Kai Keng Ang | Institute for Infocomm Research (original) (raw)

Papers by Kai Keng Ang

2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2021

Journal of Neural Engineering, 2019

Objective. This paper proposes an iterative negative-unlabeled (NU) learning algorithm for cross-... more Objective. This paper proposes an iterative negative-unlabeled (NU) learning algorithm for cross-subject detection of passive fatigue from labelled alert (negative) and unlabeled driving EEG data. Approach. Unlike other studies which used manual labeling of the fatigue state, the proposed algorithm (PA) first iteratively uses 29 subjects' alert data and unlabeled driving data to identify the most fatigued block of EEG data in each subject in a cross-subject manner. Subsequently, the PA computes subjects' driving fatigue score. Repeated measures correlations of the score to EEG band powers are then performed. Main results. The PA yields an averaged accuracy of 93.77% ± 8.15% across subjects in detecting fatigue, which is significantly better than the various baselines. The fatigue scores obtained are also significantly positively correlated with theta band power and negatively correlated with beta band power that are known to respectively increase and decrease in presence of passive fatigue. There is a strong negative correlation with alpha band power as well. Significance. The proposed iterative NU learning algorithm is capable of labelling and quantifying the most fatigued block in a cross-subject manner despite the lack of ground truth in the fatigue levels of unlabeled driving EEG data. Together with the significant correlations with theta, alpha and beta band power, the results show promise in the application of the proposed algorithm to detect fatigue from EEG.

Applied Soft Computing, 2016

2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2014

2011 9th IEEE International Conference on Control and Automation (ICCA), 2011

The brain signals are generally measured by Electroencephalogram (EEG) in Brain-Computer Interfac... more The brain signals are generally measured by Electroencephalogram (EEG) in Brain-Computer Interface (BCI) applications. In motor imagery-based BCI, the performed MI tasks (e.g., imagined hand movement) are identified through a classification algorithm to communicate and control the device. Consequently, improving the performance of the classifier is crucial to the success of the BCI system. One of the most popular linear

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2014

This paper presents an asynchronously intracortical brain-computer interface (BCI) which allows t... more This paper presents an asynchronously intracortical brain-computer interface (BCI) which allows the subject to continuously drive a mobile robot. This system has a great implication for disabled patients to move around. By carefully designing a multiclass support vector machine (SVM), the subject&amp;amp;amp;amp;amp;amp;amp;amp;amp;#39;s self-paced instantaneous movement intents are continuously decoded to control the mobile robot. In particular, we studied the stability of the neural representation of the movement directions. Experimental results on the nonhuman primate showed that the overt movement directions were stably represented in ensemble of recorded units, and our SVM classifier could successfully decode such movements continuously along the desired movement path. However, the neural representation of the stop state for the self-paced control was not stably represented and could drift.

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019

Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on

The performance of Brain-Computer Interface (BCI) applications are sometimes hindered by non-stat... more The performance of Brain-Computer Interface (BCI) applications are sometimes hindered by non-stationarity in the EEG data from sessions on different days. This paper proposes an algorithm for adaptive training of a SVM classifier to address the non-stationarity in EEG by adapting the kernel to data from subsequent sessions. The kernel width parameter of the kernel function of the SVM classifier is adapted using an information theoretic cost function based on minimum error entropy (MEE). An experiment is performed using the proposed method on EEG data collected without feedback from 12 healthy subjects in two sessions on separate days. The results using the proposed method yielded a mean accuracy of 75%, which is significantly better compared to the baseline result of 67% without kernel adaptation (P=0.00029).

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2014

To address the nonstationarity issue in EEG-based brain computer interface (BCI), the computation... more To address the nonstationarity issue in EEG-based brain computer interface (BCI), the computational model trained using the training data needs to adapt to the data from the test sessions. In this paper, we propose a novel adaptation approach based on the divergence framework. Cross-session changes can be taken into consideration by searching the discriminative subspaces for test data on the manifold of orthogonal matrices in a semi-supervised manner. Subsequently, the feature space becomes more consistent across sessions and classifiers performance can be enhanced. Experimental results show that the proposed adaptation method yields improvements in classification performance.

2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2013

Recent studies have demonstrated that hand movement directions can be decoded from low-frequency ... more Recent studies have demonstrated that hand movement directions can be decoded from low-frequency electroencephalographic (EEG) signals. This paper proposes a novel framework that can optimally select dyadic filter bank common spatial pattern (CSP) features in low-frequency band (0-8 Hz) for multi-class classification of four orthogonal hand movement directions. The proposed framework encompasses EEG signal enhancement, dyadic filter bank CSP feature extraction, fuzzy mutual information (FMI)-based feature selection, and one-versus-rest Fisher&amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;#39;s linear discriminant analysis. Experimental results on data collected from seven human subjects show that (1) signal enhancement can boost accuracy by at least 4%; (2) low-frequency band (0-8 Hz) can adequately and effectively discriminate hand movement directions; and (3) dyadic filter bank CSP feature extraction and FMI-based feature selection are indispensable for analyzing hand movement directions, increasing accuracy by 6.06%, from 60.02% to 66.08%.

2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013

ABSTRACT This paper proposes a novel method to detect motor imagery of walking for the rehabilita... more ABSTRACT This paper proposes a novel method to detect motor imagery of walking for the rehabilitation of stroke patients using the Laplacian derivatives (LAD) of power averaged across frequency bands as the feature. We propose to select the most correlated channels by jointly considering the mutual information between the LAD power features of the channels and the class labels, and the redundancy between the LAD power features of the channel with that of the selected channels. Experiments are conducted on the EEG data collected for 11 healthy subjects using proposed method and compared with existing methods. The results show that the proposed method yielded an average classification accuracy of 67.19% by selecting as few as 4 LAD channels. An improved result of 71.45% and 73.23% are achieved by selecting 10 and 22 LAD channels, respectively. Comparison results revealed significantly superior performance of our proposed method compared to that obtained using common spatial pattern and filter bank with power features. Most importantly, our proposed method achieves significant better accuracy for poor BCI performers compared to existing methods. Thus, the results demonstrated the potential of using the proposed method for detecting motor imagery of walking for the rehabilitation of stroke patients.

The 2011 International Joint Conference on Neural Networks, 2011

ABSTRACT In this paper, a Brain-Computer Interface (BCI) for classifying EEG correlates of chroni... more ABSTRACT In this paper, a Brain-Computer Interface (BCI) for classifying EEG correlates of chronic mental stress is proposed. Data from 8 EEG channels are collected from 26 healthy right-handed students during university examination period and after the examination whereby the former is considered to be relatively more stressful to students than the latter. The mental stress level are measured using the Perceived Stress Scale 14 (PSS-14) and categorized into stressed and stress-free groups. The proposed BCI is then used to classify the subjects' mental stress level on EEG features extracted using the Higuchi's fractal dimension of EEG, Gaussian mixtures of EEG spectrogram, and Magnitude Square Coherence Estimation (MSCE) between the EEG channels. Classification on the EEG features are then performed using the K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM). The performance of the proposed BCI is then evaluated from the inter-subject classification accuracy using leave-one- out validation. The results showed that the proposed BCI using features extracted by MSCE yielded a promising inter-subject validation accuracy of over 90% in classifying the EEG correlates of chronic mental stress.

2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013

ABSTRACT Decoding movement targets from neural activity in motor cortex using invasive brain-comp... more ABSTRACT Decoding movement targets from neural activity in motor cortex using invasive brain-computer interface (BCI) has potential application to help disabled patients. Most works employed spike sorting to obtain the single units (SUs) for decoding from the extracellular electrode recordings. However, spike sorting is difficult, computational demanding, and is often limited by the spike waveform variability especially in low SNR and high neuronal density conditions. To address these issues, we proposed a decoding method using unsorted spike trains from recording electrodes based on the maximal likelihood (ML) estimation approach. An experiment was performed to test neuronal data recorded from a rhesus monkey performing the center-out movement task of eight targets. The results showed that the proposed method yielded average correct decoding rate of 98.5% compared to the SU based method that yielded correct decoding rate of 96.3%. The results also showed that the proposed method yielded improved computational efficiency. Thus the proposed method showed potential for real time BCI applications with large scale of neuronal recordings.

Applied Sciences

Deep learning has achieved remarkable progress, particularly in neuroimaging analysis. Deep learn... more Deep learning has achieved remarkable progress, particularly in neuroimaging analysis. Deep learning applications have also been extended from adult to pediatric medical images, and thus, this paper aims to present a systematic review of this recent research. We first introduce the commonly used deep learning methods and architectures in neuroimaging, such as convolutional neural networks, auto-encoders, and generative adversarial networks. A non-exhaustive list of commonly used publicly available pediatric neuroimaging datasets and repositories are included, followed by a categorical review of recent works in pediatric MRI-based deep learning studies in the past five years. These works are categorized into recognizing neurodevelopmental disorders, identifying brain and tissue structures, estimating brain age/maturity, predicting neurodevelopment outcomes, and optimizing MRI brain imaging and analysis. Finally, we also discuss the recent achievements and challenges on these applicat...

The 2010 International Joint Conference on Neural Networks (IJCNN)

The design of multiclass BCI is a very challenging task because of the need to extract complex sp... more The design of multiclass BCI is a very challenging task because of the need to extract complex spatial and temporal patterns from noisy multidimensional time series generated from EEG measurements. This paper proposes a Multiclass Common Spatial Pattern (MCSP) based on Joint Approximate Diagonalization (JAD) for multiclass BCIs. The proposed method based on fast Frobenius diagonalization (FFDIAG) is compared with

2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2018

Local field potentials (LFPs) have been proposed as a neural decoding signal to compensate for sp... more Local field potentials (LFPs) have been proposed as a neural decoding signal to compensate for spike signal deterioration in invasive brain-machine interface applications. However, the presence of redundancy among LFP signals at different frequency bands across multiple channels may affect the decoding performance. In order to remove redundant LFP channels, we proposed a novel Fisher-distance ratio-based method to actively batch select discriminative channels to maximize the separation between classes. Experimental evaluation was conducted on 5 non-consecutive days of data from a non-human primate. For data from each day, the first experimental session was used to generate the training model, which was then used to perform 4-class decoding of signals from other sessions. Decoding achieved an average accuracy of 79.55%, 79.02% and 79.40% using selected LFP channels for beta, low gamma and high gamma frequency bands, respectively. Compared with decoding using full LFP channels, decodi...

IEEE Transactions on Neural Networks and Learning Systems, 2016

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2013

Non-stationarity of electroencephalograph (EEG) data from session-to-session transfer is one of t... more Non-stationarity of electroencephalograph (EEG) data from session-to-session transfer is one of the challenges for EEG-based brain-computer interface systems, which can inversely affect their performance. Among methods proposed to address non-stationarity, adaptation is a promising method. In this study, an adaptive extreme learning machine (AELM) is proposed to update the initial classifier from the calibration session by using chunks of EEG data from the evaluation session whereby the common spatial pattern (CSP) algorithm is used to extract the most discriminative features. The effectiveness of the proposed algorithm is on motor imagery data collected from 12 healthy subjects during a calibration session and an evaluation session on a separate day. The results from the proposed AELM were compared with non-adaptive ELM and SVM classifiers. The results showed that AELM was significantly better (p=0.03). Moreover, the results also showed that accumulating the evaluation session data...

2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2013

The performance degradation for session to session classification in brain computer interface is ... more The performance degradation for session to session classification in brain computer interface is a critical problem. This paper proposes a novel method for model adaptation based on motor imagery of swallow EEG signal for dysphagia rehabilitation. A small amount of calibration testing data is utilized to select the model catering for test data. The features of the training and calibration testing data are firstly clustered and each cluster is labeled by the dominant label of the training data. The cluster with the minimum impurity is selected and the number of features consistent with the cluster label are calculated for both training and calibration testing data. Finally, the training model with the maximum number of consistent features is selected. Experiments conducted on motor imagery of swallow EEG data achieved an average accuracy of 74.29% and 72.64% with model adaptation for Laplacian derivates of power features and wavelet features, respectively. Further, an average accuracy increase of 2.9% is achieved with model adaptation using wavelet features, in comparison with that achieved without model adaptation, which is significant at 5% significance level as demonstrated in the statistical test.

The 2012 International Joint Conference on Neural Networks (IJCNN), 2012

ABSTRACT This paper addresses an important problem known as EEG non-stationarity in Brain-compute... more ABSTRACT This paper addresses an important problem known as EEG non-stationarity in Brain-computer Interfacing. We propose a novel technique called Dynamically Weighted Classification with Clustering (DWCC), which explores hidden states in non-stationary EEG using a modified k-means clustering method by combining cosine distance measure and mutual information criterion. DWCC builds a set of classifiers, one for each pair of clusters from different classes. A dynamically-weighted classifier ensemble network is trained to combine the outputs of the classifiers, where we propose to dynamically assign the weight of a classifier for each test sample based on its distances to the cluster centres associated with the classifier. Experimental results on publicly available BCI Competition IV Dataset 2a yielded a mean accuracy of 81.5% which is statistically significant (t-test p