Sh Hussain Salleh

Electroencephalographic motor imagery brain connectivity analysis for bci: A review

Recent research has reached a consensus on the feasibility of motor imagery brain-computer interface (MI-BCI) for different applications, especially in stroke rehabilitation. Most MI-BCI systems rely on temporal, spectral, and spatial features of single channels to distinguish different MI patterns. However, no successful communication has been established for a completely locked-in subject. To provide more useful and informative features, it has been recommended to take into account the relationships among electroencephalographic (EEG) sensor/source signals in the form of brain connectivity as an efficient tool of neuroscience. In this review, we briefly report the challenges and limitations of conventional MI-BCIs. Brain connectivity analysis, particularly functional and effective, has been described as one of the most promising approaches for improving MI-BCI performance. An extensive literature on EEG-based MI brain connectivity analysis of healthy subjects is reviewed. We subsequently discuss the brain connectomes during left and right hand, feet, and tongue MI movements. Moreover, key components involved in brain connectivity analysis that considerably affect the results are explained. Finally, possible technical shortcomings that may have influenced the results in previous research are addressed and suggestions are provided.

EMG-based facial gesture recognition through versatile elliptic basis function neural network

BackgroundRecently, the recognition of different facial gestures using facial neuromuscular activities has been proposed for human machine interfacing applications. Facial electromyograms (EMGs) analysis is a complicated field in biomedical signal processing where accuracy and low computational cost are significant concerns. In this paper, a very fast versatile elliptic basis function neural network (VEBFNN) was proposed to classify different facial gestures. The effectiveness of different facial EMG time-domain features was also explored to introduce the most discriminating.MethodsIn this study, EMGs of ten facial gestures were recorded from ten subjects using three pairs of surface electrodes in a bi-polar configuration. The signals were filtered and segmented into distinct portions prior to feature extraction. Ten different time-domain features, namely, Integrated EMG, Mean Absolute Value, Mean Absolute Value Slope, Maximum Peak Value, Root Mean Square, Simple Square Integral, Variance, Mean Value, Wave Length, and Sign Slope Changes were extracted from the EMGs. The statistical relationships between these features were investigated by Mutual Information measure. Then, the feature combinations including two to ten single features were formed based on the feature rankings appointed by Minimum-Redundancy-Maximum-Relevance (MRMR) and Recognition Accuracy (RA) criteria. In the last step, VEBFNN was employed to classify the facial gestures. The effectiveness of single features as well as the feature sets on the system performance was examined by considering the two major metrics, recognition accuracy and training time. Finally, the proposed classifier was assessed and compared with conventional methods support vector machines and multilayer perceptron neural network.ResultsThe average classification results showed that the best performance for recognizing facial gestures among all single/multi-features was achieved by Maximum Peak Value with 87.1% accuracy. Moreover, the results proved a very fast procedure since the training time during classification via VEBFNN was 0.105 seconds. It was also indicated that MRMR was not a proper criterion to be used for making more effective feature sets in comparison with RA.ConclusionsThis work was accomplished by introducing the most discriminating facial EMG time-domain feature for the recognition of different facial gestures; and suggesting VEBFNN as a promising method in EMG-based facial gesture classification to be used for designing interfaces in human machine interaction systems.

Heart Sound Analysis Using MFCC and Time Frequency Distribution

This paper presents heart sound analysis method based on Time-Frequency Distribution (TFD) analysis and Mel Frequency Cepstrum Coefficient (MFCC). TFD represents the heart sound in term of time and frequency simultaneously which while the MFCC defines a signal in term of frequency coefficient corresponding to the Mel filter scale. There are 100 normal data and 100 data with disease obtained from the hospital which consists of various kinds of problems including mitral regurgitation and stenosis, tricuspid regurgitation and stenosis, ventricular septal defect and other structural related disease. B-Distribution is chosen from a number of time-frequency analysis methods due its capability to represent the signal in the most efficient way in term of noise and cross term reduction. The advantage of MFCC is that it is good in error reduction and able to produce a robust feature when the signal is affected by noise. SVD/PCA technique is used to extract the important features out of the B-Distribution representation. The coefficient obtained from SVD-PCA and MFCC is later used for classification Artificial Neural Network. The results show that the system is able to produce the accuracy up to 90.0% using the TFD and 80.0% using the MFCC.

A Unified Estimation Framework for State-Related Changes in Effective Brain Connectivity

Objective: This paper addresses the critical problem of estimating time-evolving effective brain connectivity. Current approaches based on sliding window analysis or time-varying coefficient models do not simultaneously capture both slow and abrupt changes in causal interactions between different brain regions. Methods: To overcome these limitations, we develop a unified framework based on a switching vector autoregressive (SVAR) model. Here, the dynamic connectivity regimes are uniquely characterized by distinct vector autoregressive (VAR) processes and allowed to switch between quasi-stationary brain states. The state evolution and the associated directed dependencies are defined by a Markov process and the SVAR parameters. We develop a three-stage estimation algorithm for the SVAR model: 1) feature extraction using time-varying VAR (TV-VAR) coefficients, 2) preliminary regime identification via clustering of the TV-VAR coefficients, 3) refined regime segmentation by Kalman smoothing and parameter estimation via expectation-maximization algorithm under a state-space formulation, using initial estimates from the previous two stages. Results: The proposed framework is adaptive to state-related changes and gives reliable estimates of effective connectivity. Simulation results show that our method provides accurate regime change-point detection and connectivity estimates. In real applications to brain signals, the approach was able to capture directed connectivity state changes in functional magnetic resonance imaging data linked with changes in stimulus conditions, and in epileptic electroencephalograms, differentiating ictal from nonictal periods. Conclusion: The proposed framework accurately identifies state-dependent changes in brain network and provides estimates of connectivity strength and directionality. Significance: The proposed approach is useful in neuroscience studies that investigate the dynamics of underlying brain states.

Design and development of speech-control robotic manipulator arm

This paper presents a speech-control robotic manipulator arm via personal computer and self-built robotic arm. It describes the software we developed to collect, process and train the speech database. First, the specifications of the robotic arm will be explained. The algorithms involved will also be briefly discussed. Finally, the result will show the ability of this system to control robotic manipulator arm with humans voice.

ESTIMATING DYNAMIC CORTICAL CONNECTIVITY FROM MOTOR IMAGERY EEG USING KALMAN SMOOTHER & EM ALGORITHM

This paper considers identifying effective cortical connectivity from scalp EEG. Recent studies use time-varying multivariate autoregressive (TV-MAR) models to better describe the changing connectivity between cortical regions where the TV coefficients are estimated by Kalman filter (KF) within a state-space framework. We extend this approach by incorporating Kalman smoothing (KS) to improve the KF estimates, and the expectation-maximization (EM) algorithm to infer the unknown model parameters from EEG. We also consider solving the volume conduction problem by modeling the induced instantaneous correlations using a full noise covariate. Simulation results show the superiority of KS in tracking the coefficient changes. We apply two derived frequency domain measures i.e. TV partial directed coherence (TV-PDC) and TV directed transfer function (TV-DTF), to investigate dynamic causal interactions between motor areas in discriminating motor imagery (MI) of left and right hand. Event-related changes of information flows around beta-band, in a unidirectional way between left and right hemispheres are observed during MI. A difference in inter-hemispheric connectivity patterns is found between left and right-hand movements, implying potential usage for BCI.

Comparison of Multilayer Perceptron and Radial Basis Function Neural Networks for EMG-Based Facial Gesture Recognition

This paper compared the application of multilayer perceptron (MLP) and radial basis function (RBF) neural networks on a facial gesture recognition system. Electromyogram (EMG) signals generated by ten different facial gestures were recorded through three pairs of electrodes. EMGs were filtered and segmented into non-overlapped portions. The time-domain feature mean absolute value (MAV) and its two modified derivatives MMAV1 and MMAV2 were extracted. MLP and RBF were used to classify the EMG features while six types of activation functions were evaluated for MLP architecture. The discriminating power of single/multi features was also investigated. The results of this study showed that symmetric saturating linear was the most effective activation function for MLP; the feature set MAV + MMAV1 provided the highest accuracy by both classifiers; MLP reached higher recognition ratio for most of features; RBF was the faster algorithm which also offered a reliable trade-off between the two key metrics, accuracy and time.

Performance metrics for active contour models in image segmentation

Image segmentation is one of the significant techniques in image processing to distinguish desired parts from its background for further analysis. It provides visual means for inspection of anatomical structure of human body, identification of disease, tracking of its development and input for surgical planning and simulation. Active contour models are regarded as promising and vigorously research model-based approach to computer assisted medical image analysis. However, it is not trivial to assess whether one segmentation algorithm performs more superior than the other. Therefore, a systematic assessment tool is designed and implemented to examine all the important aspects of active contour models. Meanwhile, a novel supervised evaluator including analytical method and empirical methods are proposed to acts as objective evaluator. The obtained results highlighted both the strengths and limitations of the studied active contour models. A proper area usage of each active contour model is also suggested at the end of this paper.

PCA, LDA and neural network for face identification

Algorithms based on Principal Component Analysis (PCA) and subspace Linear Discriminant Analysis (LDA) are popular in face recognition. PCA is used to perform dimension reduction on human face data and LDA creates another subspace to improve discriminant of PCA features. In this paper, we propose Artificial Neural Networks (ANN) as an alternative to replace Euclidean distances in classification of human face features extracted by PCA and LDA. ANN is well recognized by its robustness and good learning ability. The algorithms were evaluated using the Database of Faces which comprises 40 subjects and with a total size of 400 images. Experimental results show that ANN reasonably improves the performance of PCA and LDA method. LDA-NN achieves an average recognition accuracy of 95.8%.

Pre-processing of input features using LPC and warping process

This paper presents pre-processing of input features to artificial neural network (NN). This is for preparation of reliable reference templates for the set of words to be recognized. The first task is to extract pitch features using Pitch Scale Harmonic Filter (PSHF) algorithm. Another task is to align the input frames (test set) to the reference template (training set) using a modified DTW algorithm called DTW fixing frame (DTW-FF) algorithm. This proper time normalization is needed since NN is designed to compare data of the same length; same speech can varies in their duration. By performing frame fixing or time normalization, the test set and the training set is adjusted to a fix number of frames throughout the sets utilizing the local distance score of the matched features. Then those features can be adapted to NN for further recognition tuning.