UTS site search

Dr Ahmed Al-Ani

Image of Ahmed Al-Ani
Senior Lecturer, School of Elec, Mech and Mechatronic Systems
Core Member, CHT - Centre for Health Technologies
Associate Member, GEVIC - Green Energy and Vehicle Innovations Centre
BSc (UT Baghdad), MPhil (QAU), PhD (QUT)
 
Phone
+61 2 9514 2420

Research Interests

Biomedical signal processing; and pattern classification

Can supervise: Yes

Chapters

Al-Ani, A. & Atiya, A. 2010, 'Pattern Classification using a Penalised Likelihood Method' in Schwenker, F. & El Gayar, N. (eds), Artificial Neural Networks in Pattern Recognition. Fourth IAPR TC3 Workshop., Springer, Germany, pp. 1-12.
View/Download from: UTS OPUS
Penalized likelihood is a well-known theoretically justified approach that has recently attracted attention by the machine learning society. The objective function of the Penalized likelihood consists of the log likelihood of the data minus some term penalizing non-smooth solutions. Subsequently, maximizing this objective function would lead to some sort of trade-off between the faithfulness and the smoothness of the fit. There has been a lot of research to utilize penalized likelihood in regression, however, it is still to be thoroughly investigated in the pattern classification domain. We propose to use a penalty term based on the Knearest neighbors and an iterative approach to estimate the posterior probabilities. In addition, instead of fixing the value of K for all pattern, we developed a variable K approach, where the number of neighbors can vary from one sample to another. The chosen value of K for a given testing sample is influenced by the K values of its surrounding training samples as well as the most successful K value of all training samples. Comparison with a number of well-known classification methods proved the potential of the proposed method.
Khushaba, R.N., Al-Ani, A. & Al-Jumaily, A. 2010, 'Swarm based Fuzzy Discriminant Analysis for Multifunction Prosthesis Control' in Goebel, R., Siekmann, J.R., WolfgangWahlster, Schwenker, F. & Gayar, N.E. (eds), Lecture Notes in Artificial Intelligence 5998 - Artificial Neural Networks in Pattern Recognition, Springer, Germany, pp. 197-206.
View/Download from: UTS OPUS or Publisher's site
In order to interface the amputeeâs with the real world, the myoelectric signal (MES) from human muscles is usually utilized within a pattern recognition scheme as an input to the controller of a prosthetic device. Since the MES is recorded using multi channels, the feature vector size can become very large. In order to reduce the computational cost and enhance the generalization capability of the classifier, a dimensionality reduction method is needed to identify an informative moderate size feature set. This paper proposes a new fuzzy version of the well known Fisherâs Linear Discriminant Analysis (LDA) feature projection technique. Furthermore, based on the fact that certain muscles might contribute more to the discrimination process, a novel feature weighting scheme is also presented by employing Particle Swarm Optimization (PSO) for the weights calculation. The new method, called PSOFLDA, is tested on real MES datasets and compared with other techniques to prove its superiority.
Khushaba, R.N., Al-Ani, A. & Al-Jumaily, A. 2009, 'Feature Subset Selection Using Differential Evolution' in Koppen, M., Kasabov, N. & Coghill, G. (eds), Advances in Neuro-Information Processing - Lecture Notes in Computer Science, Springer, Germany, pp. 103-110.
View/Download from: UTS OPUS or Publisher's site
One of the fundamental motivations for feature selection is to overcome the curse of dimensionality. A novel feature selection algorithm is developed in this chapter based on a combination of Differential Evolution (DE) optimization technique and statistical feature distribution measures. The new algorithm, referred to as DEFS, utilizes the DE float number optimizer in a combinatorial optimization problem like feature selection. The proposed DEFS highly reduces the computational cost while at the same time proves to present a powerful performance. The DEFS is tested as a search procedure on different datasets with varying dimensionality. Practical results indicate the significance of the proposed DEFS in terms of solutions optimality and memory requirements.
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.

Conferences

Al-Dmour, H., Ali, N. & Al-Ani, A. 2015, 'An Efficient Hybrid Steganography Method Based on Edge Adaptive and Tree Based Parity Check', MultiMedia Modeling (LNCS), 21st International Conference on MultiMedia Modelling, MMM 2015, Springer, Sydney, Australia, pp. 1-12.
View/Download from: Publisher's site
A major requirement for any steganography method is to minimize the changes that are introduced to the cover image by the data embedding process. Since the Human Visual System (HVS) is less sensitive to changes in sharp regions compared to smooth regions, edge adaptive has been proposed to discover edge regions and enhance the quality of the stego image as well as improve the embedding capacity. However, edge adaptive does not apply any coding scheme, and hence it embedding efficiency may not be optimal. In this paper, we propose a method that enhances edge adaptive by incorporating the Tree-Based Parity Check (TBPC) algorithm, which is a well-established coding-based steganography method. This combination enables not only the identification of potential pixels for embedding, but it also enhances the embedding efficiency through an efficient coding mechanism. More specifically, the method identifies the embedding locations according to the difference value between every two adjacent pixels, that form a block, in the cover image, and the number of embedding bits in each block is determined based on the difference between its two pixels. The incorporation of TBPC minimizes the modifications of the cover image, as it changes no more than two bits out of seven pixel bits when embedding four secret bits. Experimental results show that the proposed scheme can achieve both large embedding payload and high embedding efficiency.
Al-Dmour, H.T. & Al-Ani, A.H.M.E.D. 2015, 'Quality Optimized Medical Image Steganography Based on Edge Detection and Hamming Code', Proceedings of the International Symposium on Biomedical Imaging, International Symposium on Biomedical Imaging, IEEE, New York, USA, pp. 1486-1489.
View/Download from: Publisher's site
A Picture Archiving and Communication System (PACS) is a technology designed to store and transmit digitized medical images over a public network for certain uses. One of the main concerns relating to most of the existing systems is that little attention has been paid to the security and protection of patients' information. Accordingly, there has been an increased interest in recent years to enhance the confidentiality of patients' information. This paper introduces a high imperceptibility digital steganography method that hides Electronic Patient Records (EPR) into a medical image without modifying its important part. This method utilizes edge detection to identify and embed secret data in sharp regions of the image, as the human visual system (HVS) is less sensitive to changes in high contrast areas of images, compared to their smooth areas. Moreover, a Hamming code that embeds 3 secret message bits into 4 bits of the cover image is utilized as this will help in enhancing the quality of the produced images. We hide EPR into the Region of Non-Interest (RONI) to protect the decision area i.e., Region of Interest (ROI), which is essential for the diagnosis. The effectiveness of the proposed scheme is proven through the well-known of imperceptibility measure of Peak Signal-to-Noise Ratio (PSNR) when considering different message length.
Aljaafreh, A.O., Al-Ani, A., Aljaafreh, R. & Chandran, D. 2015, 'Understanding Customer's Initial Trust in Internet Banking Services: A Field Study in Jordan', ISD2015, 24th International Conference on Information Systems Development (ISD2015), AISEL, Harbin, China.
The aim of this study is to develop a unified model of initial trust for the adoption of internet banking services (IBS) in developing countries. In particular, three groups of factors have been investigated: trust literature, diffusion of innovation theory, and national culture, in order to reveal their effect on forming a customer's initial trust in IBS. We collected data using a survey and then analysed it using structural equation modelling. According to the obtained results, initial trust in internet banking services was significantly affected by: (i) factors obtained from the trust literature, which are disposition to trust, organisational structural assurance, and reputation. (ii) Relative advantages, which was adopted from the diffusion of innovation theory. (iii) Uncertainty avoidance, which is a dimension of national culture. Also, analysis of results showed a high impact of initial trust in IBS on the intention to use it. However, unlike developed countries, we found that some factors not to have noticeable influence on initial trust in IBS, such as: technical structural assurance and individualism versus collectivism.
Aljaafreh, A., Al-Ani, A., Aljaafreh, R. & Chandran, D. 2015, 'Understanding Customer's Initial Trust in Internet Banking Services: A field Study in Jordan', Proceedings of the 24th International Conference on Information Systems Development, 24th International Conference on Information Systems Development (ISD2015 Harbin), Department of Information Systems, City University of Hong Kong Copyright © 2015, City University of Hong Kong, Harbin, China, pp. 333-344.
View/Download from: UTS OPUS
The aim of this study is to develop a unified model of initial trust for the adoption of internet banking services (IBS) in developing countries. In particular, three groups of factors have been investigated: trust literature, diffusion of innovation theory, and national culture, in order to reveal their effect on forming a customer's initial trust in IBS. We collected data using a survey and then analysed it using structural equation modelling. According to the obtained results, initial trust in internet banking services was significantly affected by: (i) factors obtained from the trust literature, which are disposition to trust, organisational structural assurance, and reputation. (ii) Relative advantages, which was adopted from the diffusion of innovation theory. (iii) Uncertainty avoidance, which is a dimension of national culture. Also, analysis of results showed a high impact of initial trust in IBS on the intention to use it. However, unlike developed countries, we found that some factors not to have noticeable influence on initial trust in IBS, such as: technical structural assurance and individualism versus collectivism.
Al-Ani, A., Naik, G. & Abbass, H. 2015, 'A Methodology for Synthesizing Interdependent Multichannel EEG Data with a Comparison Among Three Blind Source Separation Techniques', Proceedings of the 22nd International Conference on Neural Information Processing, 22nd International Conference on Neural Information Processing, Springer International Publishing, Istanbul, Turkey, pp. 154-161.
View/Download from: Publisher's site
In this paper, we introduce a novel method for constructing synthetic, but realistic, data of four Electroencephalography (EEG) channels. The data generation technique relies on imitating the relationships between real EEG data spatially distributed over a closed-circle. The constructed synthetic dataset establishes ground truth that can be used to test different source separation techniques. The work then evaluates three projection techniques – Principal Component Analysis (PCA), Independent Component Analysis (ICA) and Canonical Component Analysis (CCA) – for source identification and noise removal on the constructed dataset. These techniques are commonly used within the EEG community. EEG data is known to be highly sensitive signals that get affected by many relevant and irrelevant sources including noise and artefacts. Since we know ground truth in a synthetic dataset, we used differential evolution as a global optimisation method to approximate the 'ideal transform that need to be discovered by a source separation technique. We then compared this transformation with the findings of PCA, ICA and CCA. Results show that all three techniques do not provide optimal separation between the noisy and relevant components, and hence can lead to loss of useful information when the noisy components are removed.
Al-Kaysi, A., Al-Ani, A. & Boonstra, T.W. 2015, 'A multichannel Deep Belief Network for the classification of EEG data', Nueral Information Processing - LNCS, International Conference on Neural Information Processing, Springer, Istanbul, Turkey, pp. 38-45.
View/Download from: UTS OPUS or Publisher's site
© Springer International Publishing Switzerland 2015. Deep learning, and in particular Deep Belief Network (DBN), has recently witnessed increased attention from researchers as a new classification platform. It has been successfully applied to a number of classification problems, such as image classification, speech recognition and natural language processing. However, deep learning has not been fully explored in electroencephalogram (EEG) classification. We propose in this paper three implementations of DBNs to classify multichannel EEG data based on different channel fusion levels. In order to evaluate the proposed method, we used EEG data that has been recorded to study the modulatory effect of transcranial direct current stimulation. One of the proposed DBNs produced very promising results when compared to three well-established classifiers; which are Support Vec- tor Machine (SVM), Linear Discriminant Analysis (LDA) and Extreme Learning Machine (ELM).
Mesbah, M., Khorshidtalab, A., Baali, H. & Al-Ani, A. 2015, 'Motor imagery task classification using a signal-dependent orthogonal transform based feature extraction', Neural Information Processing LNCS, 22nd International Conferenceon Nueral Information Processing, Springer, Istanbul, Turkey, pp. 1-9.
View/Download from: UTS OPUS or Publisher's site
© Springer International Publishing Switzerland 2015. In this paper, we present the results of classifying electroencephalographic (EEG) signals into four motor imagery tasks using a new method for feature extraction. This method is based on a signal-dependent orthogonal transform, referred to as LP-SVD, defined as the left singular vectors of the LPC filter impulse response matrix. Using a logistic tree based model classifier, the extracted features are mapped into one of four motor imagery movements, namely left hand, right hand, foot, and tongue. The proposed technique-based classification performance was benchmarked against those based on two widely used linear transform for feature extraction methods, namely discrete cosine transform (DCT) and adaptive autoregressive (AAR). By achieving an accuracy of 67.35 %, the LP-SVD based method outperformed the other two by large margins (+25 % compared to DCT and +6 % compared to AAR-based methods).
Al-Dmour, H. & Al-Ani, A. 2015, 'A Medical Image Steganography Method Based on Integer Wavelet Transform and Overlapping Edge Detection', Neural Information Processing - LNCS, Internatiuonal Conference on Neural Information Processing (ICONIP), Springer, Istanbul, Turkey, pp. 436-444.
View/Download from: UTS OPUS or Publisher's site
Recently, there has been an increased interest in the transmission of digital medical images for e-health services. However, existing implementations of this service do not pay much attention to the confidentiality and protection of patients' information. In this paper, we present a new medical image steganography technique for protecting patients' confidential information through the embedding of this information in the image itself while maintaining high quality of the image as well as high embedding capacity. This technique divides the cover image into two areas, the Region of Interest (ROI) and the Region of Non-Interest (RONI), by performing Otsu's method and then encloses ROI pixels in a rectangular shape according to the binary pixel intensities. In order to improve the security, the Electronic Patient Records (EPR) is embedded in the high frequency sub-bands of the wavelet transform domain of the RONI pixels. An edge detection method is proposed using overlapping blocks to identify and classify the edge regions. Then, it embeds two secret bits into three coefficient bits by performing an XOR operation to minimize the difference between the cover and stego images. The experimental results indicate that the proposed method provides a good compromise between security, embedding capacity and visual quality of the stego images
Aljaafreh, A.O., Gill, A.Q. & Al-Ani, A. 2014, 'Towards the Development of an Initial Trust Model for the Adoption of Internet Banking Services in Jordan', PACIS 2014 PROCEEDINGS, Pacific Asia Conference on Information Systems, AIS, Chengdu, China, pp. 1-11.
Internet banking service (IBS) is transforming the traditional ways of customer banking. Although IBS is very common in developed countries, however, its adoption by customers in developing countries is still very slow. This may well be due to the lack of customers trust in IBS in developing countries. This paper studies the important issue of customers initial trust in IBS in the Jordanian context and proposes the customer initial trust model. The objective of this model is to understand and analyse the underlying factors that affect the early stage of trust (i.e. initial customer trust) in IBS, which may, impact customers initial intention to use IBS. The proposed model of customers initial trust in IBS integrates constructs from Diffusion of Innovation (DoI) theory, Hofstede culture theory and trust literature. The distinguishable property of this model is the incorporation of national culture dimensions on initial trust. The proposed model will assist Jordanian banks in understanding the factors that may impact their customers initial trust in IBS.
Al-Ani, A. & Mesbah, M. 2014, 'Fuzzy Rule-Based Alertness State Classification Based On The Optimization Of EEG Rhythm/Channel Combinations', The 11th IASTED International Conference on Biomedical Engineering (BioMed 2014), ACTA Press, Zurich, Switzerland.
View/Download from: UTS OPUS or Publisher's site
This paper presents a method to automatically select the optimal EEG rhythm/channel combination capable of classifying the different human alertness states. We considered four alertness states, namely 'engaged', 'calm', 'drowsy', and 'asleep'. Energies associated with the conventional EEG rhythms, delta, theta, alpha, beta and gamma, extracted from overlapping segments of the different EEG channels were used as features. We followed a two-stage process, where in the first stage the optimal brain regions are identified, represented by a set of EEG channels are identified. In the second stage, a fuzzy rule-based alertness classification system (FRBACS) is developed to select the optimal EEG rhythms from the previously selected EEG channels. The IF-THEN rules used in FRBACS are constructed using a novel bi-level differential evolution (DE) based search algorithm. Unlike most of the existing classification methods, the proposed classification approach reveals easy to interpret rules that describe each of the alertness states.
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).
Aljaafreh, A. & Al-Ani, A. 2014, 'Conceptualizing Initial Trust in Internet Banking Services: A Pilot Study', International Conference on Information Systems Development (ISD), Varazdin, Croatia.
Ali, M., Al-Ani, A., Eamus, A., Tan, D. & Rochester, I. 2014, 'Detection of Nitrogen Status in Cotton using an Image Processing Approach', 25th International Scientific - Experts Congress On Agriculture and Food Industry, eme-İzmir/Turkey.
Aljaafreh, A.O., Gill, A.Q., Al-Ani, A., Al-adaileh, R.M. & Alzoubi, Y.I. 2013, 'Factors Influencing Customer's Initial Trust of Internet Banking Services in the Jordanian Context', 22nd IBIMA Conference, The 22nd IBIMA conference on Creating Global Competitive Economies: 2020 Vision Planning & Implementation, IBIM, Rome, Italy, pp. 281-288.
View/Download from: UTS OPUS
Internet banking services (IBS) offer many benefits to customers and banks. IBS have widely adopted and used in developed countries, however IBS adoption in developing countries such as Jordan is still low. Lack of customer trust is considered as the most important impediment to the use of IBS in developing countries. The aim of this study is to investigate and identify the factors that influence customers initial trust of IBS in the Jordanian context. This paper adopts the qualitative literature survey approach and reports two main categories: Human category and Information Technology category. Human category includes: personality- based trust, cognition-based trust (Reputation), Institutional-based trust (structural assurance), social factors (culture) and supporting factors (relative advantages). Information Technology category includes: website factors (security, privacy, and general online experiences)). We argue that these factors can be useful for organisations in understanding and addressing customers initial trust about IBS in the Jordanian context.
Ali, M.M., Al-Ani, A., Eamus, D. & Tan, D.K. 2013, 'An Algorithm Based on the RGB Colour Model to Estimate Plant Chlorophyll and Nitrogen Contents', 2013 International Conference on Sustainable Environment and Agriculture, 2013 International Conference on Sustainable Environment and Agriculture, International Association of Computer Science & Information Technology Press, Abu Dhabi, UAE, pp. 52-56.
View/Download from: UTS OPUS or Publisher's site
Leaf colour gives a good indication of chlorophyll (Ch) and nitrogen (N)status in plants. In this paper we developed a new, easy to use and non-destructive diagnostic approach to detect plantCh and N levels using an image processing technique developed using the RGB (Red, Green and Blue) colour model. The experiment was conducted on tomato (Tommy Toy) in field with three N treatments (0, 60 and 140 kg N / ha), where leaf images were collected using a handheld scanner. The new algorithm achieves superior correlation with the value of Ch and N, measured in laboratory, compared with the existing non-destructive methods of SPAD 502 and Dark green Colour Index (DGCI ).
Rabie, A., Al-Ani, A., Van Dun, B. & Dillon, H. 2013, 'Detection of alertness states using electroencephalogram and cortical auditory evoked potential responses', International IEEE/EMBS Conference on Neural Engineering, NER, pp. 1433-1436.
View/Download from: Publisher's site
In this paper, we focus on identifying the alertness state of subjects undergoing the cortical auditory evoked potential (CAEP) hearing test. A supervised classification approach is adopted, where subjects were advised to indicate their alertness states in specified time instances. Two sets of features are considered here to represent the recorded data. The first is based on the wavelet transform of the background EEG, while the second is obtained from the peaks of the CAEP responses. The rational behind using the second feature set is to evaluate the relationship between CAEP responses and alertness levels. Obtained results suggest that the CAEP-based features are very comparable, in terms of classification accuracy, to the well-established wavelet-based features of EEG signals (79% compared to 80%). The findings of this paper will contribute towards a better understanding of CAEP responses at the different alertness states. © 2013 IEEE.
Al-Ani, A. & Khushaba, R.N. 2012, 'A Population based Feature Subset Selection Algorithm Guided by Fuzzy Feature Dependency', Advanced Machine Learning Technologies and Applications, The first International Conference on Advanced Machine Learning Technologies and Applications (AMLTA12), Springer Berlin Heidelberg, Cairo, Egypt, pp. 430-438.
View/Download from: UTS OPUS
Population-based (or evolutionary) algorithms have been attracting an increased attention due to their powerful search capabilities. For the particular problem of feature selection, population-based methods aim to produce better or fitter future generations that contain more informative subsets of features. It is well-known that feature subset selection is a very challenging optimization problem, especially when dealing with datasets that contain large number of features. Most of the commonly used population-based feature selection methods use operators that do not take into account relationships between features to generate future subsets, which can have an impact on their capabilities to properly explore the search space. We present here a new populationbased feature selection method that utilize dependency between features to guide the search. In addition, a novel method for estimating dependency between feature pairs is proposed based on the concept of fuzzy entropy. Results obtained from datasets with various sizes indicate the superiority of the proposed method in comparison to some of the wellknown methods in the literature.
Ali, M., Al-Ani, A., Eamus, D. & Tan, D. 2012, 'Leaf Nitrogen Determination using Handheld Meters', 16th Australian Agronomy Conference 2012, Armidale, NSW.
Alsukker, A., Khushaba, R.N. & Al-Ani, A. 2010, 'Enhancing the diversity of genetic algorithm for improved feature selection', 2010 IEEE International Conference on Systems Man and Cybernetics (SMC), IEEE, Istanbul, pp. 1325-1331.
View/Download from: UTS OPUS or Publisher's site
Genetic algorithm (GA) is one of the most widely used population-based evolutionary search algorithms. One of the challenging optimization problems in which GA has been extensively applied is feature selection. It aims at finding an optimal small size subset of features from the original large feature set. It has been found that the main limitation of the traditional GA-based feature selection is that it tends to get trapped in local minima, a problem known as premature convergence. A number of implementations are presented in the literature to overcome this problem based on fitness scaling, genetic operator modification, boosting genetic population diversity, etc. This paper presents a new modified genetic algorithm based on enhanced population diversity, parents' selection and improved genetic operators. Practical results indicate the significance of the proposed GA variant in comparison to many other algorithms from the literature on different datasets.
Alsukker, A.S. & Al-Ani, A. 2011, 'An Enhanced Neural Network Ensemble for Automatic Sleep Scoring', International Conference on Communications and Information Technology (ICCIT 2011), International Conference on Communications and Information Technology (ICCIT 2011), IEEE Xplore, Aqaba, Jordan, pp. 126-129.
View/Download from: UTS OPUS or Publisher's site
Improving the diversity of Neural Network Ensembles (NNE) plays an important role in creating robust classification systems in many fields. Several methods have been proposed in the literature to create such diversity using different sets of classifiers or using different portions of training/feature sets. Neural networks are often used as base classifiers in multiple classifier systems as they adapt easily to small changes in the training data, therefore creating diversity that is necessary to make the ensemble work. This paper presents a novel algorithm based on generating a set of classifiers such that each one of them is biased towards one of the target classes. This will improve the ensemble diversity and hence its performance. Results on sleep data sets show that the proposed method is able to outperform the traditional fusion algorithms of bagging and boosting.
Alsukker, A.S., Khushaba, R.N. & Al-Ani, A. 2010, 'Optimising the K-NN Metric Weights Using Differential Evolution', International Conference on Multimedia Computing and Information Technology (MCIT-2010), International Conference on Multimedia Computing and Information Technology, IEEE, U.A.E., pp. 89-92.
View/Download from: UTS OPUS
Traditional k-NN classifier poses many limitations including that it does not take into account each class distribution, importance of each feature, contribution ofeach neighbor, and the number ofinstances for each class. A Differential evolution (DE) optimization technique is utilized to enhance the performance of kNN through optimizing the metric weights offeatures, neighbors and classes. Several datasets are used to evaluate the performance of the proposed DE based metrics and to compare it to some k-NN variants from the literature. Practical experiments indicate that in most cases, incorporating DE in k-NN classification can provide more accurate performance.
Khushaba, R.N., Elliott, R., Alsukker, A., Al-Ani, A. & McKinley, S.M. 2010, 'Orthogonal locality sensitive fuzzy discriminant analysis in sleep-stage scoring', Proceedings - 2010 International Conference on Pattern Recognition, International Conference on Pattern Recognition, IEEE, Istanbul, Turkey, pp. 165-168.
View/Download from: UTS OPUS or Publisher's site
Sleep-stage scoring plays an important role in analyzing the sleep patterns of people. Studies have revealed that Intensive Care Unit (ICU) patients do not usually get enough quality sleep, and hence, analyzing their sleep patterns is of increased import
Alsukker, A.S., Al-Ani, A. & Atiya, A. 2009, 'A Modified K-Nearest Neighbor Classifier to Deal with Unbalanced Classes', International Conference on Neural Computation (ICNC 2009), International Conference on Neural Computation, INSTICC - Institute for Systems and Technologies of Information, Control and Communication, Madeira, Portugal, pp. 408-413.
View/Download from: UTS OPUS
We present in this paper a simple, yet valuable improvement to the traditional k-Nearest Neighbor (kNN) classifier. It aims at addressing the issue of unbalanced classes by maximizing the class-wise classification accuracy. The proposed classifier also gives the option of favoring a particular class through evaluating a small set of fuzzy rules. When tested on a number of UCI datasets, the proposed algorithm managed to achieve a uniformly good performance.
Khushaba, R.N., Al-Ani, A., Alsukker, A.S. & Al-Jumaily, A. 2008, 'A Combined Ant Colony and Differential Evolution Feature Selection Algorithm', Lecture Notes In Computer Science Vol 5217: Ant Colony Optimization and Swarm Intelligence, International Workshop on Ant Colony, Springer, Brussels, Belgium, pp. 1-12.
View/Download from: UTS OPUS or Publisher's site
Feature selection is an important step in many pattern recognition systems that aims to overcome the so-called curse of dimensionality problem. Although Ant Colony Optimization (ACO) proved to be a powerful technique in different optimization problems, but it still needs some improvements when applied to the feature selection problem. This is due to the fact that it builds its solutions sequentially, where in feature selection this behavior will most likely not lead to the optimal solution. In this paper, a novel feature selection algorithm based on a combination of ACO and a simple, yet powerful, Differential Evolution (DE) operator is presented. The proposed combination enhances both the exploration and exploitation capabilities of the search procedure. The new algorithm is tested on two biosignal-driven applications. The performance of the proposed algorithm is compared with other dimensionality reduction techniques to prove its superiority.
Khushaba, R.N., Al-Ani, A. & Al-Jumaily, A. 2008, 'Differential Evolution based Feature Subset Selection', Proceedings of the 19th International Conference on Pattern Recognition (ICPR-2008), International Conference on Pattern Recognition, IEEE, USA, pp. 1-4.
View/Download from: UTS OPUS or Publisher's site
In this paper, a novel feature selection algorithm based on differential evolution (DE) optimization technique is presented. The new algorithm, called DEFS, modifies the DE which is a real-valued optimizer, to suit the problem of feature selection. The proposed DEFS highly reduces the computational costs while at the same time proving to present powerful performance. The DEFS technique is applied to a brain-computer-interface (BCI) application and compared with other dimensionality reduction techniques. The practical results indicate the significance of the proposed algorithm in terms of solutions optimality, memory requirement, and computational cost.
Khushaba, R.N., Al-Ani, A. & Al-Jumaily, A. 2008, 'Fuzzy Discriminant Analysis based Feature Projection in Myoelectric Control', 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, Canada, pp. 5049-5052.
View/Download from: UTS OPUS or Publisher's site
The myoelectric signal (MES) from human muscles is usually utilized as an input to the controller of a multifunction prosthetic hand. In such a system, a pattern recognition approach is usually employed to discriminate between the MES from different classes. Since the MES is recorded using multi channels, the feature vector size can become very large. In order to reduce the computational cost and enhance the generalization capability of the classifier, a dimensionality reduction method is needed to identify an informative moderate size feature set. This paper proposes a novel feature projection technique based on a combination of Fisher's Linear Discriminant Analysis (LDA), and Fuzzy Logic. The new method, called FLDA, assigns different membership degrees to the data points thus reducing the effect of overlapping points in the discrimination process. Furthermore, the concept of Mutual Information (MI) is introduced in the fuzzy memberships in order to assign weights to the features (attributes) according to their contribution to the discrimination process. The FLDA method is tested on a seven classes MES dataset and compared with other feature projection techniques proving its superiority.
Alsukker, A.S., Khushaba, R.N., Al-Ani, A. & Al-Jumaily, A. 2008, 'Enhanced Feature Selection Algorithm Using Ant Colony Optimization and Fuzzy Memberships', Proceedings of the 6th IASTED International Conference on Biomedical Engineering (BioMED 2008), IASTED International Conference on Biomedical Engineering, IASTED, Innsbruck, Austria, pp. 34-39.
View/Download from: UTS OPUS
Feature selection is an indispensable pre-processing step when mining huge datasets that can significantly improve the overall system performance. This paper presents a novel feature selection method that utilizes both the Ant Colony Optimization (ACO) and fuzzy memberships. The algorithm estimates the local importance of subsets of features, i.e., their pheromone intensities by utilizing fuzzy c-means (FCM) clustering technique. In order to prove the effectiveness of the proposed method, a comparison with another powerful ACO based feature selection algorithm that utilizes the Mutual Information (MI) concept is presented. The method is tested on two biosignals driven applications: Brain Computer Interface (BCI), and prosthetic devices control with myoelectric signals (MES). A linear discriminant analysis (LDA) classifier is used to measure the performance of the selected subsets in both applications. Practical experiments prove that the new algorithm can be as accurate as the original method with MI, but with a significant reduction in computational cost, especially when dealing with huge datasets.
Khushaba, R.N., Al-Ani, A. & Al-Jumaily, A. 2008, 'Swarm Intelligence In Myoelectric Control: Particle Swarm Based Dimensionality Reduction', 6th IASTED International Conference on Biomedical Engineering (BioMED 2008), IASTED International Conference on Biomedical Engineering, IASTED, Austria, pp. 601-694.
View/Download from: UTS OPUS
The myoelectric signals (MES) from human muscles have been utilized in many applications such as prosthesis control. The identification of various MES temporal structures is used to control the movement of prosthetic devices by utilizing a pattern recognition approach. Recent advances in this field have shown that there are a number of factors limiting the clinical availability of such systems. Several control strategies have been proposed but deficiencies still exist with most of those strategies especially with the Dimensionality Reduction (DR) part. This paper proposes using Particle Swarm Optimization (PSO) algorithm with the concept of Mutual Information (MI) to produce a novel hybrid feature selection algorithm. The new algorithm, called PSOMIFS, is utilized as a DR tool in myoelectric control problems. The PSOMIFS will be compared with other techniques to prove the effectiveness of the proposed method. Accurate results are acquired using only a small subset of the original feature set producing a classification accuracy of 99% across a problem of ten classes based on tests done on six subjects MES datasets.
Khushaba, R.N., Alsukker, A.S., Al-Ani, A. & Al-Jumaily, A. 2008, 'Intelligent Artificial Ants based Feature Extraction from Wavelet Packet Coefficients for Biomedical Signal Classification', 3rd International Symposium on Communications, Control and Signal Processing (ISCCSP 2008), International Symposium on Communications, Control and Signal Processing, IEEE, Malta, pp. 1366-1371.
View/Download from: UTS OPUS or Publisher's site
n this paper, a new feature extraction method utilizing ant colony optimization in the selection of wavelet packet transform (WPT) best basis is presented and adopted in classifying biomedical signals. The new algorithm, termed intelligent artificial ants (IAA), searches the wavelet packet tree for subsets of features that best interact together to produce high classification accuracies. While traversing the WPT tree, the IAA takes into account existing correlation between features thus avoiding information redundancy. The IAA method is a mixture of filter and wrapper approaches in feature subset selection. The pheromone that the ants lay down is updated by means of an estimation of the information contents of a single feature or feature subset. The significance of the subsets selected by the ants is measured using linear discriminant analysis (LDA) classifier. The IAA method is tested on one of the most important biosignal driven applications, which is the brain computer interface (BCI) problem with 56 EEG channels. Practical results indicate the significance of the proposed method achieving a maximum accuracy of 83%.
Khushaba, R.N., Al-Ani, A. & Al-Jumaily, A. 2008, 'Swarm intelligence in myoelectric control: Particle Swarm based Dimensionality Reduction', Proceedings of the 6th IASTED International Conference on Biomedical Engineering, BioMED 2008, pp. 40-45.
The myoelectric signals (MES) from human muscles have been utilized in many applications such as prosthesis control. The identification of various MES temporal structures is used to control the movement of prosthetic devices by utilizing a pattern recognition approach. Recent advances in this field have shown that there are a number of factors limiting the clinical availability of such systems. Several control strategies have been proposed but deficiencies still exist with most of those strategies especially with the Dimensionality Reduction (DR) part. This paper proposes using Particle Swarm Optimization (PSO) algorithm with the concept of Mutual Information (MI) to produce a novel hybrid feature selection algorithm. The new algorithm, called PSOMIFS, is utilized as a DR tool in myoelectric control problems. The PSOMIFS will be compared with other techniques to prove the effectiveness of the proposed method. Accurate results are acquired using only a small subset of the original feature set producing a classification accuracy of 99% across a problem of ten classes based on tests done on six subjects MES datasets.
Khushaba, R.N., Al-Jumaily, A. & Al-Ani, A. 2008, 'Fuzzy discriminant analysis based feature projection in myoelectric control', Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology", pp. 5049-5052.
The myoelectric signal (MES) from human muscles is usually utilized as an input to the controller of a multifunction prosthetic hand. In such a system, a pattern recognition approach is usually employed to discriminate between the MES from different classes. Since the MES is recorded using multi channels, the feature vector size can become very large. In order to reduce the computational cost and enhance the generalization capability of the classifier, a dimensionality reduction method is needed to identify an informative moderate size feature set. This paper proposes a novel feature projection technique based on a combination of Fisher's Linear Discriminant Analysis (LDA), and Fuzzy Logic. The new method, called FLDA, assigns different membership degrees to the data points thus reducing the effect of overlapping points in the discrimination process. Furthermore, the concept of Mutual Information (MI) is introduced in the fuzzy memberships in order to assign weights to the features (attributes) according to their contribution to the discrimination process. The FLDA method is tested on a seven classes MES dataset and compared with other feature projection techniques proving its superiority. © 2008 IEEE.
Al-Azzawi, A.A., Aziz, R.J. & Al-Ani, A.A. 2008, 'Finite element analysis of conical shell foundations', Proceedings of the 6th International Conference on Engineering Computational Technology.
In this paper, the conical shell foundation is investigated. The two components of the interacting system; the soil and the shell foundation, are modelled using the finite element method. In this study, 8-node isoparametric degenerated shell element with five degrees of freedom at each node is used. The soil-structure interaction between the shell elements and the supporting medium are modeled by representing the soil medium by certain analytical equivalent such as Winkler model with both normal compressional and tangential frictional resistances. A parametric studies have been carried out to investigate the effect of some important parameters on the behaviour of shell foundations. Three parameters are considered which are: semi-vertical angle, conical shell thickness and vertical subgrade reaction. Comparison between the results obtained by the present analysis and those obtained by other investigations are made. The present analysis shows satisfactory results when compared with those obtained by other studies with largest percentage difference of 2.5% in the value of the vertical displacement. © 2008 Civil-Comp Press.
Darvishi, S. & Al-Ani, A. 2007, 'Brain-Computer Interface Analysis using Continuous Wavelet Transform and Adaptive Neuro-Fuzzy 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. 3220-3223.
View/Download from: UTS OPUS or Publisher's site
The purpose of this paper is to analyze the electroencephalogram (EEG) signals of imaginary left and right hand movements, an application of Brain-Computer Interface (BCI). We propose here to use an Adaptive Neuron-Fuzzy Inference System (ANFIS) as the classification algorithm. ANFIS has an advantage over many classification algorithms in that it provides a set of parameters and linguistic rules that can be useful in interpreting the relationship between extracted features. The continuous wavelet transform will be used to extract highly representative features from selected scales. The performance of ANFIS will be compared with the well-known support vector machine classifier.
Khushaba, R.N., Al-Jumaily, A. & Al-Ani, A. 2007, 'Novel Feature Extraction Method based on Fuzzy Entropy and Wavelet Packet Transform for Myoelectric Control', Proceedings 7th International Symposium on Communications and Information Technologies (ISCIT '07), 2007, International Symposium on Communications and Information Technologies, IEEE, Sydney, Australia, pp. 352-357.
View/Download from: UTS OPUS or Publisher's site
In this paper, a novel feature extraction method based on the utilization of wavelet packet transform (WPT) and the concept of fuzzy entropy is presented. The method acts in steps, were in the first step the WPT is employed to generate a wavelet decomposition tree from which many features are extracted. In the second step, a new algorithm to compute the fuzzy entropy is developed and adopted as a measure of information content to judge on features suitability in classification, by setting a threshold and removing the features that fall under a certain threshold. In the third step, principle component analysis (PCA) is employed to reduce the dimensionality of the generated feature set. As an application, the new algorithm is employed in multifunction myoelectric control problem to prove its efficiency. Accurate results (99% accuracy) are acquired from using only a small subset of the original feature set generated by the wavelet tree. The obtained results indicate that the generated features are of maximum relevance and with minimum degree of redundancy.
Khushaba, R.N., Al-Ani, A. & Al-Jumaily, A. 2007, 'Swarm Intelligence based Dimensionality Reduction for Myoelectric Control', The third International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP) 2007, International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE, Melbourne, Australia, pp. 577-582.
View/Download from: UTS OPUS or Publisher's site
Recent approaches in multifunction myoelectrically controlled prosthetic devices revealed that dimensionality reduction plays a significant role in the overall system performance. In this paper, a new feature selection method is developed based on a mixture of particle swarm optimization (PSO) method and the concept of mutual information (MI). The new method, termed PSO-MI, is adopted as a dimensionality reduction tool for myoelectric control. The PSO-MI employs the MI measure to aid in controlling the movements of particles in the solution space, thus forming a kind of a hybrid filter-wrapper method. The new PSO-MI is able to account for the interaction property between the features in the selected subset, thus producing high classification accuracies. A dataset of transient myoelectric signal (MES) consisting of six classes of hand grasp is utilized to test the performance of the proposed method. It is proved that the PSO-MI outperforms other methods adopted for dimensionality reduction in myoelectric control achieving 95.5% of classification accuracy across six classes problem.
Darvishi, S. & Al-Ani, A. 2007, 'Brain-computer interface analysis using continuous wavelet transform and adaptive neuro-fuzzy classifier', Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 3220-3223.
View/Download from: Publisher's site
The purpose of this paper is to analyze the electroencephalogram (EEG) signals of imaginary left and right hand movements, an application of Brain-Computer Interface (BCI). We propose here to use an Adaptive Neuron-Fuzzy Inference System (ANFIS) as the classification algorithm. ANFIS has an advantage over many classification algorithms in that it provides a set of parameters and linguistic rules that can be useful in interpreting the relationship between extracted features. The continuous wavelet transform will be used to extract highly representative features from selected scales. The performance of ANFIS will be compared with the well-known support vector machine classifier. © 2007 IEEE.
Al-Ani, A. & Alsukker, A.S. 2006, 'Effect of Feature and channel Selection on EEG Classification', Proceedings of the 28th 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, New York City, USA, pp. 2171-2174.
View/Download from: UTS OPUS or Publisher's site
n this paper, we evaluate the significance of feature and channel selection on EEG classification. The selection process is performed by searching the feature/channel space using genetic algorithm, and evaluating the importance of subsets using a linear support vector machine classifier. Three approaches have been considered: (i) selecting a subset of features that will be used to represent a specified set of channels, (ii) selecting channels that are each represented by a specified set of features, and (iii) selecting individual features from different channels. When applied to a brain-computer interface (BCI) problem, results indicate that improvement in classification accuracy can be achieved by considering the correct combination of channels and features
Alsukker, A.S. & Al-Ani, A. 2006, 'Evaluation of Feature Selection Methods for Improved EEG Classification', Proceedings of the International Conference on Biomedical and Pharmaceutical Engineering, International Conference on Biomedical and Pharmaceutical Engineering, Research Publishing Services, Singapore, pp. 146-151.
View/Download from: UTS OPUS
Al-Ani, A. 2006, 'Channell and Feature Classifier Fusion in EEG Analysis', Proceedings of the 3rd Cairo International Biomedical Engineering Conference (CIBEC06), IEEE, Cairo, Egypt, p. CV1.4.
Al-Ani, A. 2005, 'An Ant Colony Optimization Based Approach for Feature Selection', AIML 2005 Proceedings, ICGT International Conference on Artifical Intelligence and Machine Learning, The International Congress for Global Science and Technology (ICGST), Cairo, Egypt, pp. 1-6.
View/Download from: UTS OPUS
This paper presents a new feature subset selection algorithm based on the Ant Colony Optimization (ACO). ACO is a metaheuristic inspired by the behaviour of real ants in their search for the shortest paths to food sources. It looks for optimal solutions by utilizing distributed computing, local heuristics and previous knowledge. We modified the ACO algorithm so that it can be used to search for the best subsets of features. A new pheromone trail update formula is presented, and the various parameters that lead to better convergence are tested. Results on speech classification problem show that the proposed algorithm achieves better performance than both greedy and genetic algorithm based feature selection methods.
Al-Ani, A. & Bennamoun, M. 2004, 'An edge fusion approach based on the concept of multiple detector behavior', Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, pp. 2999-3003.
View/Download from: Publisher's site
One of the fundamental steps in image processing is edge detection. The performance of any edge detection method is highly affected by the choice of parameters, e.g. thresholds. For some applications, such as identi cat ion of objects in a scene, the interesting regions do not usually cover the whole image. Hence, applying edge detection with global parameters to these images will detect Edges of Interest (EoI) as well as edges caused by background details, illumination or re ect ance. We present here a new edge fusion approach that aims at identifying edges of interest and discarding unwanted edges. For this purpose, different parameter values are used to generate edge images from a given gray-scale image. The image is then divided into small windows and for each window the local detection accuracy of the various parameter values are estimated. Finally, the edge images are fused to produce a new edge image by locally choosing parameter values that achieve maximum detection accuracy. Initial results have shown that this method has the potential to produce very promising results. © 2004 IEEE.
Al-Ani, A. & Deriche, M. 2002, 'Feature selection using a mutual information based measure', Proceedings - International Conference on Pattern Recognition, pp. 82-85.
In this paper, we discuss the problem of feature selection for the purpose of classification and propose a solution based on the concept of mutual information. In addition, we propose a new evaluation function to measure the ability of feature subsets in distinguishing between class labels. The proposed function is based on the information gain and takes into consideration how features work together. Finally, we discuss the performance of this function compared to that of other measures which evaluate features individually. © 2002 IEEE.
Al-Ani, A. & Deriche, M. 2002, 'A new algorithm for multi-channel EEG signal analysis using mutual information', ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. III/2961-III/2964.
Electroencephalogram (EEG) signals have long been used for the analysis of brain activities and for the detection of abnormalities (such as seizures). More recently, and with advance of computer technology, we have seen new applications using EEG signals in the control of PC keyboards through BCIs (Brain Computer Interfaces). These EEG signals are normally collected through multi-sensors (8, 12 or channels). For proper interpretation of such data, several techniques have been proposed to extract features from the collected multi-channel data, then analyse them, or classify them into patterns. However, most existing techniques do not take into consideration the inherent relationship among features across channels. Here, we propose a scheme based on a hybrid information maximization concept (HIM) to process multi-channel data for optimal feature extraction. The experiments carried show a clear advantage of the approach over principal component and canonical correlation analysis.
Al-Ani, A. & Deriche, M. 2001, 'An optimal feature selection technique using the concept of mutual information', 6th International Symposium on Signal Processing and Its Applications, ISSPA 2001 - Proceedings; 6 Tutorials in Communications, Image Processing and Signal Analysis, pp. 477-480.
View/Download from: Publisher's site
We present a mutual information-based technique to perform feature selection for the purpose of classification. The technique selects those features that have maximum mutual information with the specified classes. The best solution may be obtained through an exhaustive search (all possible combinations). However, even with a small number of features, this solution becomes impractical due to the exponentially increasing computational cost. Unlike other techniques that select features individually, our technique considers a trade off between computational cost and combined feature selection. Extensive experiments have shown that the proposed technique outperforms existing feature selection methods based on individual features. © 2001 IEEE.
Al-Ani, A. & Deriche, M. 2001, 'A Dempster-Shafer theory of evidence approach for combining trained neural networks', Proceedings - IEEE International Symposium on Circuits and Systems, pp. 703-706.
The Dempster-Shafer theory of evidence is a powerful method for combining measures of evidence from different classifiers. However, since there is not a unique way to perform such a combination, we have developed an algorithm which adapts to the training data set so that the overall mean square error is minimised. The proposed method was proved to be superior and more robust than other available combination methods.
Deriche, M. & Al-Ani, A. 2001, 'A new algorithm for EEG feature selection using mutual information', ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 1057-1060.
An EEG feature selection technique for the purpose of classification is developed. The technique selects those features that have maximum mutual information with the specified classes of interest (two classes in this case). Obviously, the simplest way is to consider all possible feature subsets (M out of N). However, even with a small number of features, this procedure is computationally impossible and can not be used in practice. Given the fact that most features used to represent EEG signal are sets of features (such as AR parameters), our technique considers a trade off between computational cost and chosen feature combination. This contrasts other techniques which select features individually. The classification accuracy of features obtained by applying our technique outperforms those obtained by applying individual feature selection methods when applied to EEG signals.
Al-Ani, A. & Deriche, M. 2000, 'Hybrid information maximisation (HIM) algorithm for optimal feature selection from multi-channel data', ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 3470-3473.
A novel feature selection algorithm is derived for multi-channel data. This algorithm is a hybrid information maximisation (HIM) technique based on 1) maximising the mutual information between the input and output of a network using the infomax algorithm proposed by Linsker, and 2) maximising the mutual information between outputs of different network modules using the Imax algorithm introduced by Becker. The infomax algorithm is useful in reducing the redundancy in the output units, while the Imax algorithm is capable of selecting higher order features from the input units. In this paper, we analyse the two methods and generalise the learning procedure of the Imax algorithm to make it suitable for maximising the mutual information between multi-dimensional output units from different network modules contrary to the original Imax algorithm which only maximises mutual information between two output units. We show that the proposed HIM algorithm provides a better representation of input compared to the original two algorithms when used separately. Finally, the HIM is evaluated with respect to biological plausibility in the case of feature selection from two-channel EEG data.

Journal articles

Alzoubi, Y., Gill, A.Q. & Al-ani, A. 2016, 'Empirical studies of geographically distributed agile development communication challenges: A systematic review', Information & Management, vol. 53, no. 1, pp. 22-37.
View/Download from: UTS OPUS or Publisher's site
There is increasing interest in studying and applying geographically distributed agile development (GDAD). Much has been published on GDAD communication. There is a need to systematically review and synthesize the literature on GDAD communication challenges. Using the SLR approach and applying customized search criteria derived from the research questions, 21 relevant empirical studies were identified and reviewed in this paper. The data from these papers were extracted to identify communication challenges and the techniques used to overcome these challenges. The findings of this research serve as a resource for GDAD practitioners and researchers when setting future research priorities and directions.
Al-Dmour, H. & Al-Ani, A. 2016, 'A steganography embedding method based on edge identification and XOR coding', Expert Systems with Applications, vol. 46, pp. 293-306.
View/Download from: Publisher's site
© 2015 Elsevier Ltd. All rights reserved. In this paper, we present a novel image steganography algorithm that combines the strengths of edge detection and XOR coding, to conceal a secret message either in the spatial domain or an Integer Wavelet Transform (IWT) based transform domain of the cover image. Edge detection enables the identification of sharp edges in the cover image that when embedding in would cause less degradation to the image quality compared to embedding in a pre-specified set of pixels that do not differentiate between sharp and smooth areas. This is motivated by the fact that the human visual system (HVS) is less sensitive to changes in sharp contrast areas compared to uniform areas of the image. The edge detection method presented here is capable of estimating the exact edge intensities for both the cover and stego images (before and after embedding the message), which is essential when extracting the message. The XOR coding, on the other hand, is a simple, yet effective, process that helps in reducing differences between the cover and stego images. In order to embed three secret message bits, the algorithm requires four bits of the cover image, but due to the coding mechanism, no more than two of the four bits will be changed when producing the stego image. The proposed method utilizes the sharpest regions of the image first and then gradually moves to the less sharp regions. Experimental results demonstrate that the proposed method has achieved better imperceptibility results than other popular steganography methods. Furthermore, when applying a textural feature steganalytic algorithm to differentiate between cover and stego images produced using various embedding rates, the proposed method maintained a good level of security compared to other steganography methods.
Al-Dmour, H. & Al-Ani, A. 2016, 'Quality Optimized Medical Image Information Hiding Algorithm that Employs Edge Detection and Data Coding', Computer Methods and Programs in Biomedicine.
View/Download from: Publisher's site
Ali, M., Al-Ani, A., Eamus, D. & Tan, D. 2016, 'Leaf Nitrogen Determination Using Non-Destructive Techniques – A Review', Journal of Plant Nutrition.
View/Download from: UTS OPUS or Publisher's site
The optimisation of plant nitrogen-use-efficiency (NUE) has a direct impact on increasing crop production by optimising use of nitrogen fertiliser. Moreover, it protects environment from negative effects of nitrate leaching and nitrous oxide production. Accordingly, nitrogen (N) management in agriculture systems has been major focus of many researchers. Improvement of NUE can be achieved through several methods including more accurate measurement of foliar N contents of crops during different growth phases. There are two types of methods to diagnose foliar N status: destructive and non-destructive. Destructive methods are expensive and time-consuming as they require tissue sampling and subsequent laboratory analysis. Thus, many farmers find destructive methods to be less attractive. Non-destructive methods are rapid and less expensive but are usually less accurate. Accordingly, improving the accuracy of non-destructive N estimations has become a common goal of many researchers, and various methods varying in complexity and optimality have been proposed for this purpose. This paper reviews various commonly used non-destructive methods for estimating foliar N status of plants.
Tareef, A. & Al-Ani, A. 2015, 'A highly secure oblivious sparse coding-based watermarking system for ownership verification', Expert Systems with Applications, vol. 42, no. 4, pp. 2224-2233.
View/Download from: Publisher's site
© 2014 Elsevier Ltd. All rights reserved. In the last few decades, the watermarking security issue has become one of the main challenges facing the design of watermarking techniques. In this paper, a secure oblivious watermarking system, based on Sparse Coding (SC) is proposed in order to tackle the three most critical watermarking security problems, i.e., unauthorized reading, false positive detection, and multiple claims of ownership problems, as well as optimize the fidelity, imperceptibility, and robustness characteristics. The reason for incorporating SC in the proposed system is to encode the watermark image before embedding it in the host image. This process is implemented using the well-known Stagewise Orthogonal Matching Pursuit (StOMP) method and an orthogonal dictionary that is derived from the host image itself. The watermark embedding is implemented in the transform domain of the Discrete Wavelet Transform (DWT) and Singular Value Decomposition (SVD) of the host image. The proposed system is oblivious, as it does not need the original host image when extracting the embedded watermark. In addition, it is suitable for both bi-level and gray-level watermarks, and can accommodate large watermarks that are up to half the size of the host image. The proposed SC-DWT-SVD based watermarking scheme is tested for various malicious and un-malicious attacks and the experimental results show that it realizes the security requirement as it tackles the false positive detection and multiple claims of ownership problems on one hand and generates an encryption form of the watermark on the other hand. In addition, the added security does not compromise the imperceptibility and robustness aspects of the proposed technique and hence can be considered to be comparable or superior to other up-to-date watermarking techniques.
Alzoubi, Y.I., Gill, A.Q. & Al-Ani, A. 2015, 'Distributed Agile Development Communication: An Agile Architecture Driven Framework', Journal of Software, vol. 10, no. 6, pp. 681-694.
View/Download from: UTS OPUS or Publisher's site
Agile methods depend on active communication and effective knowledge sharing among team members for producing high quality working software systems in short releases and iterations. However, effective communication in Distributed Agile Development (DAD) can be challenging due to a number of different factors, such as physical locations, multi-cultures and time-zones. The agile body of knowledge mainly discusses some technology and non-technology solutions and strategies to mitigate the DAD communication challenges from a project management perspective. Nevertheless, it has recently been argued that there is a need to understand and analyze DAD communication from other related but different perspectives, such as enterprise strategy, enterprise architecture and service management. Due to the fact that agile EA provides a holistic view and blueprint of the whole environment in which a number of projects are developed and managed, we attempt in this study to explore the effect of agile Enterprise Architecture (EA) on DAD communication. Particularly, we propose the development of an agile EA driven approach from the architecture body of knowledge for handling the DAD communication challenges that have not been thoroughly investigated before
Aljaafreh, A., Al-Ani, A., Aladaileh, R. & Aljaafreh, R. 2015, 'Initial trust in internet banking service in Jordan: Modeling and instrument validation', Journal of Theoretical and Applied Information Technology, vol. 74, no. 1, pp. 68-81.
View/Download from: UTS OPUS
© 2005 - 2015 JATIT & LLS. All rights reserved. As with many other e-services, the adoption rate of Internet banking services (IBS) in developing countries is relatively low compared to developed countries. It is well-established that customer's trust plays an important role in adopting new technologies, and hence, initial trust could be the first issue that needs to be investigated when studying the adoption of online banking. The aim of this study is to develop and validate a research instrument empirically, and then use it to examine a proposed conceptual model of initial trust for IBS in developing countries. The model's constructs are integrated from the trust literature, diffusion of innovation theory (DoI), and the Hofstede's culture theory. This paper also aims to develop and validate a research instrument to examine the research model. We conducted a pilot study in Jordan, one of the developing countries in the Middle East. A survey was carried out, and a total of 75 responses were gathered in the study. The collected data was analyzed using IBM SPSS 22.0. Results of the pilot study are used to validate the instrument and to refine the proposed model. The validated and refined instrument will be used to examine the model in the intended primary study.
AlJaafreh, A., Al-adaileh, R., Gill, A., Al-Ani, A. & Alzoubi, Y. 2014, 'A Review of Literature of Initial Trust in E-Services: The Case of Internet Banking Services in Jordanian Context', Journal of Electronic Banking Systems, vol. 2014, pp. 1-10.
View/Download from: UTS OPUS or Publisher's site
Al-Ani, A., Alsukker, A. & Khushaba, R.N. 2013, 'Feature subset selection using differential evolution and a wheel based search strategy', Swarm and Evolutionary Computation, vol. 9, no. 1, pp. 15-26.
View/Download from: UTS OPUS or Publisher's site
Differential evolution has started to attract a lot of attention as a powerful search method and has been successfully applied to a variety of applications including pattern recognition. One of the most important tasks in many pattern recognition systems is to find an informative subset of features that can effectively represent the underlying problem. Specifically, a large number of features can affect the system's classification accuracy and learning time. In order to overcome such problems, we propose a new feature selection method that utilizes differential evolution in a novel manner to identify relevant feature subsets. The proposed method aims to reduce the search space using a simple, yet powerful, procedure that involves distributing the features among a set of wheels. Two versions of the method are presented. In the first one, the desired feature subset size is predefined by the user, while in the second the user only needs to set an upper limit to the feature subset size. Experiments on a number of datasets with different sizes proved that the proposed method can achieve remarkably good results when compared with some of the well-known feature selection methods.
Al-Ani, A., Mesbah, M., van Dun, B. & Dillon, H. 2013, 'Fuzzy Logic-Based Automatic Alertness State Classification Using Multi-channel EEG Data', Lecture Notes in Computer Science, vol. 8226, no. 1, pp. 176-183.
View/Download from: UTS OPUS or Publisher's site
This paper represents an attempt to automatically classify alertness state using information extracted from multi-channel EEG. To reduce the amount of data and improve the performance, a channel selection method based on support vector machine (SVM) classifier has been performed. The features used for the EEG channel selection process and subsequently for alertness classification represent the energy values of the five EEG rhythms; namely d, ?, a, and ?. In order to identify the feature/channel combination that leads to the best alertness state classification performance, we used a fuzzy rule-based classification system (FRBCS) that utilizes differential evolution in constructing the rules. The results obtained using the FRBCS were found to be comparable to those of SVM but with the added advantage of revealing the rhythm/channel combination associated with each alertness state.
Al-Ani, A., Talaat, A.S., Atiya, A.F., Mokhtar, S.A. & Fayek, M. 2012, 'Multiclass Penalized Likelihood Pattern Classification Algorithm', Lecture Notes in Computer Science, vol. 7665, pp. 141-148.
View/Download from: UTS OPUS or Publisher's site
Penalized likelihood is a general approach whereby an objective function is defined, consisting of the log likelihood of the data minus some term penalizing non-smooth solutions. Subsequently, this objective function is maximized, yielding a solution that achieves some sort of trade-off between the faithfulness and the smoothness of the fit. In this paper we extend the penalized likelihood classification that we proposed in earlier work to the multi class case. The algorithms are based on using a penalty term based on the K-nearest neighbors and the likelihood of the training patterns classifications. The algorithms are simple to implement, and result in a performance competitive with leading classifiers.
Gargiulo, G., Shephard, R., Tapson, J., Mcewan, A., Bifulco, P., Cesarelli, M., Jin, C., Al-Ani, A., Wang, N. & Van Schaik, A. 2012, 'Pregnancy Detection And Monitoring In Cattle Via Combined Foetus Electrocardiogram And Phonocardiogram Signal Processing', BMC Veterinary Research, vol. 8, no. NA, pp. 1-10.
View/Download from: UTS OPUS or Publisher's site
Background: Pregnancy testing in cattle is commonly invasive requiring manual rectal palpation of the reproductive tract that presents risks to the operator and pregnancy. Alternative non-invasive tests have been developed but have not gained popularity
Al-Ani, A., Rabie, A., van Dun, B. & Dillon, H. 2012, 'Analysis of Alertness Status of Subjects Undergoing the Cortical Auditory Evoked Potential Hearing Test', Lecture Notes in Computer Science, vol. 7663, pp. 92-99.
View/Download from: UTS OPUS or Publisher's site
In this paper, we analyze the EEG rhythms of subjects undergoing the cortical auditory evoked potential (CAEP) hearing test. Investigation of the importance of the different EEG rhythms in terms of their capability in differentiating between the different alertness states when considering 64 channel EEG montage is conducted. This is followed by considering subsets that contain 2, 3, 4 as well as all 5 EEG rhythms. Finally, a feature subset selection method based on differential evolution (DE) that has particularly been proposed to deal with multi-channel signals is used to search for the best subset of EEG rhythms for the various channels.
Ali, M.M., Al-Ani, A., Eamus, D. & Tan, D.K. 2012, 'A New Image-Processing-Based Technique for Measuring Leaf Dimensions', American-Eurasian J. Agric. & Environ. Sci., vol. 12, no. 12, pp. 1588-1594.
View/Download from: UTS OPUS
We propose in this paper a new method for measuring a number of leaf dimension parameters including height, width, average width, perimeter and area. A digital scanner is utilized to acquire leaf images, which unlike digital cameras, requires no calibration in terms of size and angle of the acquired images. Edge detection, filtering and thresholding algorithms are applied to identify the leaf section of the image against the background. Forty leaves that differ in shape and size were used to validate the estimated parameters against the true values and parameters produced by the popular Li-Cor 3100. Data indicated that the proposed method achieved a constantly high accuracy
Ali, M.M., Al-Ani, A., Eamus, D. & Tan, D.K. 2012, 'A New Image Processing Based Technique to Determine Chlorophyll in Plants', American-Eurasian J. Agric. & Environ. Sci., vol. 12, no. 10, pp. 1323-1328.
View/Download from: UTS OPUS
Leaf colour is usually used as a guide for assessments of nutrient status and plant health. We propose a new inexpensive, hand-held and easy-to-use technique for the detection of chlorophyll content and foliar nitrogen content in plants based on leaf colour. This method provides a rapid analysis and data storage at minimal cost and does not require any technical or laboratory skills. Most of the existing methods that examined relationships between chlorophyll status and leaf colour were developed for particular species. These methods acquire leaf images using digital cameras, which can be sensitive to lighting conditions (colour, angle, flux density) and hence, require proper calibration. Our method analyses leaf colour images obtained from a digital scanner that requires minimal calibration compared as it has its one light source and the angle and distance between light and leaf are constant. Our new algorithm produced superior correlations with the true value of foliar chlorophyll content measured in the laboratory compared with existing non-destructive methods when applied to three different species (lettuce, broccoli and tomato).
Khushaba, R.N., Al-Ani, A. & Al-Jumaily, A. 2011, 'Feature subset selection using differential evolution and a statistical repair mechanism', Expert Systems with Applications, vol. 38, no. 9, pp. 11515-11526.
View/Download from: UTS OPUS or Publisher's site
One of the fundamental motivations for feature selection is to overcome the curse of dimensionality problem. This paper presents a novel feature selection method utilizing a combination of differential evolution (DE) optimization method and a proposed repair mechanism based on feature distribution measures. The new method, abbreviated as DEFS, utilizes the DE float number optimizer in the combinatorial optimization problem of feature selection. In order to make the solutions generated by the float-optimizer suitable for feature selection, a roulette wheel structure is constructed and supplied with the probabilities of features distribution. These probabilities are constructed during iterations by identifying the features that contribute to the most promising solutions. The proposed DEFS is used to search for optimal subsets of features in datasets with varying dimensionality. It is then utilized to aid in the selection of Wavelet Packet Transform (WPT) best basis for classification problems, thus acting as a part of a feature extraction process. Practical results indicate the significance of the proposed method in comparison with other feature selection methods.
Khushaba, R.N., Al-Ani, A. & Al-Jumaily, A. 2011, 'Swarmed Discriminant Analysis for Multifunction Prosthesis Control', International Journal of Engineering and Natural Sciences, vol. 5, no. 1, pp. 27-34.
View/Download from: UTS OPUS
One of the approaches enabling people with amputated limbs to establish some sort of interface with the real world includes the utilization of the myoelectric signal (MES) from the remaining muscles of those limbs. The MES can be used as a control input to a multifunction prosthetic device. In this control scheme, known as the myoelectric control, a pattern recognition approach is usually utilized to discriminate between the MES signals that belong to different classes of the forearm movements. Since the MES is recorded using multiple channels, the feature vector size can become very large. In order to reduce the computational cost and enhance the generalization capability of the classifier, a dimensionality reduction method is needed to identify an informative yet moderate size feature set. This paper proposes a new fuzzy version of the well known Fisher's Linear Discriminant Analysis (LDA) feature projection technique. Furthermore, based on the fact that certain muscles might contribute more to the discrimination process, a novel feature weighting scheme is also presented by employing Particle Swarm Optimization (PSO) for estimating the weight of each feature. The new method, called PSOFLDA, is tested on real MES datasets and compared with other techniques to prove its superiority.
Khushaba, R.N., Al-Ani, A. & Al-Jumaily, A. 2011, 'Swarmed discriminant analysis for multifunction prosthesis control', World Academy of Science, Engineering and Technology, vol. 51, pp. 1088-1095.
One of the approaches enabling people with amputated limbs to establish some sort of interface with the real world includes the utilization of the myoelectric signal (MES) from the remaining muscles of those limbs. The MES can be used as a control input to a multifunction prosthetic device. In this control scheme, known as the myoelectric control, a pattern recognition approach is usually utilized to discriminate between the MES signals that belong to different classes of the forearm movements. Since the MES is recorded using multiple channels, the feature vector size can become very large. In order to reduce the computational cost and enhance the generalization capability of the classifier, a dimensionality reduction method is needed to identify an informative yet moderate size feature set. This paper proposes a new fuzzy version of the well known Fisher's Linear Discriminant Analysis (LDA) feature projection technique. Furthermore, based on the fact that certain muscles might contribute more to the discrimination process, a novel feature weighting scheme is also presented by employing Particle Swarm Optimization (PSO) for estimating the weight of each feature. The new method, called PSOFLDA, is tested on real MES datasets and compared with other techniques to prove its superiority.
Khushaba, R.N., Al-Ani, A. & Al-Jumaily, A. 2010, 'Orthogonal Fuzzy Neighborhood Discriminant Analysis for Multifunction Myoelectric Hand Control', IEEE Transactions On Biomedical Engineering, vol. 57, no. 6, pp. 1410-1419.
View/Download from: UTS OPUS or Publisher's site
Developing accurate and powerful electromyogram (EMG) driven prostheses controllers that can provide the amputees with effective control on their artificial limbs, has been the focus of a great deal of research in the past few years. One of the major challenges in such research is extracting an informative subset of features that can best discriminate between the different forearm movements. In this paper, a new dimensionality reduction method, referred to as orthogonal fuzzy neighborhood discriminant analysis (OFNDA), is proposed as a response to such a challenge. Unlike existing attempts in fuzzy linear discriminant analysis, the objective of the proposed OFNDA is to minimize the distance between samples that belong to the same class and maximize the distance between the centers of different classes, while taking into account the contribution of the samples to the different classes. The proposed OFNDA is validated on EMG datasets collected from seven subjects performing a range of 5 to 10 classes of forearm movements. Practical results indicate the significance of OFNDA in comparison to many other feature projection methods (including locality preserving and uncorrelated variants of discriminant analysis) with accuracies ranging from 97.66% to 87.84% for 5 to 10 classes of movements, respectively, using only two EMG electrodes.
Khushaba, R.N., Al-Jumaily, A. & Al-Ani, A. 2009, 'Evolutionary Fuzzy Discriminant Analysis Feature Projection Technique in Myoelectric Control', Pattern Recognition Letters, vol. 30, no. 7, pp. 699-707.
View/Download from: UTS OPUS or Publisher's site
The controller of a multifunction prosthetic hand usually employs a pattern recognition scheme to discriminate between the myoelectric signals (MES) from different classes of the forearm movements. The MES is recorded using a multichannel approach that makes the feature vector size very large. Hence a dimensionality reduction technique is needed to identify an informative moderate size feature set. This paper proposes a novel feature projection technique based on a combination of fisher linear discriminant analysis (LDA), fuzzy logic (FL), and differential evolution (DE) optimization technique. The new technique, DEFLDA, assigns different membership degrees to the data points in order to reduce the effect of overlapping points in the discrimination process. Furthermore, an optimized weighting scheme is presented in which certain weights are assigned to the features according to their contribution in the discrimination process. The proposed DEFLDA is tested on different datasets and compared with other projection techniques to prove its functionality.
Khushaba, R.N., Alsukker, A.S., Al-Ani, A., Al-Jumaily, A. & Zomaya, A.Y. 2009, 'A Novel Swarm-Based Feature Selection Algorithm in Multifunction Myoelectric Control', Journal of Intelligent & Fuzzy Systems, vol. 20, no. 4/5, pp. 175-185.
View/Download from: UTS OPUS or Publisher's site
Accurate and computationally efficient myoelectric control strategies have been the focus of a great deal of research in recent years. Although many attempts exist in literature to develop such strategies, deficiencies still exist. One of the major challenges in myoelectric control is finding an optimal feature set that can best discriminate between classes. However, since the myoelectric signal is recorded using multi channels, the feature vector size can become very large. Hence a dimensionality reduction method is needed to identify an informative, yet small size feature set. This paper presents a new feature selection method based on modifying the Particle Swarm Optimization (PSO) algorithm with the inclusion of Mutual Information (MI) measure. The new method, called BPSOMI, is a mixture of filter and wrapper approaches of feature selection. In order to prove its efficiency, the proposed method is tested against other dimensionality reduction techniques proving powerful classification accuracy.
Atiya, A. & Al-Ani, A. 2009, 'A penalized likelihood based pattern classification algorithm', pattern recognition, vol. 42, no. 11, pp. 2684-2694.
View/Download from: UTS OPUS or Publisher's site
Penalized likelihood is a general approach whereby an objective function is defined, consisting of the log likelihood of the data minus some term penalizing non-smooth solutions. Subsequently, this objective function is maximized, yielding a solution that achieves some sort of trade-off between the faithfulness and the smoothness of the fit. Most work on that topic focused on the regression problem, and there has been little work on the classification problem. In this paper we propose a new classification method using the concept of penalized likelihood (for the two class case). By proposing a novel penalty term based on the K-nearest neighbors, simple analytical derivations have led to an algorithm that is proved to converge to the global optimum. Moreover, this algorithm is very simple to implement and converges typically in two or three iterations. We also introduced two variants of the method by distance-weighting the K-nearest neighbor contributions, and by tackling the unbalanced class patterns situation. We performed extensive experiments to compare the proposed method to several well-known classification methods. These simulations reveal that the proposed method achieves one of the top ranks in classification performance and with a fairly small computation time.
Al-Ani, A. 2009, 'A dependency-based search strategy for feature selection', Expert Systems with Applications, vol. 36, no. 10, pp. 12392-12398.
View/Download from: UTS OPUS or Publisher's site
Feature selection has become an increasingly important field of research. It aims at finding optimal feature subsets that can achieve better generalization on unseen data. However, this can be a very challenging task, especially when dealing with large feature sets. Hence, a search strategy is needed to explore a relatively small portion of the search space in order to find "semi-optimal" subsets. Many search strategies have been proposed in the literature, however most of them do not take into consideration relationships between features. Due to the fact that features usually have different degrees of dependency among each other, we propose in this paper a new search strategy that utilizes dependency between feature pairs to guide the search in the feature space. When compared to other well-known search strategies, the proposed method prevailed.
Khushaba, R.N., Al-Jumaily, A. & Al-Ani, A. 2009, 'Dimensionality Reduction with Neuro-Fuzzy Discriminant Analysis', International Journal of Computational Intelligence, vol. 5, no. 3, pp. 225-232.
View/Download from: UTS OPUS or Publisher's site
One of the most important tasks in any pattern recognition system is to find an informative, yet small, subset of features with enhanced discriminatory power. In this paper, a new neuro-fuzzy discriminant analysis based feature projection technique is presented based on a two stages hybrid of Neural Networks, optimized with Differential Evolution (DE), and a proposed Fuzzy Linear Discriminant Analysis (FLDA) technique. Although dimensionality reduction via FLDA can present a set of well clustered features in the reduced space, but like any version of the existing DAs it assumes that the original data set is linearly separable, which is not the case with many real world problems. In order to overcome this problem, the first stage of the proposed technique maps the initially extracted features in a nonlinear manner into a new domain, with larger dimensionality, in which the features are linearly separable. FLDA acts then on these linearly separable features to further reduce the dimensionality. The proposed combination, referred to as NFDA, is validated on a prosthetic device control problem with Electroencephalogram (EEG) datasets collected from 5 subjects achieving a maximum testing accuracy of 85.7% for a three classes of EEG based imaginations of movements.
Al-Ani, A. & Al-Sukker, A. 2006, 'Effect of feature and channel selection on EEG classification.', Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, pp. 2171-2174.
In this paper, we evaluate the significance of feature and channel selection on EEG classification. The selection process is performed by searching the feature/channel space using genetic algorithm, and evaluating the importance of subsets using a linear support vector machine classifier. Three approaches have been considered: (i) selecting a subset of features that will be used to represent a specified set of channels, (ii) selecting channels that are each represented by a specified set of features, and (iii) selecting individual features from different channels. When applied to a brain-computer interface (BCI) problem, results indicate that improvement in classification accuracy can be achieved by considering the correct combination of channels and features.
Al-Ani, A. 2005, 'Feature Subset Selection Using Ant Colony Optimization', International Journal of Computational Intelligence, vol. 2, no. 1, pp. 53-58.
View/Download from: UTS OPUS
Al-Ani, A. & Deriche, M. 2004, 'Multi-Channel Subspace Mapping Using an Information Maximization Criterion', Multidimensional Systems and Signal Processing, vol. 15, no. 2, pp. 117-145.
View/Download from: UTS OPUS or Publisher's site
A new hybrid information maximization (HIM) algorithm is derived. This algorithm is able to perform subspace mapping of multi-channel signals, where the input (feature) vector for each of the channels is linearly transformed to an output vector. The algorithm is based on maximizing the mutual information (MI) between input and output sets for each of the channels, and between output sets across channels. Such formulation leads to a substantial redundancy reduction in the output sets, and the extraction of higher order features that exhibit coherence across time and/or space. In this paper, we develop the proposed algorithm and show that it combines efficiently the strengths of two well-known subspace mapping techniques, namely the principal component analysis (PCA) and the canonical correlation analysis (CCA). Unlike CCA, which is limited to two channels, the HIM algorithm can easily be extended to multiple channels. A number of simulations and real experiments are conducted to compare the performance of HIM to that of PCA and CCA.
Al-Ani, A., Deriche, M. & Chebil, J. 2003, 'A new mutual information based measure for feature selection', Intelligent Data Analysis, vol. 7, no. 1, pp. 43-57.
View/Download from: UTS OPUS
In this paper, we discuss the problem of feature selection and the importance of using mutual information in evaluating the discrimination ability of feature subsets between class labels. Because of the difficulties associated with estimating the exact value of mutual information, we propose a new evaluation measure that is based on the information gain and takes into consideration the interaction between features. The proposed measure is integrated into a robust feature selection scheme and compared with the well-known mutual information feature selection (MIFS) algorithm using the problems of texture classification, speech segment classification and speaker identification.
Al-Ani, A. & Deriche, M. 2002, 'A new technique for combining multiple classifiers using the Dempster-Shafer theory of evidence', Journal of Artificial Intelligence Research, vol. 17, pp. 333-361.
This paper presents a new classifier combination technique based on the Dempster-Shafer theory of evidence. The Dempster-Shafer theory of evidence is a powerful method for combining measures of evidence from different classifiers. However, since each of the available methods that estimates the evidence of classifiers has its own limitations, we propose here a new implementation which adapts to training data so that the overall mean square error is minimized. The proposed technique is shown to outperform most available classifier combination methods when tested on three different classification problems.
Al-Ani, A. & Deriche, M. 2000, 'Optimal feature selection using information maximization: Case of biomedical data', Neural Networks for Signal Processing - Proceedings of the IEEE Workshop, vol. 2, pp. 841-850.
The hybrid information maximization (HIM) algorithm is derived. This algorithm is based on maximizing the mutual information (MI) between the input and output of a network using the infomax principle, and between outputs of different network modules using the Imax algorithm. These two folds enable reducing the redundancy in output units in addition to selecting higher order features from input units. In this paper, we analyze the proposed algorithm and generalize the learning procedure of the Imax algorithm. We show that the proposed HIM algorithm provides a better representation of input compared to the original two algorithms when used separately. An example showing the power of the HIM algorithm in the analysis of EEG data is discussed.