Senior Lecturer with the School of Mechanical and Mechatronic Engineering, Faculty of Engineering and Information Technology. PhD from UNSW, MA and BSc from Sydney University. Consulting services re accidents, equipment/machinery and consumer products.
Research projects within and outside UTS - contact me for further information - happy to consider new projects - available to talk with new potential partners and new research students.
Alzoubi, Y, Gill, AQ & Moulton, B 2018, 'A measurement model to analyze the effect of agile enterprise architecture on geographically distributed agile development', Journal of Software Engineering Research and Development, vol. 6, no. 4.View/Download from: UTS OPUS or Publisher's site
Pupatwibul, P, Banjar, AR, Hossain, MI, Braun, R & Moulton, B 2018, 'A Novel Software-Defined Networking Controller: the Distributed Active Information Model (DAIM)', International Journal of Electronics and Telecommunications, vol. 64, pp. 209-216.View/Download from: UTS OPUS
Yuwono, M, Su, SW, Moulton, BD & Nguyen, HT 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.
Yuwono, M, Su, SW, Guo, Y, Moulton, BD & Nguyen, HT 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.
Fleming, J, Iyer, M, Shortis, MR, Vuthaluru, HB, Xing, K & Moulton, BD 2012, 'Biomedical engineering curricula: trends in Australia and abroad', World Transactions on Engineering and Technology Education, vol. 10, no. 1, pp. 23-28.View/Download from: UTS OPUS
This article provides an analysis of representative biomedical engineering curricula in Australia, the USA and the UK. The research was undertaken as part of an Australian Learning and Teaching Council project on Australian dual degrees. The findings suggest that biomedical engineering offerings in the United States tend to treat biomedical engineering as a separate discipline in itself, with distinct methodological and analytical techniques. Many universities in the United Kingdom offer courses specifically in medical engineering and/or biomedical engineering made up of core engineering subjects together with specialist biomedical engineering subjects or medical engineering subjects. A limited number of Australian universities offer degrees specifically in biomedical engineering. Australian dual degrees tend to offer standard engineering subjects alongside standard medical science subjects, and the structure can prevent students from choosing subjects that specialise in the area of biomedical engineering. It can be concluded that Australian dual degrees can be a poor choice for students who wish to progress in the field of biomedical engineering.
Yuwono, M, Moulton, BD, Su, SW, Celler, BG & Nguyen, HT 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.
Moulton, BD & Khalifan, Z 2011, 'In-home Health Alert Systems in Rural and Remote Areas of Australia: A Survey of Doctors' and Patients' Views', Journal of Convergence Information Technology, vol. 6, no. 1, pp. 1-14.View/Download from: UTS OPUS or Publisher's site
Australias population is ageing, and this is placing increased stress on the national health system. There has been an increased focus on providing services that enable older people to live safely at home rather than in hospitals or retirement accommodation settings. Health-alert systems that use pendants or sensors are especially important for an increasing number of older people who live at home in rural and remote areas. This paper presents preliminary findings from a survey of 56 elderly people and 12 medical practitioners regarding the use of in-home health alert systems. The study was conceived to improve understanding of user requirements relating to in-home trauma alert systems and shed light on concerns, risks and design constraints. The preliminary findings suggest that cost is a primary limitation preventing older people from installing these systems. In addition, the findings suggest that there is a need for automatic sensor-based systems to complement existing systems that rely on the user to wear and operate a push-button pendant or other device. The results also suggest that there is an unmet demand for sensor-based systems that automatically register these events and send alerts to nominated peers in the first instance, and only send alerts to emergency services if the nominated peers failed to register a response to the alert. The study also found that older people may be opposed to camera-based systems, but are not opposed to less intrusive sensors in key areas such as bathrooms and kitchens. The surveyed medical practitioners suggested that systems that sense heart rate and oxygenation may be of particular benefit, and that potential candidates for automatic systems include people who have medical conditions such as dementia, epilepsy, cardiovascular illness, stroke, Parkinsons disease, vertigo and osteoarthritis.
Moulton, BD 2011, 'Capacitive Sensor to Detect Fallen Humans in Conditions of Low Visibility', Journal of Convergence Information Technology, vol. 6, no. 9, pp. 1-8.View/Download from: UTS OPUS or Publisher's site
This paper examines the potential for a capacitive sensor to be used as part of a system to detect fallen humans at very close range. Previous research suggests that a robotic system incorporating a low cost capacitive sensor could potentially distinguish between different materials. The work reported in this paper stemmed from an attempt to determine the true extent to which such a system might reliably differentiate between fallen humans and other objects. The work is motivated by the fact that there are several different emergency circumstances in which such a system might save lives if it could reliably detect immobile humans. These scenarios include situations where older people have fallen and are unable to move or raise an alert, and circumstances where people have been overcome by smoke in a burning building. Current sensing systems are typically unsuitable in conditions of low visibility such as smoke filled rooms. This analysis focused specifically on the potential for a robot equipped with a capacitive sensing system to identify an immobile human in a low visibility emergency scenario. It is concluded that further work would be required to determine whether this type of capacitive sensing system is genuinely suitable for this task.
Moulton, BD & Johnson, D 2010, 'Robotics education: a review of graduate profiles and research pathways', World Transactions on Engineering and Technology Education, vol. 8, no. 1, pp. 26-31.View/Download from: UTS OPUS
Robotics is a rapidly emerging field of engineering, and many of the Australian universities that offer a Bachelor of Engineering now offer majors in robotics/mechatronics. This article explores and analyses some implications for robotics education, focusing on graduate attributes and research pathways. The preliminary results of this review suggest that courses in robotics tend to include introductory material from a relatively large number of sub-disciplines, and robotics courses do not ordinarily permit the selection of sub-majors from other inter-related disciplines. This analysis finds that the current structures can in some cases prevent students from traversing pathways towards postgraduate research in their own particular areas of special interest. It is concluded that courses might place greater emphasis on the graduate attributes that are essential to be able to work effectively in cross-discipline teams. It is also concluded that it may be beneficial to undertake further research which compares the approaches to robotics education taken in Australian universities with the approaches of overseas counterparts.
Fleming, J., Iyer, M., Shortis, M.R., Vuthaluru, H.B., Xing, K. & Moulton, B.D. 2010, 'Employers' perceptions regarding graduates of engineering dual degrees', World Transactions on Engineering and Technology Education, vol. 8, no. 3, pp. 277-282.View/Download from: UTS OPUS
This article presents findings from part of an Australian Learning and Teaching Council project regarding Australian dual degrees. Employers from 30 engineering-focused organisations were interviewed to solicit their views on their expectations and willingness to employ graduates with engineering dual degrees. The employers organisations ranged from small to large engineering firms. Respondents indicated that recruiters are more concerned about graduates engineering skills and academic results than whether the graduates had a single or a dual degree. However employers also indicated that they viewed dual degrees as equipping graduates with a broader skill set that could be valuable to the organisation over the longer term. Employers indicated that whereas graduates were expected to focus on engineering tasks over the first few years of their employment, a dual qualification, particularly engineeringbusiness, could lead to a dual degree graduate being promoted more rapidl
Niebecker, KD, Eager, DM & Moulton, BD 2010, 'Collaborative and cross-company project management within the automotive industry using the Balanced Scorecard', International Journal of Managing Projects in Business, vol. 3, no. 2, pp. 328-337.View/Download from: UTS OPUS or Publisher's site
Purpose -This paper aims to summarize the scope, methodology, and main findings of a doctoral thesis about cross-company project management in the automotive industry. The concept of the collaborative project scorecard (CPS) is described and the results of its application to a project are sununarized and discussed. Design/methodology/approach -The project adopted an action research approach which included a series of interviews, surveys, workshops, and a case study where the developed project management concept was tested and evaluated in a real project setting, Findings -The concept of the CPS supports the alignment of project goals with business strategies, improves transparency in networked project organizations with respect to roles, responsibilities, goal achievement, sta.keholder identification, and performance assessment. Project goals is not only based on and measured by hard facts but also on soft facts such as trust and employee satisfaction. The balanced choice of common strategic project goals improves the achievement of long-term strategies in a project partnership.
Chaczko, ZC, Quang, J & Moulton, BD 2010, 'Knowledge transfer model for the development of software equirements analysis CASE tools to be used in cross time-zone projects', International Journal of Digital Content Technology and its Applications, vol. 4, no. 1, pp. 10-15.View/Download from: UTS OPUS or Publisher's site
This article describes work undertaken to evaluate an approach for developing collaborative requirementsanalysis CASE tools that are specifically designed to address the needs of cross-time-zone development teams, that is, teams spread across different geographical locations around the world. Few of the software requirements analysis computer assisted software environment (CASE) tools readily available are designed specifically for cross-time-zone development activities. We propose a specifically tailored data and knowledge-transfer model, and investigate its suitability for the development of a cross-time-zone oriented CASE tool. The approach was used to develop a working prototype. The approach and prototype will be further evaluated in a collaborative undertaking involving the Wroclaw University of Technology, the University of Technology Sydney and the University of Arizona (UA).
Moulton, B.D. & Natividad, C. 2009, 'Remotely accessible laboratory model for enabling improved understanding of robot simultaneous localisation and mapping', World Transactions on Engineering and Technology..., vol. 7, no. 1, pp. 6-11.View/Download from: UTS OPUS
Remotely accessible laboratory model for enabling improved understanding of robot simultaneous localisation and mapping.
Moulton, BD, Croucher, G, Varis, AP & chen, J 2009, 'Method for increasing the energy efficiency of wirelessly networked ambulatory health monitoring devices', Journal of Convergence Information Technology, vol. 5, no. 1, pp. 7-14.View/Download from: UTS OPUS or Publisher's site
In-home healthcare applications that use wearable devices ordinarily have strict power constraints due to the small size of the battery in the device. The power constraints are a key driver of research to develop new methods for improving the energy efficiency of ambulatory health monitoring devices. The radio-communication components typically consume a large proportion of the available energy in systems such as these. Given that radio transmissions use far more power than on-board processing, it is proposed that energy can be conserved by performing fall detection at the node. The proposed algorithm is intended to be performed at the node and provide a suitable balance between power consumption and detection accuracy. The research and prototype system described in this article focuses on wearable fall detection devices to be used elderly people who are living in non-hospital settings, and discusses considerations arising from the development of a prototype system. The outcomes of the system design and development process are discussed, and conclusions are drawn concerning the potential of the method to improve the energy efficiency of fall detection systems.
Moulton, B.D. 2009, 'Enabling safer design via an improved understanding of knowledge-related hazards; a role for cross-disciplinarity', Australasian Journal of Engineering Education, vol. 15, no. 3, pp. 117-127.View/Download from: UTS OPUS
Many accidents arise from knowledge-related hazards. These hazards can lead to catastrophic industrial disasters and 'routine' harm. AN example of a knowledge-related hazard is knowledge-loss due to employee turnover. It is proposed that safe design requires expertise relating to these and other hazards, even though such hazards are ordinarily associated with non-engineering disciplines. However, rather than trying to enable each designed to achieve expertise in all of the relevant disciplines, it is proposed that curricula might place greater emphasis on enabling the ability to work effectively in cross-disciplinary teams.
Moulton, BD, Chaczko, ZC & Karatovic, M 2009, 'Updating Electronic Health Records with Information from Sensor Systems: Considerations Relating To Standards and Architecture Arising From the Development of a Prototype System', Journal of Convergence Information Technology, vol. 4, no. 4, pp. 21-26.View/Download from: UTS OPUS
Several countries around the globe are moving towards national and international standards for Electronic Health Records (EHRs). One function of the standards is to guide the long-term convergence of local systems into integrated evolving national health information systems. The Australian commonwealth government is implementing a nationwide EHR system whereby every Australian will be able to upload data to his or her EHR. Thus Australians, if they wish, will eventually be able to upload data from on-body sensors and in-home monitoring systems to their EHRs. This article explores issues associated with the architecture of systems which allow medical records to be updated with information from monitoring/sensor systems. A prototype was developed to determine some of the key architectural considerations. A sensor simulator was implemented for testing purposes which allows a user of the simulator to impersonate a bed or group of in-home or on-body sensors connected with a person who is in a hospital, retirement home or private home. Findings are discussed relating to key architectural considerations including security, maintainability and modularity.
Moulton, BD, Chaczko, ZC & Karatovic, M 2009, 'Data Fusion and Aggregation Methods for Pre-Processing Ambulatory Monitoring and Remote Sensor Data for Upload to Personal Electronic Health Records', International Journal of Digital Content Technology a..., vol. 3, no. 4, pp. 120-127.View/Download from: UTS OPUS
Several countries including Australia are developing standards for personal electronic health records, and in many cases the standards provide ways for patients to upload data from their own sensor systems to their electronic health records. This article explores issues relating to the design of systems where electronic medical records are updated with data or meta-data from in-home or on-body health monitoring sensor systems. A prototype system was designed, implemented and subsequently evaluated in a way intended to further understanding regarding collection and transfer of sensor data to an electronic health record. A key issue that arose was the extent to which levels of confidence in the data may be affected by the type, quality, installation, maintenance and calibration of the sensors.
Moulton, BD, Chaczko, ZC & Pradhan, G 2009, 'Voice Operated Guidance Systems for Vision Impaired People: Investigating a User-Centered Open Source Model', International Journal of Digital Content Technology and its Applications, vol. 3, no. 4, pp. 60-68.View/Download from: UTS OPUS
People who have impaired vision regularly use white canes and/or guide dogs to assist in obstacle avoidance. Several electronic devices are currently available for providing guidance to a remote location, but these tend to be expensive, or make use of a Braille interface. This project investigated the suitability of a user centered client server approach for the development of a talking GPS system intended to fill a niche for outdoor wayfinding. The work resulted in a working prototype proof-of-concept system that uses a speech-recognition speech-synthesis interface. The prototype solution includes a custom web application which accesses the Google maps API. The system is intended to be scalable and extensible with additional features such as sensors for obstacle avoidance and access to web-based information such as weather, train or bus timetable information. The client server approach was found to be suitable for the development of this type of application.
Moulton, B.D. 2008, 'Designing criterion-based assessment in a way that emphasizes the development of professional judgment and can be incorporated in a criterion-based e-Learning tool', TCU ICT Journal, vol. 1, no. 1, pp. 1-6.
This paper discusses a systematic approach for assessing some of the skills which students develop while undertaking and reflecting on internships. The approach provides a simple yet effective way to develop relevant assessment tasks, so that the assessment itself plays a constructive role in the learning process. It also provides a practical method for developing assessment criteria that are (a) consistent with the objectives of a program, and (b) suitable for inclusion as part of an e-Learning tool. The approach has been piloted with a beta version of the ReView e-Learning tool which is currently being developed at UTS. The e-Learning tool helps to achieve three main goals. First, the tool helps the course-developer to connect assessment criteria with the desired graduate attributes. Second, it is used in a way that encourages students to consider their reports' strengths and weakness. Third, it provides a convenient means for markers to mark the students' reports and provide timely and constructive feedback to the students.
Moulton, B.D. 2008, 'Roles for new technologies in mitigating the detrimental effects of poor integration and other issues that are connected with the curriculum-development and provision of double degrees', TCU ICT Journal, vol. 1, no. 2, pp. 1-6.
This paper discusses four primary issues associated with double degrees, and considers ways in which new technologies may help in addressing those issues. The four issues are (1) in a double degree, each of the two degrees is shortened, which raises questions relating to the sufficiency of coverage of required material; (2) students can find it difficult to know where to turn for help; (3) the two programs tend to be not well integrated, and (4) it can be more difficult for double degree students to participate in peer networks. Some double degree programs are international, and these are particularly problematic, especially in programs where lecturers from one institution visit the other for brief periods (typically week-ends) to deliver lectures before returning to their home country. To some extent many courses are already trending towards on-line delivery modes, and this in itself may help double degree students. Even so, there may be potential to provide additional resources to enabling additional e-Learning capacity to certain subjects if those subjects are identified as causing specific bottlenecks for double degree students. It is concluded that even though double degrees present serious educational challenges, if reasonable effort is expended in a few well-targeted areas, new technologies may play a significant role in improving the educational outcomes for students of double degrees.
Moulton, B.D., Thompson, D.G. & O'Loughlin, P.A. 2007, 'A multidisciplinary education framework for interdisciplinary education which enables people from different disciplines to work together with community based organisations on real-world projects.', World Transactions on Engineering and Technology Education, vol. 6, no. 2, pp. 235-238.View/Download from: UTS OPUS
This article provides findings and presents a collaborative education framework developed at UTS. It also reviews research and theoretical approaches relating to multidisciplinary education. The article is intended to be of interest to researchers and professionals who have interests in workplace learning and multidisciplinary education research.
Moulton, BD & Forrest, Y 2005, 'Accidents will happen: safety-critical knowledge and automated control systems', New Technology Work And Employment, vol. 20, no. 2, pp. 102-114.View/Download from: UTS OPUS or Publisher's site
This article presents findings from a study of control operators that raise concerns about safety-critical knowledge, culture and training. It is argued that the adoption of automated control systems can hinder the transfer of knowledge amongst operators
Moulton, B.D., Lasky, V. & Murray, S.J. 2004, 'The Development of a Remote Laboratory: Educational Issues', World Transactions on Engineering and Technology Education, vol. 3, no. 1, pp. 19-22.
Moulton, B.D., Murray, S.J. & Lasky, V. 2003, 'The development of an environment for remote embedded systems; feedback from students and subsequent enhancements', World Transactions on Engineering and Technology Education, vol. 2, no. 1, pp. 65-68.
Yuwono, M, Su, SW & Moulton, BD 2013, 'An Approach to Fall Detection using Gaussian Distribution of Clustered Knowledge' in Agbinya, JI, Custovic, E & Whittington, J (eds), Bio-Informatic Systems, Processing and Applications, River Publishers, Denmark, pp. 1-13.
The increasing population of elderly people has created significant push to research in fall prevention and detection. World Health Organization noted substantial amounts of incidents and accidents among elderly people due to falls worldwide. This chapter proposes a fall detection algorithm using clustered fall signals from a single waist worn wireless tri-axial accelerometer. The method proposed is to approach fall detection using digital signal processing, data clustering, signal multiplexing, and neural networks.
Chaczko, ZC, Moulton, BD, Quang, J & Jain, K 2009, 'Data and Knowledge-Transfer Model for the Development of Software Requirements Analysis CASE Tools designed for Cross-Time-Zone Projects' in Chaczko, Z, Klempous, R & Nikodem, J (eds), STEALING TIME EXPLORATION IN 24/7 SOFTWARE ENGINEERING DEVELOPMENT, River Publishers, Denmark, pp. 157-169.View/Download from: UTS OPUS
This chapter describes work undertaken to evaluate an approach for developing collaborative requirements-analysis CASE tools that are specifically designed to address the needs of cross-time-zone development teams, that is, teams spread across different geographical locations around the world. Few of the software requirements analysis computer assisted software environment (CASE) tools readily available are designed specifically for cross-time-zone development activities. We propose a specifically tailored data and knowledge-transfer model, and investigate its suitability for the development of a cross-time-zone oriented CASE tool. The approach was used to develop a working prototype. The approach and prototype will be further evaluated in a collaborative undertaking involving the WrocÅaw University of Technology, the University of Technology, Sydney and the University of Arizona (UA).
Moulton, BD, Tuttle, S & Lowe, DB 2015, 'An Information Taxonomy for Remotely-Accessible Engineering Instructional Laboratories', Proceedings of the ASEE annual conference - An Information Taxonomy for Remotely-Accessible Engineering Instructional Laboratories, ASEE Annual Conference and Exposition, American Society of Engineering Education, Seattle, USA.
This paper introduces an information taxonomy for remotely-accessible engineering
instructional laboratories [REILs]. A taxonomy within some given domain organizes and
clarifies the domain content and provides a common framework that supports and facilitates
reasoning, discussion, and communication about the domain in question. In this case, the
taxonomy aims to support reasoning, discussion, and communication about remotelyaccessible
engineering instructional laboratories.
This taxonomy was emergent from peer-reviewed remote laboratories literature. Twenty-five
papers were initially selected and analysed for terms which were characteristically descriptive
of a REIL. Over 1,000 such terms were identified. This number was reduced to some 800
through the elimination of duplicates and the conflation of equivalents. These 800 were then
examined, line-item by line-item and placed into a containing category. If a an appropriate
containing category did not exist, one was created. In the end, there were 37 containing
categories to hold all the terms.
Five additional REIL papers were then selected and close read for terms that were
descriptively characteristic of remotely-accessible engineering instructional laboratories. As
before, these terms were then considered, line-item by line-item, and placed in a containing
category. No additional containing categories were required during this follow on phase,
indicating that categorical saturation was achieved. Four top level categories were added to
the 37 containers; effectively creating an hierarchical taxonomy for REILs.
Yuwono, M, Su, SW, Moulton, BD, Guo, Y & Nguyen, HT 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.
Banjar, A, Pupatwibul, P, Braun, R & Moulton, B 2014, 'Analysing the performance of the OpenFlow standard for software-defined networking using the OMNeT++ network simulator', Conference on Computer Aided System Engineering (APCASE), 2014 Asia-Pacific, Asia-Pacific Conference on Computer Aided System Engineering (APCASE), IEEE, South Kuta, Indonesia, pp. 31-37.View/Download from: UTS OPUS or Publisher's site
Software-defined networking (SDN) is a relatively advanced method for implementing communication networks. SDN separates the decision maker, called the control plane, which decides where packets are sent, from the underlying infrastructure, called the data plane, which forwards packets to the decided destination. A newly emerging standard for SDN is the OpenFlow standard, which includes a standardized protocol for communications between the control plane and the data plane. This study analyses the extent to which the location of OpenFlow controllers affect the performance of an OpenFlow network. The analysis is undertaken using the OMNeT++ INET Framework discrete events network simulator. By analyzing key network metrics including round-trip-time (RTT) and data transfer rate (DTR), the results indicate the location of the controller has a demonstrable affect the performance of the network.
Yuwono, M, Su, SW, Moulton, BD & Nguyen, HT 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, International 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.
Tuttle, SW, Lowe, D & Moulton, B 2011, 'A Survey of Issues and Approaches to Remote Laboratory Adoption by Teacher-Academics', FiE 2011: 41st Frontiers in Education Conference: GOLC Workshop, IEEE Frontiers in Education Conference, IEEE, Rapid City, SD, USA.View/Download from: UTS OPUS or Publisher's site
Adoption is a key concern for those interested addressing the underutilization of remote engineering instructional laboratories (REIL). Lessons from related areas of technology adoption research are identified, presented, and related to REIL adoption. The REIL adoption perspective taken is that of the individual teacher-academic engaged in some aspect of engineering education which features laboratory work.
Yuwono, M, Su, SW, Moulton, BD & Nguyen, HT 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, International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Xplore, San Diego, CA, 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. © 2012 IEEE.
Yuwono, M, Su, SW, Moulton, BD & Nguyen, HT 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, International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Xplore, San Diego, CA, USA, pp. 2949-2952.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 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. © 2012 IEEE.
Yuwono, M, Su, SW, Moulton, BD & Nguyen, HT 2012, 'Optimization strategies for rapid centroid estimation', Proceedings of the 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, International 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 swarmÂ±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%Â±1.1% in 9Â±5 iterations) followed by RCE+ (89%Â±3.5% in 65Â±62 iterations) and RCE (87%Â±5.9% in 54Â±44). Similar quality is also reflected in other benchmark datasets including Iris, Wine, Breast Cancer, and Diabetes.
Yuwono, M, Su, SW, Moulton, BD & Nguyen, HT 2012, 'Fast unsupervised learning method for rapid estimation of cluster centroids', 2012 IEEE Congress of Evolutionary Computation, IEEE Congress on Evolutionary Computation, IEEE, Brisbane, QLD, Australia, 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.
Yuwono, M, Su, SW, Moulton, BD & Nguyen, HT 2012, 'Method for increasing the computation speed of an unsupervised learning approach for data clustering', IEEE Congress of Evolutionary Computation, IEEE Congress on 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.
Pirapinthan, M, Moulton, BD & Lal, S 2011, 'Trends in home-based safety and health alert support systems for older people', 2011 6th International Conference on Broadband and Biomedical Communications (IB2Com), International Conference on Broadband and Biomedical Communications, IEEE, Melbourne, Australia, pp. 206-212.View/Download from: UTS OPUS or Publisher's site
There is a trend towards the development of sensor systems to help older people improve their safety in the home environment. This is due to an increase in the average age of the population, together with a greater focus on providing non-hospital health care services, and greater availability of low-cost components to support such systems. It is expected that smart home care technologies would be potentially useful in monitoring the safety of the elderly in the home environment. The safety of older and disabled people can be continuously monitored without interrupting their daily routine with intelligent devices and modern sensors located in their home environment and on the body. While home care technologies are beneficial for older people, and encourage independence, there are still privacy and safety issue that need to be considered if such systems are to be widely adopted. Further research is required, especially with respect to regarding use cases and the cost implications of home-based systems.
Yuwono, M, Su, SW & Moulton, BD 2011, 'Fall detection using a Gaussian distribution of clustered knowledge, augmented radial basis neural-network, and multilayer perceptron', 2011 6th International Conference on Broadband and Biomedical Communications (IB2Com), International Conference on Broadband and Biomedical Communications, IEEE, Melbourne, Australia, pp. 145-150.View/Download from: UTS OPUS or Publisher's site
The rapidly increasing population of elderly people has posed a big challenge to research in fall prevention and detection. Substantial amounts of injuries, disabilities, traumas and deaths among elderly people due to falls have been reported worldwide. There is therefore a need for a reliable, simple, and affordable automatic fall detection system. This paper proposes a reliable fall detection algorithm using minimal information from a single waist worn wireless tri-axial accelerometer. The method proposed is to approach fall detection using digital signal processing and neural networks. This method includes the application of Discrete Wavelet Transform (DWT), Regrouping Particle Swarm Optimization (RegPSO), a proposed method called Gaussian Distribution of Clustered Knowledge (GCK), and an Ensemble of Classifiers using two different classifiers: Multilayer Perceptron Neural Network (MLP) and Augmented Radial Basis Neural Networks (ARBF). The proposed method has been tested on 8 healthy individuals in a home environment and yields promising result of up to 100% sensitivity on ingroup, 97.65% sensitivity on outgroup, and 99.56% specificity on Activities of Daily Living (ADL) data.
Moulton, BD 2008, 'Double Degrees: Concerns Regarding Overall Standards and Graduate Attributes such as Probabilistic Reasoning', Technological Developments in Education and Automation, International Joint Conferences on Computer, Information, and Systems Sciences, and Engineering, Springer, Bridgeport, USA, pp. 327-331.View/Download from: UTS OPUS or Publisher's site
Double degrees (also known as combined degrees) typically allow engineering students to complete, in just 5 years, two degrees that would ordinarily take 7 years to complete. This paper provides and discusses the results of a pilot study relating to engineering double degrees. The study participants offered opinions relating to non-engineering fields of interest, and why they enrolled in their current double degree course. The study found that double degree students appear to be interested in breadth, but not depth. This finding seems to contradict a prevailing view that double degrees offer students the potential to gain depth in a particular niche or âoverlap areaâ between the two degrees. The paper also discusses double degree curricula, in particular, the subjects that are âomittedâ from a typical double degree. It is noted that some elements that would ordinarily be strongly associated with depth and critical thinking seem to be missing from double degrees. The issue is exemplified in this paper by focusing on one aspect of critical thinking: probabilistic reasoning.
Moulton, BD, Hanlen, L, Chen, J, Croucher, G, Mahendran, L & Varis, AP 2010, 'Body-Area-Network transmission power control using variable adaptive feedback periodicity', Proceedings of the 2010 Australian Communications Theory Workshop (AusCTW), Australian Communications Theory Workshop, IEEE, Canberra, Australia, pp. 139-144.View/Download from: UTS OPUS or Publisher's site
We propose a class of adaptive power control protocol, where the period between each feedback transmission is adaptively varied to accommodate run-time variation in the quality of each channel. Initial analyses suggest that transmission control protocols with adaptive feedback periodicity can outperform other comparable schemes. For certain measured channels the period can increase to once every few minutes (thousands of packets) and still provides substantial power savings. Adaptive power control protocols also provide the potential to reduce intracell interference.
Moulton, BD 2008, 'Pro Bono in Engineering: Towards an Improved Understanding', Technological Developments in Education and Automation, International Joint Conferences ion Computer, Information, and Systems Sciences, and Engineering, Springer, Bridgeport, USA, pp. 333-337.View/Download from: UTS OPUS or Publisher's site
Pro bono work is more commonly associated with the legal profession than with the engineering profession. It is work that is undertaken at significantly reduced cost to a client. While many engineering professionals do undertake pro bono work, when compared with law and medicine, engineering pro bono work is not as well-known, nor does it attract high-profile support and visible recognition. This is despite the fact that the work of engineering organizations typically has great impact, for example by achieving safer water and improved sanitation. However, even though pro bono engineering work may be comparatively less visible, it is definitely occurring, frequently in ways that successfully address local capacity building, health, sanitation, information technology and housing issues among the most vulnerable and disadvantaged. This notwithstanding, it seems that a pro bono culture is less developed in the engineering profession than in the legal profession. It is proposed that part of the process for facilitating a pro bono culture within the engineering profession involves engineering education, and that to this end an important step is to understand engineering studentsâ current attitudes and values with respect to the principles of pro bono. Thus this paper provides the results of a preliminary study about studentsâ attitudes and values about pro bono engineering work. The results of this study suggest that only 10% clearly intend to, and a further 20% might, undertake some form of occasional pro bono work at some point in their careers, together with a general understanding of engineering pro bono. A goal of the study is to explore some underlying issues, with a view to making recommendations on the feasibility and viability of possible approaches for supporting greater recognition and adoption of principles of pro bono within the engineering profession.
Moulton, B.D. 2008, 'Unfolding Scenarios as Platforms for Experiential Learning Research', 11th International Conference on Experiential Learning (ICEL 2008): Identity of Experience: Challenges for Experiential Learning, 11th International Conference on Experiential Learning, UTS, Sydney, Australia, pp. 1-6.
Moulton, BD 2009, 'Conventions to achieve safer design and reduce catastrophic and routine harm to the environment', Proceedings 2009 International Conference on Computer Engineering and Technology, International Conference on Computer Engineering and Technology, The Printing House, Singapore, pp. 564-568.View/Download from: UTS OPUS or Publisher's site
A principle of safe design is that it is preferable for a design to "eliminate"hazards, rather than "manage"them. Some of the principles of safe design appear to be enacted in Australian legislation. In addition, tort law can hold designers liable for harm attributable to their actions and inactions. Designers' desire to avoid litigation most likely serves to curb extreme examples of reckless and harmful unsafe design. However, in many instances, it seems that designers who bring about "routine" harm tend not to be held liable. Nevertheless, when litigation does occur, the court ordinarily asks what a reasonable person in the position of the designer would have foreseen and done. In this context, it is proposed that safe design conventions may play two roles. First, such conventions may serve to influence designers in all countries to appreciate and adopt principles of safe design. Second, such conventions may help to provide courts with guidance as to what is expected of a reasonable person in the position of a designer.
Moulton, BD, Chen, J, Croucher, G, Lal, S, Lawrence, EM, Mahendran, L & Varis, AP 2009, 'Ambulatory Health Monitoring and Remote Sensing Systems to be used by Outpatients and Elders at Home: User-Related Design Considerations', 2009 11th IEEE International Conference on e-Health Networking, Applications & Services, International Conference on e-Health Networking, Applications & Services, IEEE International Conference, Sydney, Australia, pp. 48-53.View/Download from: UTS OPUS or Publisher's site
Recent developments have seen increased interest in the effect of end-user attributes on the in-practice effectiveness of systems that detect incapacitating falls and trauma at home. It is hoped that consideration and evaluation of such issues will ultimately result in long-term benefits including earlier crisis detection and response, reduced hospital admissions, and improved quality of life for relatively large groups of people. Key concerns include the needs and capabilities of end-users, the ability to nominate who is to be alerted, security, privacy, interface design and system failures. It is concluded that particularly relevant avenues for further research include end-user characteristics, interface design and peer-to-peer components.
Kumar, J, Chaczko, ZC, Moulton, BD & Mahdevan, V 2009, 'Investigating the Suitability of a .NET/SQL Server approach for developing a remotely accessible information system for vehicle inspectors, International Conference on Information and Network Technology', International Conference on Information and Network Technology 2009, International Conference on Information and Network Technology, ICINT 2009, Perth, Australia, pp. 1-7.View/Download from: UTS OPUS
Vehicle inspectors using current systems typically make mental or brief written notes while inspecting a vehicle, to be entered into a computer system at a later date. We propose a paperless system for vehicle inspection, and investigate some software engineering tools and methods for its development. The work was initiated as part of a final year computer system engineering thesis project. The research project involved analyses of the requirements and functional specifications, and included the design, implementation and analysis of a working prototype system. Preliminary evaluation of the approach suggests that it appears to be suitable for the development of the specified vehicle inspection information system. The approach is intended to be scalable, but questions remain as to the extent to which the approach is suitable for the development of a larger scale deployment.
Lee, C, Chaczko, ZC & Moulton, BD 2009, 'Bio-inspired Agent-based System for Cooperative Decision-making and Control of Unmanned Aerial Vehicles', Selected Papers on the 4th International Conference on Broadband Communication, Information Technology & Biomedical Applications, BroadBandCom '09, International Conference of Broadband Communication, Information Technology and Biomedical Applications, BroadBandCom '09, Wroclaw, Poland, pp. 105-110.View/Download from: UTS OPUS
Moulton, B.D. 2007, 'Towards an improved understanding of methods for obtaining information relevant for evaluating work integrated learning programs', Australaian Technology Network Evaluation and Assessment Conference 2007 Assessment and Evaluation for Real World Learning, Australaian Technology Network Evaluation and Assessment Conference, Queensland University of Technology, Brisbane, Queensland, pp. 95-101.View/Download from: UTS OPUS
This paper explores issues associated with research-based methods for obtaining information intended to be useful for evaluating work integrated learning programs. In particular, the paper compares and contrasts two studies undertaken within the University of Technology Sydney Faculty of Engineering
Moulton, B.D. & Lowe, D.B. 2006, 'Students' Perception about the relative importance of specific skills and knowledge for career performance', Proceedings of WACE Shanghai Asia Pacific, WACE Shanghai Asia Pacific Conference, WACE, Shanghai, China, pp. 1-12.View/Download from: UTS OPUS
Moulton, B.D. & Lowe, D.B. 2005, 'Engineering Students' perceptions of the importance of personal abilities in relation to career performance, and their perceptions of the extent to which their courses focus on personal abilities', Proceedings: 4th ASEE/AaeE Global Colloquium on Engineering Education, ASEE Global Colloquium of Engineering Education, University of Queensland, School of Engineering, Sydney, Australia, pp. 1-10.View/Download from: UTS OPUS
Moulton, B.D., McGregor, H.T., Coates, C. & Cedercreutz, K. 2004, 'Internship, Classroom & Other Sources of Ability', Learning Partnerships in the Global Classroom: Proceedings of the 5th Asia Pacific Cooperative Education Conference, Asia Pacific Cooperative Educaiton Conference, New Zealand Association for Cooperative Education, Auckland, New Zealand, pp. 1-8.View/Download from: UTS OPUS
Forrest, Y. & Moulton, B.D. 2003, 'New technology, new hazards: a survey of control operators', 2003 GBATA Readings Book, Global Business and Technology Association, Budapest, Hungary, pp. 425-429.
Moulton, B.D., Carmody, N.J. & Lasky, V. 2002, 'Practice-based engineering education: a distributed environment for teaching and learning embedded systems', 5th UICEE Annual Conference on Engineering Education Conference Proceedings, UICEE International Centre for Engineering Education, Chennai, India, pp. 33-35.