View/Download from: UTS OPUS or Publisher's site
Ling, S.S.H., Chan, K.Y., Palade, V., Dillon, T., Nguyen, H.T., Nguyen, T.N. & Chen, X.W. 2014, 'Special issue on hybrid intelligent methods for health technologies', Applied Soft Computing, vol. 20, pp. 1-3.
View/Download from: UTS OPUS or Publisher's site
Lai, J.C., Leung, F.H., Ling, S.S. & Nguyen, H.T. 2013, 'Hypoglycaemia detection using fuzzy inference system with multi-objective double wavelet mutation differential evolution', Applied Soft Computing, vol. 13, no. 5, pp. 2803-2811.
View/Download from: UTS OPUS or Publisher's site
In this paper, a fuzzy inference system (FIS) is developed to recognize hypoglycaemic episodes. Hypoglycaemia (low blood glucose level) is a common and serious side effect of insulin therapy for patients with diabetes. We measure some physiological parameters continuously to provide hypoglycaemia detection for Type 1 diabetes mellitus (TIDM) patients. The FIS captures the relationship between the inputs of heart rate (HR), corrected QT interval of the electrocardiogram (ECG) signal (QTc), change of HR, change of QTc and the output of hypoglycaemic episodes to perform the classification. An algorithm called Differential Evolution with Double Wavelet Mutation (DWM-DE) is introduced to optimize the FIS parameters that govern the membership functions and fuzzy rules. DWM-DE is an improved Differential Evolution algorithm that incorporates two wavelet-based operations to enhance the optimization performance. To prevent the phenomenon of overtraining (over-fitting), a validation approach is proposed. Moreover, in this problem, two targets of sensitivity and specificity should be met in order to achieve good performance. As a result, a multi-objective optimization using DWM-DE is introduced to perform the training of the FIS. Experiments using the data of 15 children with TIDM (569 data points) are studied. The data are randomly organized into a training set with 5 patients (l99 data points), a validation set with 5 patients (177 data points) and a testing set with 5 patients (193 data points). The result shows that the proposed FIS tuned by the multi-objective DWM-DE can offer good performance of doing classification.
San, P., Ling, S.S. & Nguyen, H.T. 2013, 'Industrial application of evolvable block-based neural network to hypoglycemia monitoring system', IEEE Transactions On Industrial Electronics, vol. 60, no. 12, pp. 5892-5901.
View/Download from: UTS OPUS or Publisher's site
Insulin-dependent diabetes mellitus is classified as type 1 diabetes mellitus (T1DM), and it can be further classified as immune-mediated or idiopathic. It is dangerous and can result in unconsciousness, seizures, and even sudden death. The most common physiological parameters to be effected from a hypoglycemic reaction are heart rate and corrected QT interval of the electrocardiogram (ECG) signal. Considering the correlation between physiological parameters of an ECG signal and the status of hypoglycemia, a noninvasive hypoglycemia monitoring system is tested and introduced by proposing a hybrid particle-swarm-optimization-based block-based neural network (BBNN) algorithm. The proposed BBNN model offers advantages over conventional neural networks by performing the simultaneous optimization of both structure and weights. The hybrid particle swarm optimization with wavelet mutation searches for optimized structure and network parameters through particle information over a search space. All the actual data sets of 15 T1DM children were collected at the Department of Health, Government of Western Australia. Several experiments showed that the proposed BBNN performed well in terms of better sensitivity and specificity.
Truong, B.C., Hoang, T.D., Ha, K. & Nguyen, H.T. 2013, 'Debye Parameter Extraction for Characterizing Interaction of TeraHertz Radiation with Human Skin Tissue', IEEE Transactions On Biomedical Engineering, vol. 60, no. 6, pp. 1528-1537.
View/Download from: UTS OPUS or Publisher's site
This paper is concerned with parameter extraction for the double Debye model, which is used for analytically determining human skin permittivity. These parameters are thought to be the origin of contrast in terahertz (THz) images of skin cancer. The existing extraction methods could generate Debye models, which track their measurements accurately at frequencies higher than 1 THz but poorly at lower frequencies, where the majority of permittivity contrast between healthy and diseased skin tissues is actually observed.We propose a global optimization-based parameter extraction,which results in globally accurate tracking and thus supports the full validity of the Debye model for simulating human skin permittivity in the whole usable THz frequencies. Numerical results confirm viability of our novel methodology.
San, P., Ling, S.S. & Nguyen, H.T. 2013, 'Hybrid PSO-based variable translation wavelet neural network and its application to hypoglycemia detection system', Neural Computing & Applications, vol. 23, no. 7-8, pp. 2177-2184.
View/Download from: UTS OPUS or Publisher's site
To provide the detection of hypoglycemic episodes in Type 1 diabetes mellitus, hypoglycemia detection system is developed by the use of variable translation wavelet neural network (VTWNN) in this paper. A wavelet neural network with variable translation
Li, Z., He, Y., Liu, Q., Zhao, L., Wong, L., Kwok, C.Y., Nguyen, H.T. & Li, J. 2013, 'Structural analysis on mutation residues and interfacial water molecules for human TIM disease understanding', BMC Bioinformatics, vol. 14, no. S16, pp. 1-15.
View/Download from: UTS OPUS or Publisher's site
Background Human triosephosphate isomerase (HsTIM) deficiency is a genetic disease caused often by the pathogenic mutation E104D. This mutation, located at the side of an abnormally large cluster of water in the inter-subunit interface, reduces the thermostability of the enzyme. Why and how these water molecules are directly related to the excessive thermolability of the mutant have not been investigated in structural biology. Results This work compares the structure of the E104D mutant with its wild type counterparts. It is found that the water topology in the dimer interface of HsTIM is atypical, having a "wet-core-dry-rim" distribution with 16 water molecules tightly packed in a small deep region surrounded by 22 residues including GLU104. These water molecules are co-conserved with their surrounding residues in non-archaeal TIMs (dimers) but not conserved across archaeal TIMs (tetramers), indicating their importance in preserving the overall quaternary structure. As the structural permutation induced by the mutation is not significant, we hypothesize that the excessive thermolability of the E104D mutant is attributed to the easy propagation of atoms' flexibility from the surface into the core via the large cluster of water. It is indeed found that the B factor increment in the wet region is higher than other regions, and, more importantly, the B factor increment in the wet region is maintained in the deeply buried core. Molecular dynamics simulations revealed that for the mutant structure at normal temperature, a clear increase of the root-mean-square deviation is observed for the wet region contacting with the large cluster of interfacial water. Such increase is not observed for other interfacial regions or the whole protein. This clearly suggests that, in the E104D mutant, the large water cluster is responsible for the subunit interface flexibility and overall thermolability, and it ultimately leads to the deficiency of this enzyme.
Nguyen, J.S., Su, S.W. & Nguyen, H.T. 2013, 'Experimental study on a smart wheelchair system using a combination of stereoscopic and spherical vision.', Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, vol. 2013, pp. 4597-4600.
This paper is concerned with the experimental study performance of a smart wheelchair system named TIM (Thought-controlled Intelligent Machine), which uses a unique camera configuration for vision. Included in this configuration are stereoscopic cameras for 3-Dimensional (3D) depth perception and mapping ahead of the wheelchair, and a spherical camera system for 360-degrees of monocular vision. The camera combination provides obstacle detection and mapping in unknown environments during real-time autonomous navigation of the wheelchair. With the integration of hands-free wheelchair control technology, designed as control methods for people with severe physical disability, the smart wheelchair system can assist the user with automated guidance during navigation. An experimental study on this system was conducted with a total of 10 participants, consisting of 8 able-bodied subjects and 2 tetraplegic (C-6 to C-7) subjects. The hands-free control technologies utilized for this testing were a head-movement controller (HMC) and a brain-computer interface (BCI). The results showed the assistance of TIM's automated guidance system had a statistically significant reduction effect (p-value = 0.000533) on the completion times of the obstacle course presented in the experimental study, as compared to the test runs conducted without the assistance of TIM.
Chai, R., Ling, S.H., Hunter, G.P., Tran, Y. & Nguyen, H.T. 2013, 'Classification of wheelchair commands using brain computer interface: comparison between able-bodied persons and patients with tetraplegia.', Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, vol. 2013, pp. 989-992.
This paper presents a three-class mental task classification for an electroencephalography based brain computer interface. Experiments were conducted with patients with tetraplegia and able bodied controls. In addition, comparisons with different time-windows of data were examined to find the time window with the highest classification accuracy. The three mental tasks used were letter composing, arithmetic and imagery of a Rubik's cube rolling forward; these tasks were associated with three wheelchair commands: left, right and forward, respectively. An eyes closed task was also recorded for the algorithms testing and used as an additional on/off command. The features extraction method was based on the spectrum from a Hilbert-Huang transform and the classification algorithm was based on an artificial neural network with a fuzzy particle swarm optimization with cross-mutated operation. The results show a strong eyes closed detection for both groups with average accuracy at above 90%. The overall result for the combined groups shows an improved average accuracy of 70.6% at 1s, 74.8% at 2s, 77.8% at 3s, 79.6% at 4s and 81.4% at 5s. The accuracy for individual groups were lower for patients with tetraplegia compared to the able-bodied group, however, does improve with increased duration of the time-window.
Nguyen, V.Q., Goto, A., Nguyen, T.V., Vo, K.T., Ta, T.M., Nguyen, T.N., Nguyen, T.M., Ho, M.B., Phan, N.A., Vu, H.H., Truong, T.M. & Nguyen, H.T. 2013, 'Prevalence and correlates of zinc deficiency in pregnant Vietnamese women in Ho Chi Minh City.', Asia Pacific journal of clinical nutrition, vol. 22, no. 4, pp. 614-619.
BACKGROUND: Although Vietnam is a region with a plant-based diet that has a high zinc deficiency, epidemiological data showing how this affects pregnant women are limited. This study explores the prevalence of zinc deficiency and possible correlates in pregnant Vietnamese women in Ho Chi Minh City. METHODS: This was a cross-sectional study conducted at a general hospital in Ho Chi Minh City, Vietnam. All pregnant women who came to their first antenatal care visit from November 2011 to June 2012 were recruited. Those taking a vitamin and/or mineral supplement were excluded. Serum zinc concentrations, determined by a standard colorimetric method, of 10.7 mol/L-17.5 mol/L (70.0 g/dL-114 g/dL) were classified as normal and under 10.7 mol/L (70.0 g/dL) as zinc deficient. RESULTS: In total, 254 pregnant women were invited and 107 (42%) participated. The mean age of participants was 29 years, and mean gestational age was 10 weeks. Median zinc concentration in serum was 13.6 mol/L, and the prevalence of zinc deficiency was 29% (95% CI=21%-39%). The daily intake of a milk product supplement was the only significant correlate of zinc deficiency of the items investigated (adjusted OR=0.40, 95% CI=0.16-0.99, p=0.049). DISCUSSION: This is the first study reporting that more than 25% of pregnant Vietnamese women in Ho Chi Minh City are zinc deficient. Further academic and clinical input is needed to confirm the scale of this neglected issue and to investigate the potential of milk product supplementation in this population.
Shannon, A.G. & Nguyen, H.T. 2013, 'Empirical approaches to the application of mathematical techniques in health technologies', International Journal Bioautomation, vol. 17, no. 3, pp. 125-150.
Mathematical modeling of ageing is built in this paper around research and development activities in cooperation with pharmaceutical companies and hospitals. The interaction of "dirty data" with appropriate mathematical techniques is exemplified mainly with applications to health technologies in endocrinology and oncology. The emphasis is more on old techniques in new situations than on new techniques, though there are references to some novel approaches to modeling.
Yuwono, M., Moulton, B.D., Su, S.W., Celler, B.G. & Nguyen, H.T. 2012, 'Unsupervised machine-learning method for improving the performance of ambulatory fall-detection systems', Biomedical Engineering Online, vol. 11, pp. 1-11.
View/Download from: UTS OPUS or Publisher's site
Background: Falls can cause trauma, disability and death among older people. Ambulatory accelerometer devices are currently capable of detecting falls in a controlled environment. However, research suggests that most current approaches can tend to have insufficient sensitivity and specificity in non-laboratory environments, in part because impacts can be experienced as part of ordinary daily living activities. Method: We used a waist-worn wireless tri-axial accelerometer combined with digital signal processing, clustering and neural network classifiers. The method includes the application of Discrete Wavelet Transform, Regrouping Particle Swarm Optimization, Gaussian Distribution of Clustered Knowledge and an ensemble of classifiers including a multilayer perceptron and Augmented Radial Basis Function (ARBF) neural networks. Results: Preliminary testing with 8 healthy individuals in a home environment yields 98.6% sensitivity to falls and 99.6% specificity for routine Activities of Daily Living (ADL) data. Single ARB and MLP classifiers were compared with a combined classifier. The combined classifier offers the greatest sensitivity, with a slight reduction in specificity for routine ADL and an increased specificity for exercise activities. In preliminary tests, the approach achieves 100% sensitivity on in-group falls, 97.65% on out-group falls, 99.33% specificity on routine ADL, and 96.59% specificity on exercise ADL. Conclusion: The pre-processing and feature-extraction steps appear to simplify the signal while successfully extracting the essential features that are required to characterize a fall. The results suggest this combination of classifiers can perform better than MLP alone. Preliminary testing suggests these methods may be useful for researchers who are attempting to improve the performance of ambulatory fall detection systems.
Nuryani, N., Ling, S.S. & Nguyen, H.T. 2012, 'Electrocardiographic signals and swarm-based support vector machine for hypoglycemia detection', Annals Of Biomedical Engineering, vol. 40, no. 4, pp. 934-945.
View/Download from: UTS OPUS or Publisher's site
Cardiac arrhythmia relating to hypoglycemia is suggested as a cause of death in diabetic patients. This article introduces electrocardiographic (ECG) parameters for artificially induced hypoglycemia detection. In addition, a hybrid technique of swarm-based support vector machine (SVM) is introduced for hypoglycemia detection using the ECG parameters as inputs. In this technique, a particle swarm optimization (PSO) is proposed to optimize the SVM to detect hypoglycemia. In an experiment using medical data of patients with Type 1 diabetes, the introduced ECG parameters show significant contributions to the performance of the hypoglycemia detection and the proposed detection technique performs well in terms of sensitivity and specificity.
Craig, A.R., Tran, Y.H., Wijesuriya, N. & Nguyen, H.T. 2012, 'Regional brain wave activity changes associated with fatigue', Psychophysiology, vol. 49, pp. 574-582.
View/Download from: UTS OPUS or Publisher's site
Assessing brain wave activity is a viable strategy for monitoring fatigue when performing tasks such as driving, and numerous studies have been conducted in this area. However, results of a systematic review on changes in brain wave activity associated with fatigue have revealed equivocal findings. This study investigated brain wave activity associated with fatigue in 48 nonprofessional healthy drivers as they participated in a simulated driving task until they fatigued. The results showed that as a person fatigues, slow wave activity increased over the entire cortex, in theta and in alpha 1 and 2 bands, while no significant changes were found in delta wave activity. Substantial increases also occurred in fast wave activity, though mostly in frontal sites. The results suggest that as a person fatigues, the brain loses capacity and slows its activity, and that attempts to maintain vigilance levels lead to increased beta activity.
Ling, S.S. & Nguyen, H.T. 2012, 'Natural occurrence of nocturnal hypoglycemia detection using hybrid particle swarm optimized fuzzy reasoning model', Artificial Intelligence in Medicine, vol. 55, no. 3, pp. 177-184.
View/Download from: UTS OPUS or Publisher's site
Introduction: Low blood glucose (hypoglycemia) is a common and serious side effect of insulin therapy in patients with diabetes. This paper will make a contribution to knowledge in the modeling and design of a non-invasive hypoglycemia monitor for patients with type 1 diabetes mellitus (T1DM) using a fuzzy-reasoning system. Methods: Based on the heart rate and the corrected QT interval of the electrocardiogram (ECG) signal, we have developed a hybrid particle-swarm-optimization-based fuzzy-reasoning model to recognize the presence of hypoglycemic episodes. To optimize the fuzzy rules and the fuzzy-membership functions, a hybrid particle-swarm-optimization with wavelet mutation operation is investigated. Conclusion: We have investigated the detection for the natural occurrence of nocturnal hypoglycemic episodes in T1DM using a hybrid particle-swarm-optimization-based fuzzy-reasoning model with physiological parameters. In this study, no restricted environment (e.g. patient's dietary requirements) is required. Furthermore, the sampling time is between 5 and 10 min. To conclude, we have shown that the testing performances of the proposed algorithm for detection of advanced hypoglycemic and hypoglycemic episodes for T1DM patients are satisfactory.
Zhao, L., Wong, L., Lu, L., Hoi, S.C. & Li, J. 2012, 'B-cell epitope prediction through a graph model', BMC Bioinformatics, vol. 13, no. S17, pp. 1-12.
View/Download from: UTS OPUS or Publisher's site
Background Prediction of B-cell epitopes from antigens is useful to understand the immune basis of antibody-antigen recognition, and is helpful in vaccine design and drug development. Tremendous efforts have been devoted to this long-studied problem, however, existing methods have at least two common limitations. One is that they only favor prediction of those epitopes with protrusive conformations, but show poor performance in dealing with planar epitopes. The other limit is that they predict all of the antigenic residues of an antigen as belonging to one single epitope even when multiple non-overlapping epitopes of an antigen exist. Results In this paper, we propose to divide an antigen surface graph into subgraphs by using a Markov Clustering algorithm, and then we construct a classifier to distinguish these subgraphs as epitope or non-epitope subgraphs. This classifier is then taken to predict epitopes for a test antigen. On a big data set comprising 92 antigen-antibody PDB complexes, our method significantly outperforms the state-of-the-art epitope prediction methods, achieving 24.7% higher averaged f-score than the best existing models. In particular, our method can successfully identify those epitopes with a non-planarity which is too small to be addressed by the other models. Our method can also detect multiple epitopes whenever they exist.
Wong, M., He, S., Nguyen, H.T. & Yeh, W. 2012, 'Mass Classification in Digitized Mammograms Using Texture Features and Artificial Neural Network', Lecture Notes in Computer Science, vol. 7667, pp. 151-158.
View/Download from: UTS OPUS or Publisher's site
A technique is proposed to classify regions of interests (ROIs) of digitized mammograms into mass and non-mass regions using texture features and artificial neural network (ANN). Fifty ROIs were extracted from the MIAS MiniMammographic Database, with 25 ROIs containing masses and 25 ROIs containing normal breast tissue only. Twelve texture features were derived from the gray level co-occurrence matrix (GLCM) of each region. The sequential forward selection technique was used to select four significant features from the twelve features. These significant features were used in the ANN to classify the ROI into either mass or non-mass region. By using leave-one-out method on the 50 images using the four significant features, classification accuracy of 86% was achieved for ANN. The test result using the four significant features is better than the full set of twelve features. The proposed method is compared with some existing works and promising results are obtained
Su, S.W., Anderson, B., Chen, W. & Nguyen, H.T. 2012, 'Multi-realization Of Nonlinear Systems', Automatica, vol. 48, no. 7, pp. 1455-1461.
View/Download from: UTS OPUS or Publisher's site
The system multi-realization problem is to find a state-variable realization for a set of systems, sharing as many parameters as possible. A multi-realization can be used to efficiently implement a multi-controller architecture for multiple model adaptive control. We extend the linear multi-realization problem to nonlinear systems. The problem of minimal multi-realization of a set of MIMO systems is introduced and solved for static feedback linearizable systems.
Nguyen, L.B., Nguyen, A.V., Ling, S.H. & Nguyen, H.T. 2012, 'An adaptive strategy of classification for detecting hypoglycemia using only two EEG channels.', Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, vol. 2012, pp. 3515-3518.
Hypoglycemia is the most common but highly feared side effect of the insulin therapy for patients with Type 1 Diabetes Mellitus (T1DM). Severe episodes of hypoglycemia can lead to unconsciousness, coma, and even death. The variety of hypoglycemic symptoms arises from the activation of the autonomous central nervous system and from reduced cerebral glucose consumption. In this study, electroencephalography (EEG) signals from five T1DM patients during an overnight clamp study were measured and analyzed. By applying a method of feature extraction using Fast Fourier Transform (FFT) and classification using neural networks, we establish that hypoglycemia can be detected non-invasively using EEG signals from only two channels. This paper demonstrates that a significant advantage can be achieved by implementing adaptive training. By adapting the classifier to a previously unseen person, the classification results can be improved from 60% sensitivity and 54% specificity to 75% sensitivity and 67% specificity.
Ling, S.H., San, P.P., Nguyen, H.T. & Leung, F.H.F. 2012, 'Non-invasive nocturnal hypoglycemia detection for insulin-dependent diabetes mellitus using genetic fuzzy logic method', International Journal of Computational Intelligence and Applications, vol. 11, no. 4.
View/Download from: Publisher's site
Hypoglycemia, or low blood glucose, is the most common complication experienced by Type 1 diabetes mellitus (T1DM) patients. It is dangerous and can result in unconsciousness, seizures and even death. The most common physiological parameter to be effected from hypoglycemic reaction are heart rate (HR) and correct QT interval (QTc) of the electrocardiogram (ECG) signal. Based on physiological parameters, a genetic algorithm based fuzzy reasoning model is developed to recognize the presence of hypoglycemia. To optimize the parameters of the fuzzy model in the membership functions and fuzzy rules, a genetic algorithm is used. A validation strategy based adjustable fitness is introduced in order to prevent the phenomenon of overtraining (overfitting). For this study, 15 children with 569 sampling data points with Type 1 diabetes volunteered for an overnight study. The effectiveness of the proposed algorithm is found to be satisfactory by giving better sensitivity and specificity compared with other existing methods for hypoglycemia detection. &copy; 2012 Imperial College Press.
Nguyen, N., Su, S.W. & Nguyen, H.T. 2011, 'Robust neuro-sliding mode multivariable control strategy for powered wheelchairs', IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 19, no. 1, pp. 105-111.
View/Download from: UTS OPUS or Publisher's site
This paper proposes an advanced robust multivariable control strategy for a powered wheelchair system. The new control strategy is based on a combination of the systematic triangularization technique and the robust neuro-sliding mode control approach. This strategy effectively copes with parameter uncertainties and external disturbances in real-time in order to achieve robustness and optimal performance of a multivariable system. This novel strategy reduces coupling effects on a multivariable system, eliminates chattering phenomena, and avoids the plant Jacobian calculation problem. Furthermore, the strategy can also achieve fast and global convergence using less computation. The effectiveness of the new multivariable control strategy is verified in real-time implementation on a powered wheelchair system. The obtained results confirm that robustness and desired performance of the overall system are guaranteed, even under parameter uncertainty and external disturbance effects.
Tran, T., Hoang, T.D., Ha, Q.P. & Nguyen, H.T. 2011, 'Stabilising agent design for the control of interconnected systems', International Journal of Control, vol. 84, no. 6, pp. 1140-1156.
View/Download from: UTS OPUS or Publisher's site
This article presents a new control design strategy for stabilising large-scale interconnected systems operating in semi-automatic control modes. The large-scale system is modelled by subsystems connected to each other in an arbitrary configuration. Each subsystem is regulated by a dedicated multivariable controller that also allows for a manual control mode. The notion of asymptotically positive realness constraint (APRC) is introduced and applied for deriving the interconnection stabilisability condition in the time domain. The interactions between subsystems are taken into consideration in the stability condition. The APRC is subsequently employed in the so-called stabilising agent to accommodate the closed-loop control and man-in-the-loop coexistence. The multipliers of the APRC quadratic supply rate are updated on-the-fly to ensure that the constraint satisfaction of stabilising agents is recursively feasible. The stabilising agents are developed independently from the control law under the same auspice controller. Due to this independence, operational errors from the manual control adjustments, that may destabilise the control systems, can be avoided. The decentralised agents render stabilising bounds for the manipulated variables in the automatic control mode, and at the same time, provide warning signals and manipulation guidance for the operators to prevent possible plant-wide destabilisation in the manual control mode. Our main results are illustrated through numerical simulations for an industrial modular system.
Ling, S.S. & Nguyen, H.T. 2011, 'Genetic algorithm based multiple regression with fuzzy inference system for detection of nocturnal hypoglycemic episodes', IEEE Transactions on Information Technology in Biomedicine, vol. 15, no. 2, pp. 308-315.
View/Download from: UTS OPUS or Publisher's site
Hypoglycemia or low blood glucose is dangerous and can result in unconsciousness, seizures, and even death. It is a common and serious side effect of insulin therapy in patients with diabetes. Hypoglycemic monitor is a noninvasivemonitor that measures some physiological parameters continuously to provide detection of hypoglycemic episodes in type 1 diabetes mellitus patients (T1DM). Based on heart rate (HR), corrected QT interval of the ECG signal, change of HR, and the change of corrected QT interval, we develop a genetic algorithm (GA)-based multiple regression with fuzzy inference system (FIS) to classify the presence of hypoglycemic episodes. GA is used to find the optimal fuzzy rules and membership functions of FIS and the model parameters of regression method. From a clinical study of 16 children with T1DM, natural occurrence of nocturnal hypoglycemic episodes is associated with HRs and corrected QT intervals. The overall data were organized into a training set (eight patients) and a testing set (another eight patients) randomly selected. The results show that the proposed algorithm performs a good sensitivity with an acceptable specificity.
Ling, S.S., Jiang, F., Nguyen, H.T. & Chan, K.Y. 2011, 'Hybrid Fuzzy Logic-Based Particle Swarm Optimization For Flow Shop Scheduling Problem', International Journal of Computational Intelligence and Applications, vol. 10, no. 3, pp. 335-356.
View/Download from: UTS OPUS or Publisher's site
This paper, proposes a hybrid fuzzy logic-based particle swarm optimization (PSO) with cross-mutated operation method for the minimization of makespan in permutation flow shop scheduling problem. This problem is a typical non-deterministic polynomial-time (NP) hard combinatorial optimization problem. In the proposed hybrid PSO, fuzzy inference system is applied to determine the inertia weight of PSO and the control parameter of the proposed cross-mutated operation by using human knowledge. By introducing the fuzzy system, the inertia weight becomes adaptive. The cross-mutated operation effectively forces the solution to escape the local optimum. To make PSO suitable for solving flow shop scheduling problem, a sequence-order system based on the roulette wheel mechanism is proposed to convert the continuous position values of particles to job permutations. Meanwhile, a new local search technique namely swap-based local search for scheduling problem is designed and incorporated into the hybrid PSO. Finally, a suite of flow shop benchmark functions are employed to evaluate the performance of the proposed PSO for flow shop scheduling problems. Experimental results show empirically that the proposed method outperforms the existing hybrid PSO methods significantly.
Chan, K., Ling, S.S., Dillon, T.S. & Nguyen, H.T. 2011, 'Diagnosis Of Hypoglycemic Episodes Using A Neural Network Based Rule Discovery System', Expert Systems With Applications, vol. 38, no. 8, pp. 9799-9808.
View/Download from: UTS OPUS or Publisher's site
Hypoglycemia or low blood glucose is dangerous and can result in unconsciousness, seizures and even death for Type 1 diabetes mellitus (T1DM) patients. Based on the T1DM patients' physiological parameters, corrected QT interval of the electrocardiogram (ECG) signal, change of heart rate, and the change of corrected QT interval, we have developed a neural network based rule discovery system with hybridizing the approaches of neural networks and genetic algorithm to identify the presences of hypoglycemic episodes for TIDM patients. The proposed neural network based rule discovery system is built and is validated by using the real T1DM patients' data sets collected from Department of Health, Government of Western Australia. Experimental results show that the proposed neural network based rule discovery system can achieve more accurate results on both trained and unseen T1DM patients' data sets compared with those developed based on the commonly used classification methods for medical diagnosis, statistical regression, fuzzy regression and genetic programming. Apart from the achievement of these better results, the proposed neural network based rule discovery system can provide explicit information in the form of production rules which compensate for the deficiency of traditional neural network method which do not provide a clear understanding of how they work in prediction as they are in an implicit black-box structure. This explicit information provided by the product rules can convince medical doctors to use the neural networks to perform diagnosis of hypoglycemia on T1DM patients.
Boord, P.R., Craig, A.R., Tran, Y.H. & Nguyen, H.T. 2010, 'Discrimination of left and right leg motor imagery for brain-computer interfaces', Medical & Biological Engineering & Computing, vol. 48, no. 4, pp. 343-350.
View/Download from: UTS OPUS or Publisher's site
This article reports on a study to identify electroencephalography (EEG) signals with potential to provide new BCI channels through mental motor imagery (MMI). Leg motion was assessed to see if left and right leg MMI could be discriminated in the EEG. The study also explored simultaneous observation of leg movement as a means to enhance MMI evoked EEG signals. The results demonstrate that MMI of the left and right leg produce a contralateral preponderance of EEG alpha band desynchronization, which can be spatially discriminated. This suggests that lower extremity MMI could provide signals for additional BCI channels. The study also shows that movement imitation enhances alpha band desynchronization during MMI, and might provide a useful aid in the identification and training of BCI signals.
Su, S.W., Chen, W., Liu, D., Fang, Y., Kuang, W., Yu, X., Guo, T., Celler, B.G. & Nguyen, H.T. 2010, 'Dynamic Modelling of Heart Rate Response Under Different Exercise Intensity', The Open Medical Informatics Journal, vol. 4, pp. 81-85.
View/Download from: UTS OPUS
Heart rate is one of the major indications of human cardiovascular response to exercises. This study investigates human heart rate response dynamics to moderate exercise. A healthy male subject has been asked to walk on a motorised treadmill under a predefined exercise protocol. ECG, body movements, and oxygen saturation (SpO2) have been reliably monitored and recorded by using non-invasive portable sensors. To reduce heart rate variation caused by the influence of various internal or external factors, the designed step response protocol has been repeated three times. Experimental results show that both steady state gain and time constant of heart rate response are not invariant when walking speed is faster than 3 miles/hour, and time constant of offset exercise is noticeably longer than that of onset exercise.
Nguyen, H.T. & Su, S.W. 2009, 'Conditions for triangular decoupling control', International Journal of Control, vol. 82, no. 9, pp. 1-7.
View/Download from: UTS OPUS or Publisher's site
The main purpose of this article is to explore the relationship of two existing conditions for the triangular decoupling problem. The first one is the triangular-diagonal-dominance condition proposed by Hung and Anderson. The second one is the stable coprime factorisation-described condition proposed by Gomez and Goodwin, which has been proven as a necessary and sufficient condition for the triangular decoupling problem. This article proves that the two conditions are actually equivalent. It also provides easy-to-use criteria for assessment of the solvability of the triangular decoupling problem.
Thornton-benko, E., Nguyen, H.T., Hung, A. & Thornton, B.S. 2009, 'Improved observer dependent perception of weak edges when scanning an image in real time indicated by introducing 1/f noise into the primary visual cortex V1. Theory and experimental support', Australian Physical And Engineering Sciences in Me..., vol. 32, no. 3, pp. 136-149.
View/Download from: UTS OPUS or Publisher's site
We present results of a new process for generating 1/f type noise sequences and introducing the noise in the primary visual cortex which then enables improved perception of weak edges when an observer is scanning a complex image in real time to detect detail such as in mammogram reading sessions. It can be explained by an adaptation of information theory for functional rather than previous task-based methods for formulating processes for edge formation in early vision. This is enabled from a two "species" classification of the interaction of opposing on-centre and off-centre neuron processes. We show that non-stationary stochastic resonances predicted by theory can occur with 1/f noise in the primary visual cortex VI and suggest that signalling exchanges between VI and the lateral geniculate nucleus (LGN) of the thalamus can initiate neural activity for saccadic action (and observer attention) for weak edge perception. Improvements predicted by our theory were shown from 600 observations by two groups of observers of limited experience and an experienced radiologist for reference (but not for diagnosis). They scanned and rated the definition of microcalcification in clusters separately rated by the experienced radiologist. The results and supporting theory showed dependence on the observer's attention and orderly scanning. Using a compact simplified equipment configuration the methodology has important clinical applications for conjunction searches of features and for detection of objects in poor light conditions for vehicles.
Su, S.W., Celler, B.G., Savkin, A.V., Nguyen, H.T., Cheng, T.M., Guo, Y. & Wang, L. 2009, 'Transient and steady state estimation of human oxygen uptake based on noninvasive portable sensor measurements', Medical & Biological Engineering & Computing, vol. 47, no. 10, pp. 1111-1117.
View/Download from: UTS OPUS or Publisher's site
The main motivation of this study is to establish an ambulatory cardio-respiratory analysis system for the monitoring and evaluation of exercise and regular daily physical activity. We explored the estimation of oxygen uptake by using noninvasive portable sensors. These sensors are easy to use but may suffer from malfunctions under free living environments. A promising solution is to combine sensors with different measuring mechanisms to improve both reliability and accuracy of the estimation results. For this purpose, we selected a wireless heart rate sensor and a tri-axial accelerometer to form a complementary sensor platform. We analyzed the relationship between oxygen uptake measured by gas analysis and data collected from the simple portable sensors using multivariable nonlinear modeling approaches. It was observed that the resulting nonlinear multivariable model could not only achieve a better estimate compared with single input single output models, but also had greater potential to improve reliability.
Nguyen, H.T. & Su, S.W. 2009, 'Conditions for triangular decoupling control', INTERNATIONAL JOURNAL OF CONTROL, vol. 82, no. 9, pp. 1575-1581.
View/Download from: UTS OPUS or Publisher's site
Nguyen, H.T. 2008, 'Intelligent Technologies for Real-time Biomedical Engineering Applications', International Journal of Automation and Control, vol. 1, no. 2/3, pp. 274-285.
View/Download from: UTS OPUS or Publisher's site
Intelligent technologies are essential for many biomedical engineering applications in order to cope with a wide variety of patient conditions or user disability. The development of advanced optimisation training algorithms such as adaptive optimal Bayesian neural networks is particularly useful when only limited training data are available. Two specific biomedical engineering applications will be presented. The first application concerns the development of a non-invasive monitor for real-time detection of hypoglycaemic episodes in Type 1 diabetes mellitus patients (T1DM). The second application relates to the development of real-time hands-free wheelchair control systems using head movement to provide mobility independence for severely disabled people.
Du, H., Zhang, N. & Nguyen, H.T. 2008, 'Mixed H-2/H-infinity control of tall buildings with reduced-order modelling technique', Structural Control & Health Monitoring, vol. 15, no. 1, pp. 64-89.
View/Download from: UTS OPUS or Publisher's site
In this paper, a reduced-order technique based on the dynamic condensation method is applied to obtain a reduced-order model of an experimental tall building which has 20 floors and is 2.5 m high. The experimental model is designed to imitate a practical
Su, S.W., Celler, B.G., Savkin, A.V., Nguyen, H.T., Cheng, T.M., Guo, Y. & Wang, L. 2008, 'Portable sensor based dynamic estimation of human oxygen uptake via nonlinear multivariable modelling.', Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, pp. 2431-2434.
Noninvasive portable sensors are becoming popular in biomedical engineering practice due to its ease of use. This paper investigates the estimation of human oxygen uptake (VO(2)) of treadmill exercises by using multiple portable sensors (wireless heart rate sensor and triaxial accelerometers). For this purpose, a multivariable Hammerstein model identification method is developed. Well designed PRBS type of exercises protocols are employed to decouple the identification of linear dynamics with that of nonlinearities of Hammerstein systems. The support vector machine regression is applied to model the static nonlinearities. Multivariable ARX modelling approach is used for the identification of dynamic part of the Hammerstein systems. It is observed the obtained nonlinear multivariable model can achieve better estimations compared with single input single output models. The established multivariable model has also the potential to facilitate dynamic estimation of energy expenditure for outdoor exercises, which is the next research step of this study.
Tran, T., Ha, Q.P. & Nguyen, H.T. 2007, 'Robust Non-Overshoot Time Responses using Cascade Sliding Mode-PID Control', Journal of Advanced Computational Intelligence and Intelligent Informatics, vol. 11, no. 10, pp. 1224-1231.
View/Download from: UTS OPUS
Overshoot is a serious problem in automatic control systems. This paper presents a new method for elimination of the step response overshoot in a conventional PID-controlled system and enhancement of its robustness by cascading a sliding mode controller in the outer loop. The idea is first to use the cascade control principle to model the under-damped system under PID control with a second-order system. Then, by making use of the sliding mode control outer loop, a robust, reduced-order response can be obtained to suppress the control overshoot. The proposed approach can also deal with time delay systems. Its validity is verified through simulation for some dynamic systems subject to highly nonlinear uncertainties, where overshoot remains an issue.
Nguyen, H.T., Nguyen Thanh, S., Taylor, P.W. & Middleton, J. 2007, 'Head Direction Command Classification using an Adaptive Optimal Bayesian Neural Network', International Journal of Factory Automation, Robotics and Soft Computing, vol. 1, no. 3, pp. 98-103.
View/Download from: UTS OPUS
Mobility has become very important for our quality of life. Head movement is a natural form of pointing and can be used to directly replace the joystick for severely disabled people. In this paper, we describe the development of an optimal Bayesian neural network for the classification of head direction commands in a hands-free wheelchair control system as it allows strong generalisation during the training phase and does not require a validation data set. Experimental results show that with limited training data, an adaptive optimal Bayesian neural network can be developed to classify head direction commands by disabled users with a high sensitivity and specificity of 93.75% and 97.92% respectively.
Kitis, M., Ilker Harman, B., Yigit, N.O., Beyhan, M., Nguyen, H. & Adams, B. 2007, 'The removal of natural organic matter from selected Turkish source waters using magnetic ion exchange resin (MIEX®)', Reactive and Functional Polymers, vol. 67, no. 12 SPEC. ISS., pp. 1495-1504.
View/Download from: Publisher's site
The primary objective of this work was to evaluate the effectiveness of the MIEX&reg; process in removing natural organic matter (NOM) from selected drinking water sources of the City of Istanbul. Raw water samples from five drinking water treatment plants (Elmali{dotless}, B.ekmece, &Ouml;merli, &#304;kitelli, and Kai{dotless}thane) serving to about 10 million people were collected and jar-tested in laboratory. The kinetics of NOM removal at various MIEX&reg; dose and contact times, the extent of resin saturation in multiple-loading experiments, and the impacts of MIEX&reg; pretreatment prior to coagulation on coagulant demands were investigated. After a resin dose of 5-10 ml settled resin/l and contact time of 10-20 min, dissolved organic carbon (DOC) concentrations and specific UV absorbance (SUVA254) values obtained for all waters were <1.5 mg/l and <2 l/mg DOC-m, respectively. In addition, for all waters, 17-42% nitrate and 9-24% sulfate removals were obtained at a resin dose and contact time of 10 ml settled resin/l and 10 min, respectively. UV254 absorbance reductions up to 96% were achieved. Increasing MIEX&reg; dose generally decreased the SUVA254 values indicating that the MIEX&reg; resin preferentially removed UV absorbing fractions of NOM. Although some degree of initial resin saturation occurred in two raw waters up to 900 bed volume (BV) loadings, such saturations were not continuous up to 2000 BV loadings. The initial saturation was not observed for the other three waters, suggesting that MIEX&reg; resin can be loaded up to 2000 BVs or more (not tested) without any saturation. Depending on the raw water, the application of MIEX&reg; as a pretreatment prior to coagulation reduced the coagulant (alum) demand by 0-30 mg/l compared to the coagulation only. Results from the laboratory experiments overall indicated that MIEX&reg; resin even at relatively low dose and short contact time effectively removes NOM in all tested raw waters and reduces coagulant demands. &copy; 2007 Elsevier Ltd. All righ...
Smith, P.J., Vigneswaran, S., Ngo, H., Nguyen, H.T. & Ben-Aim, R. 2006, 'Application of an automation system and a supervisory control and data acquisition (SCADA) system for the optimal operation of a membrane adsorption hybrid system', Water Science And Technology, vol. 53, no. 4-5, pp. 179-184.
View/Download from: UTS OPUS or Publisher's site
The application of automation and supervisory control and data acquisition (SCADA) systems to municipal water and wastewater treatment plants is rapidly increasing. However, the application of these systems is less frequent in the research and developmen
Smith, P.J., Vigneswaran, S., Ngo, H., Nguyen, H.T. & Aim, R.B. 2006, 'A New Approach to backwash initiation in Membrance Systems', Journal of Membrane Science, vol. 278, no. 1-2, pp. 381-389.
View/Download from: UTS OPUS or Publisher's site
Smith, P.J., Shon, H., Vigneswaran, S., Ngo, H. & Nguyen, H.T. 2006, 'Productivity enhancement in a cross-flow ultrafiltration membrane system through automated de-clogging operations', Journal Of Membrane Science, vol. 280, no. 1-2, pp. 82-88.
View/Download from: UTS OPUS or Publisher's site
A membrane system only has a limited operational lifetime, whereby it becomes so severely fouled that continued operation must be stopped. In the cross-flow configuration of membrane filtration of wastewater, both increased cross-flow velocities and decr
Smith, P.J., Shon, H.K., Vigneswaran, S., Ngo, H.H. & Nguyen, H. 2006, 'Productivity enhancement in a cross-flow ultrafiltration membrane system through automated de-clogging operations', Journal of Membrane Science, vol. 280, no. 1-2, pp. 82-88.
View/Download from: Publisher's site
A membrane system only has a limited operational lifetime, whereby it becomes so severely fouled that continued operation must be stopped. In the cross-flow configuration of membrane filtration of wastewater, both increased cross-flow velocities and decreased operational transmembrane pressures can be used to decrease membrane fouling and extend the life cycle of the membrane separation process. The study found that an optimised usage of two de-clogging techniques, with a 1 h production period followed by a 1 min relaxation period and then a 1 min high cross-flow rate period, resulted in a net productivity increase of 14.8%. The study involved a detailed investigation into the utilization of two automated cleaning techniques to reduce fouling problems encountered when cross-flow membrane systems are operated with high permeate flux rates. The two cleaning techniques studied were periodic membrane relaxation and a periodic high rate cross-flow. During both the relaxation and high rate cross-flow periods, permeate production was stopped. This results in an operational loss in productivity. When each cleaning technique was operated individually, there was a net productivity decrease of 0.7%, due to the 3.2% operational loss due to cleaning technique being implemented. The system was developed using a Programmable Logic Controller (PLC) and a Supervisory Control and Data Acquisition (SCADA) system to accurately control and monitor the process. &copy; 2006 Elsevier B.V. All rights reserved.
Nguyen, S.D., Jeong, T.S., Kim, M.R. & Sok, D.E. 2006, 'Broad-spectrum antioxidant peptides derived from His residue-containing sequences present in human paraoxonase 1.', Free radical research, vol. 40, no. 4, pp. 349-358.
Hydroxyl or peroxyl radicals and hypochlorous acid (HOCl) are known to cause the oxidation of lipoproteins. Here, we examined Cu(2+)-binding property of paraoxonase 1 (PON1), and antioxidant actions of peptides, resembling His residue-containing sequences in PON1, against oxidations by Cu(2+), peroxyl radicals or HOCl. When Cu(2+)-binding property of PON1 was examined spectrophotometrically, the maximal Cu(2+) binding was achieved at 1:1 molar ratio of PON1: Cu(2+). Additionally, Cu(2+)-catalyzed oxidative inactivation of PON1 was prevented by Ca(2+)-depleted PON1 at 1:1 ratio, but not diethylpyrocarbonate (DEPC)-modified PON1, suggesting the participation of His residue in Cu(2+)-binding. When His-containing peptides were examined for antioxidant actions, those with either His residue at N-terminal position 2 or 3, or His-Pro sequence at C-terminal remarkably prevented Cu(2+)-mediated low density lipoprotein (LDL) oxidation and PON1 inactivation. Especially, FHKALY, FHKY or NHP efficiently prevented Cu(2+)-induced LDL oxidation (24 h), indicating a tight binding of Cu(2+) by peptides. In support of this, the peptide/Cu(2+) complexes exhibited a superoxide-scavenging activity. Separately, in oxidations by 2,2'-azobis-2-amidinopropane hydrochloride or HOCl, the presence of Tyrosine (Tyr) or Cysteine (Cys) residue markedly enhanced antioxidant action of His-containing peptides. These results indicate that His-containing peptides with Tys or Cys residues correspond to broad spectrum antioxidants in oxidation models employing Cu(2+), 2,2'-azobis-2-amidinopropane hydrochloride (AAPH) or HOCl.
Nguyen, H.T., Kim, J.H., Nguyen, A.T., Nguyen, L.T., Shin, J.C. & Lee, B.W. 2006, 'Using canopy reflectance and partial least squares regression to calculate within-field statistical variation in crop growth and nitrogen status of rice', Precision Agriculture, vol. 7, no. 4, pp. 249-264.
View/Download from: Publisher's site
For the site-specific prescription of fertilizer topdressing in rice cultivation, a non-destructive diagnosis of the rice growth and nutrition status is necessary. Three experiments were done to develop and test a model using canopy reflectance for the non-destructive diagnosis of plant growth and N status in rice. Two experiments for model development were conducted, one in 2000 and another in 2003 in Suwon, Korea, including two rice varieties and four nitrogen (N) rates in 2000 and four rice varieties and 10 N treatments in 2003. Hyperspectral canopy reflectance (300-1,100 nm) data recorded at various growth stages before heading were used to develop a partial least squares regression (PLS) model to calculate plant biomass and N nutrition status. The 342 observations were split for model calibration (75%) and validation (25%). The PLS model was then tested to calculate within-field statistical variation of four crop variables: shoot dry weight (SDW), shoot N concentration (SN), shoot N density (SND) and N nutrition index (NNI) using measured canopy reflectance data from a field of 6,500 m2 in 2004. Results showed that PLS regression using logarithm reflectance had better performance than both the PLS and multiple stepwise linear regression (MSLR) models using original reflectance data to calculate the four plant variables in year 2000 and 2003. It produced values with an acceptable model coefficient of determination (R 2) and relative error of calculation (REC). The model R 2 and REC ranged from .83 to .89 and 13.4% to 22.8% for calibration, and .76 to .87 and 14.0% to 24.4% for validation, respectively. The PLS regression model R 2 was reduced in the test data of year 2004 but the root mean square error of calculation (RMSEC) was smaller, suggesting that the PLS regression model using canopy reflectance data could be a promising method to calculate within-field spatial variation of rice crop growth and N status. &copy; 2006 Springer Science+Business Media, LLC.
Smith, P.J., Vigneswaran, S., Ngo, H., Ben-Aim, R. & Nguyen, H.T. 2005, 'Design of a generic control system for optimising back flush durations in a submerged membrane hybrid reactor', Journal Of Membrane Science, vol. 255, no. 38749, pp. 99-106.
View/Download from: UTS OPUS
Organic fouling on the membrane can be minimised through powdered activated carbon (PAC) usage in the submerged membrane reactor to adsorb dissolved organic matter and reduce direct organic loading on the membrane. However, fouling cannot be totally alle
Boord, P.R., Barriskill, A.B., Craig, A.R. & Nguyen, H.T. 2004, 'Brain-Computer Interface - FES Integration: Towards a Hands-free Neuroprosthesis Command System', Neuromodulation, vol. 7, no. 4, pp. 267-276.
View/Download from: UTS OPUS or Publisher's site
This paper presents a critical review of brain-computer interfaces (BCIs) and their potential for neuroprosthetic applications. Summaries are provided for the command interface requirements of hand grasp, multijoint, and lower extremity neuroprostheses,and the characteristics of various BCIs are discussed in relation to these requirements. The current limitations of BCIs and areas of research that need to be addressed to enhance BCI - FES inetgration.
Smith, P.J., Vigneswaran, S., Ngo, H., Ben-Aim, R. & Nguyen, H.T. 2004, 'Investigation of Membrane De-Clogging Techniques in the Submerged Filtration Absorption Hybrid System (SMFAHS)', Fluid/Particle Separation Journal, vol. 16, no. 2, pp. 165-173.
View/Download from: UTS OPUS
Lal, S., Craig, A.R., Boord, P.R., Kirkup, L. & Nguyen, H.T. 2003, 'Development of an algorithm for an EEG-based driver fatigue countermeasure', Journal Of Safety Research, vol. 34, no. 3, pp. 321-328.
View/Download from: UTS OPUS or Publisher's site
Ha, Q.P., Trinh, H.M., Nguyen, H.T. & Tuan, H.D. 2003, 'Dynamic output feedback sliding-mode control using pole placement and linear functional observers', IEEE Transactions On Industrial Electronics, vol. 50, no. 5, pp. 1030-1037.
View/Download from: UTS OPUS or Publisher's site
Hung, A., Nguyen, H.T., Lee, W.B., Rickard, M.T., Thornton, B.S. & Blinowska, A. 2003, 'Diagnostic Abilities of Three CAD Methods for Assessing Microcalcifications In Mammograms and An Aspect of Equivocal Cases Decisions by Radiologists', Australian Physical And Engineering Sciences in Medicine, vol. 26, no. 3, pp. 78-83.
View/Download from: UTS OPUS
Hung, A., Nguyen, H.T., Thornton, B.S. & Zinder, Y. 2003, 'Dynamic Programming Approach to Image Segmentation and its Application to Pre-processing of Mammograms', Australian Journal of Intelligent Information Processing Systems, vol. 8, no. 2, pp. 51-56.
View/Download from: UTS OPUS
Images egmentationis an importent componento f imagop rocessings irce significantt ime can be savedi f a region of interest is extracted by al efficient segmentationa lgorithm. A dynamic programming image segmentation algorithnr is presented. The algorithm is applicable to images with a large matrix of gray levels of pixel values and generatesa path separatingt he object from the background.T he report of a.na pplication of the proposed algorithm to digitised mammotramsc omplementsit s description.
Hung, W.T., Nguyen, H.T., Lee, W.B., Rickard, M.T., Thornton, B.S. & Blinowska, A. 2003, 'Diagnostic abilities of three CAD methods for assessing microcalcifications in mammograms and an aspect of equivocal cases decisions by radiologists.', Australasian physical & engineering sciences in medicine / supported by the Australasian College of Physical Scientists in Medicine and the Australasian Association of Physical Sciences in Medicine, vol. 26, no. 3, pp. 104-109.
Radiologists use an "Overall impression" rating to assess a suspicious region on a mammogram. The value ranges from 1 to 5. They will definitely send a patient for biopsy if the rating is 4 or 5. They will send the patient for core biopsy when a rating of 3 (indeterminate) is given. We have developed three methods to aid diagnosis of cases with microcalcifications. The first two methods, namely, Bayesian and multiple logistic regression (with a special "cutting score" technique), utilise six parameter ratings which minimise subjectivity in characterising the microcalcifications. The third method uses three parameters (age of patient, uniformity of size of microcalcification and their distribution) in a multiple stepwise regression. For both training set and test set, all three methods are as good as the two radiologists in terms of percentages of correct classification. Therefore, all three proposed methods potentially can be used as second readers.
Djajakesukma, S., Samali, B. & Nguyen, H.T. 2002, 'Study of a semi-active stiffness damper under various earthquake inputs', Earthquake Engineering and Structural Dynamic, vol. 31, no. 10, pp. 1757-1776.
View/Download from: UTS OPUS or Publisher's site
Semi-active sti-ness damper (SASD) is one of many semi-active control systems with the capability to mitigate the dynamic response using only a small amount of external power. The system consists of a hydraulic damper connected to the bracing frame in a selected story unit. In this paper, study of a SASD in two building models of ?ve-stories under four benchmark earthquake records is reported. The purpose of this study is to evaluate the e-ectiveness of the control system against structure type and varying earthquake inputs. Various control laws are chosen to work with SASD, such as: resetting control, switching control, linear quadratic regulator (LQR) and modi?ed LQR, and the results are compared with no control and passive control cases. Numerical results show that the use of a SASD is effective in reducing seismic responses. Control efftiveness is dependent on the type of structure and earthquake excitation. Passive control is less e-ective than other control cases as expected. Resetting control, switching control and LQR generally perform similarly in response reduction. While modified LQR is more efficient and robust compared with other control algorithms.
Slunjski, M., Nguyen, H., Ballard, M., Eldridge, R., Morran, J., Drikas, M., O'Leary, B. & Smith, P. 2002, 'Miex® - Good research commercialised', Water, vol. 29, no. 2, pp. 42-51.
The MIEX&reg; DOC resin process, a brainchild of Australian water scientists and engineers, represents an exciting development in potable water treatment technology. It enables new 21st century water quality standards to be achieved with low capital and operating costs and as such has worldwide applications. The technology was the end result of a massive research and development effort over a number of years spanning areas of product and process development, testing and scale-up by a consortium consisting of teams from CSIRO Molecular Science, SA Water Corporation and Orica. This culminated in the first commercial applications of the technology by the SA Water Corporation at Mt Pleasant (South Australia) and the Water Corporation of WA at Wanneroo (Western Australia), which are outlined here in some detail. Under the overall coordination of Orica, each of the initial partners was very innovative in the concept development and how they went about fulfilling their roles of resin chemistry, application and process development and commercialisation. The Water Corporation's contribution occurred later and focused on the area of process scale-up and large scale plant design. This article provides a summary review of the reasons the parties became involved in the MIEX&reg; project, their respective endeavours and plans for future.
Thornton, B.S., Nguyen, H.T., Hung, A., Hirst, C., Thornton-Benko, E. & Langtry, T. 2001, 'Breast Screening Outcomes: Communications Problems, Chaos Relationship and Control Theory', Canadian Applied Mathematics Quarterly, vol. 9, no. 4, pp. 377-401.
Daly, M.A., Kovoor, P., Thomas, S.P., McKinley, S.M., Nguyen, H.T., Uther, J. & Ross, D.L. 1997, 'A Novel Technique For Delivery Of Radiofrequency Energy Through Multiple Electrodes Simultaneously With Individual Temperature Control', Circulation, vol. 96, no. 8, pp. 1427-1427.
NA
Nguyen, H.T., Shannon, A.G., Coates, P. & Owens, D. 1997, 'Estimation Of Glomerular Filtration Rate In Type Ii (non-insulin Dependent) Diabetes Mellitus Patients', IMA Journal Of Mathematics Applied In Medicine And Biology, vol. 14, no. 2, pp. 151-160.
The aim of this research was to develop an estimation of glomerular filtration rates (GFRs) from a combination of simple parameters in a large group of type II diabetic patients. We selected 122 newly presenting, previously untreated, type II patients wh
Ghevondian, N. & Nguyen, H. 1997, 'Low power portable monitoring system of parameters for hypoglycaemic patients', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, vol. 3, pp. 1029-1031.
Hypoglycaemia in diabetic patients has the potential to become harmful, causing symptoms such as anxiety, sweating, tremor. Severe cases can cause coma or even death. Hypoglycaemia is only significant when it is associated with symptoms, hence by monitoring parameters such as sweating, snoring, EEG and heart rate, severe hypoglycaemia can be detected. This paper describes the monitoring system of four body functions described above for the detection of early symptoms of severe hypoglycaemia. A battery powered monitoring system has been built on a Eurocard size PCB and tested for its performance of these parameters.
Nguyen, H., Roychoudhry, A. & Shannon, A. 1997, 'Classification of diabetic retinopathy lesions from stereoscopic fundus images', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, vol. 1, pp. 426-428.
Classification of the severity of diabetic retinopathy (DR) is vital for determining appropriate therapies for this frequent complication of diabetes. The purpose of this study is develop an automated system to help with the classification of some diabetic retinopathy lesions stereoscopic fundus images. The system is used in particular to distinguish drusen from hard exudates (diabetic retinopathy lesions), and to evaluate the severity of lesions such as retinal oedema.
Nguyen, H., Nguyen, D.K., Shannon, A. & Owens, D. 1997, 'Estimation of minimal model parameters with the use of an adaptive observer for suprabasal insulin action', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, vol. 5, pp. 2146-2148.
Based on the minimal model, insulin sensitivity (S I) and glucose effectiveness (S G) can be estimated from the results of an intravenous glucose tolerance test (IVGTT). However, this task is complex because the suprabasal insulin action (X) at any one time depends on the whole history of plasma insulin levels since the basal steady-state was disrupted. In this paper, we develop an adaptive observer for accurate estimation of insulin action (X). This adaptive observer forms the foundation of a new way to identify minimal model parameters. Compared to the well-known MINMOD program, this new technique is robust as it is less dependent on initial estimates, and accurate as it minimises both the plasma glucose error and insulin action error.
Ghevondian, N. & Nguyen, H. 1997, 'Using fuzzy logic reasoning for monitoring hypoglycaemia in diabetic patients', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, vol. 3, pp. 1108-1111.
Non-invasive monitoring and detecting hypoglycaemia in diabetic patients requires simultaneous measurements of body functions such as sweating, snoring, recording EEG and heart rate. There are numerous factors that can affect the parameters being measured, e.g., environmental conditions, stress of patients, behavioural changes, duration of test etc. Therefore a physician is required to make a collective decision from the information in hand from these parameters to determine the state of the diabetic patient. This paper describes the design of a microcontroller based fuzzy logic controller which uses fuzzy reasoning method to monitor and help to detect hypoglycaemia in diabetic patients.
Martinez-Coll, A., Cooper, P., Murphy, G. & Nguyen, H. 1997, 'Assessment of a laser-powered multiwavelength near-infrared spectrometer', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, vol. 2, pp. 696-699.
Near infrared spectroscopy is a non-invasive technique for measuring relative blood volume and oxygen saturation in tissue. We have designed and built a research NIR-spectrometer which offers the flexibility to study changes in blood oxygen saturation (SO 2) and in blood volume (BV) during skeletal muscle pacing. The instrument consists of five 1 watt solid state lasers (780, 800, 830, 850 and 980 nm) fired sequentially at 5 s pulses for a 1 ms cycle, and a 5 mm 2 photodiode receiver. Features of the spectrometer include, rapid realtime data acquisition (1000 samples/s), receiver protection against ambient light, large dynamic optical power output adjustable for each wavelength, and portability. In vitro photon scattering experiments and linear response to blood oxygen saturation changes for differential absorption (780-850 nm) provide an accurate measure of changes in SO 2, while the 800 nm signal can be used as a measure of blood volume change independently of SO 2 (&plusmn;2%-SO 2 error). In addition, the 980 nm signal level is explored as an index of mean pathlength which may provide crucial information for determining absolute SO 2.
Kovoor, P., Eipper, V., Dewsnap, B., McKinley, S.M., Nguyen, H.T., Uther, J. & Ross, D.L. 1996, 'The Effect Of Differing Frequencies On Lesion Size During Radiofrequency Ablation', Circulation, vol. 94, no. 8, pp. 3953-3953.
NA
Nguyen, H.T., Luzio, S., Dolben, J., West, J.M., Beck, L., Coates, P. & Owens, D. 1996, 'Dominant Risk Factors For Retinopathy At Clinical Diagnosis In Patients With Type Ii Diabetes Mellitus', Journal Of Diabetes And Its Complications, vol. 10, no. 4, pp. 211-219.
View/Download from: UTS OPUS or Publisher's site
A study of 270 newly presenting, previously untreated, type II diabetic patents revealed that 38 patients (14%) had already developed diabetic retinopathy (DR). Among this group, 26 patients had lesions of background diabetic retinopathy and 12 patients
Wan, S.W. & Nguyen, H.T. 1994, '50Hz interference and noise in ECG recordings--a review.', Australasian physical & engineering sciences in medicine / supported by the Australasian College of Physical Scientists in Medicine and the Australasian Association of Physical Sciences in Medicine, vol. 17, no. 3, pp. 108-115.
In this review paper, a simplified model is used to explain the various ways by which 50Hz interference can disturb electrocardiogram recordings. From the model, noise expressions are also derived which explain sources of noise in recordings. Means of minimising the 50Hz interference and noise with emphasis placed on skin abrasion and right-leg drive circuits are discussed. An add-on circuit which can be used with existing amplifiers to improve their performance is shown. Previous interference analysis has concentrated on 2-input differential amplifiers, however in modern hospitals, a wide variety of amplifier configurations are used. An example is the Wilson Central Terminal which is used to obtain a zero potential in body surface mapping applications. In this review it is shown with an example for an ECG amplifier incorporating a Wilson Central Terminal, how it is easy to extend the interference model to other applications.
Nguyen, H.T. & Prince, M.P. 1994, 'Power starter with low output current harmonics', Journal of Electrical and Electronics Engineering, Australia, vol. 14, no. 1, pp. 1-7.
This paper describes the development and implementation of a new power starter which may be used for smooth starting of induction motors but without the high harmonics associated with standard power starters. Based on the selected-harmonic-elimination technique, this power starter generates lower output current harmonics, and produces a higher input power factor compared to the standard power starter. As a consequence, the new power starter has two important features: minimisation of heat loss in the motors and continuous power saving during starting operation.
Nguyen, H.T. 1994, 'State-variable feedback controller for an overhead crane', Journal of Electrical and Electronics Engineering, Australia, vol. 14, no. 2, pp. 75-84.
A state-variable feedback controller has been designed for the set-point tracking control of both the trolley position and the rope length of a multimotor crane while minimising the load swing. The overhead crane system is modelled using Lagrangian extended equations of motion, and the overall multivariable system model is simulated using MATLAB. For real-time implementation, a state-variable feedback controller is developed and implemented using a digital control system. In particular, this state-variable feedback controller varies with rope length during crane operation to ensure closed-loop stability throughout the operating space. The controller is successfully implemented using a scale model of an overhead crane.
Shoon, S.Y., Wan, S.W. & Nguyen, H.T. 1993, 'A novel approach to the design of a Wilson referenced ECG amplifier.', Australasian physical & engineering sciences in medicine / supported by the Australasian College of Physical Scientists in Medicine and the Australasian Association of Physical Sciences in Medicine, vol. 16, no. 3, pp. 111-117.
The Wilson Central Terminal consists of three limb electrodes connected through a resistor network at the inverting input to the ECG amplifier. It is often used as a zero potential reference in ECG recordings. In this paper, the implications of using a Wilson central reference on the overall amplifier's common-mode rejection ratio and noise specifications is analysed. It is shown that the Wilson reference can degrade the overall amplifier specifications. The design of a Wilson referenced amplifier is then described which shows this to be true. A novel approach to the design of a Wilson referenced ECG amplifier is then presented, whereby the reference network is moved from the input to an intermediate stage of the amplifier. An analysis on the improvements achieved over the conventional approach is given. An amplifier design using the new approach is then described. Tests results showed a significant improvement in amplifier common mode rejection ratio and noise specifications when compared to the conventional design.
Hung, N.T. & Anderson, B.D.O. 1980, 'Analysis and Synthesis of Nonlinear Reciprocal Networks Containing Two Element Types and Transformers', IEEE Transactions on Circuits and Systems, vol. 27, no. 4, pp. 263-276.
View/Download from: UTS OPUS or Publisher's site
This paper presents results for some analysis and synthesis problems of nonlinear reciprocal networks. In particular, for special systems such as lossless reciprocal networks and nonlinear RC reciprocal networks, synthesis techniques are introduced. The central feature of these techniques is the method of finding an appropriate stored energy function for the synthesizing network from prescribed network equations. Under certain assumptions, the stored energy function can be determined directly from the controllability and observability matrices of a system obtained by linearization around any state of the original system. &copy; 1980 IEEE
Hung, N.T. & Anderson, B.D.O. 1979, 'Triangularization Technique for the Design of Multivariable Control Systems', IEEE Transactions on Automatic Control, vol. 24, no. 3, pp. 455-460.
View/Download from: UTS OPUS or Publisher's site
This paper presents a novel technique for the design of multivariable control systems. A stable and proper precompensator is to be determined for a multivariable plant such that the compensated plant transfer function matrix is triangular and diagonally dominant in a nonstandard way. As a consequence of the triangular-diagonal-dominance property, only the diagonal elements need to be considered in an overall closed-loop design. In effect, the technique provides a systematic procedure to reduce a multivariable design problem to independent scalar design problems. Copyright &copy; 1979 by The Institute of Electrical and Electronics Engineers, Inc.

Kolling Institute of Medical Research; Brain & Mind Institute; Princess Margaret Hospital for Children, Perth; Royal Institute of Technology, Stockholm, Sweden; The Garvan Institute of Medical Research; Sun Yat-sen University, Guangzhou, China