Kai Keng Ang - Profile on Academia.edu (original) (raw)

Journal Papers by Kai Keng Ang

Biomimetics, 2025

Multimodal brain-computer interfaces (BCIs) that combine electrical features from electroencephal... more Multimodal brain-computer interfaces (BCIs) that combine electrical features from electroencephalography (EEG) and hemodynamic features from functional nearinfrared spectroscopy (fNIRS) have the potential to improve performance. In this paper, we propose a multimodal EEG-and fNIRS-based BCI system with soft robotic (BCI-SR) components for personalized stroke rehabilitation. We propose a novel method of personalizing rehabilitation by aligning each patient's specific abilities with the treatment options available. We collected 160 single trials of motor imagery using the multimodal BCI from 10 healthy participants. We identified a confounding effect of respiration in the fNIRS signal data collected. Hence, we propose to incorporate a breathing sensor to synchronize motor imagery (MI) cues with the participant's respiratory cycle. We found that implementing this respiration synchronization (RS) resulted in less dispersed readings of oxyhemoglobin (HbO). We then conducted a clinical trial on the personalized multimodal BCI-SR for stroke rehabilitation. Four chronic stroke patients were recruited to undergo 6 weeks of rehabilitation, three times per week, whereby the primary outcome was measured using upper-extremity Fugl-Meyer Motor Assessment (FMA) and Action Research Arm Test (ARAT) scores on weeks 0, 6, and 12. The results showed a striking coherence in the activation patterns in EEG and fNIRS across all patients. In addition, FMA and ARAT scores were significantly improved on week 12 relative to the pre-trial baseline, with mean gains of 8.75 ± 1.84 and 5.25 ± 2.17, respectively (mean ± SEM). These improvements were all better than the Standard Arm Therapy and BCI-SR group when retrospectively compared to previous clinical trials. These results suggest that personalizing the rehabilitation treatment leads to improved BCI performance compared to standard BCI-SR, and synchronizing motor imagery cues to respiration increased the consistency of HbO levels, leading to better motor imagery performance. These results showed that the proposed multimodal BCI-SR holds promise to better engage stroke patients and promote neuroplasticity for better motor improvements.

Brain Research Bulletin, 2025

Paralysis affects many people worldwide, and the people affected often suffer from impaired commu... more Paralysis affects many people worldwide, and the people affected often suffer from impaired communication. We developed a microelectrode-based Brain-Computer Interface (BCI) for enabling communication in patients affected by paralysis, and implanted it in a patient with Multiple System Atrophy (MSA), a neurodegenerative disease that causes widespread neural symptoms including paralysis. To verify the effectiveness of the BCI system, it was also tested by implanting it in a non-human primate (NHP). Data from the human and NHP were used to train binary classifiers two different types of machine learning models: a Linear Discriminant Analysis (LDA) model, and a Long Short-Term Memory (LSTM)-based Artificial Neural Network (ANN). The LDA model performed at up to 72.7 % accuracy for binary decoding in the human patient, however, performance was highly variable and was much lower on most recording days. The BCI system was able to accurately decode movement vs non-movement in the NHP (accuracy using LDA: 82.7 ± 3.3 %, LSTM: 83.7 ± 2.2 %, 95 % confidence intervals), however it was not able to with recordings from the human patient (accuracy using LDA: 47.0 ± 5.1 %, LSTM: 44.6 ± 9.9 %, 95 % confidence intervals). We discuss how neurodegenerative diseases such as MSA can impede BCI-based communication, and postulate on the mechanisms by which this may occur.

Scientific Reports, 2025

Sleep posture, a vital aspect of sleep wellness, has become a crucial focus in sleep medicine. St... more Sleep posture, a vital aspect of sleep wellness, has become a crucial focus in sleep medicine. Studies show that supine posture can lead to a higher occurrence of obstructive sleep apnea, while lateral posture might reduce it. For bedridden patients, frequent posture changes are essential to prevent ulcers and bedsores, highlighting the importance of monitoring sleep posture. This paper introduces CHMMConvScaleNet, a novel method for sleep posture recognition using pressure signals from limited piezoelectric ceramic sensors. It employs a Movement Artifact and Rollover Identification (MARI) module to detect critical rollover events and extracts multi-scale spatiotemporal features using six subconvolution networks with different-length adjacent segments. To optimize performance, a Continuous Hidden Markov Model (CHMM) with rollover features is presented. We collected continuous real sleep data from 22 participants, yielding a total of 8583 samples from a 32-sensor array. Experiments show that CHMMConvScaleNet achieves a recall of 92.91%, precision of 91.87%, and accuracy of 93.41%, comparable to state-of-the-art methods that require ten times more sensors to achieve a slightly improved accuracy of 96.90% on non-continuous datasets. Thus, CHMMConvScaleNet demonstrates potential for home sleep monitoring using portable devices. Keywords Sleep posture, Markov Model optimization, Multi-scaled features fusion, Home sleep test Sleep posture, closely related to sleep quality, has become a crucial focus in sleep medicine. Studies associate the supine posture with increased risk of obstructive sleep apnea (OSA), while a lateral posture may help reduce the severity of OSA. Additionally, frequent posture changes are essential for bedridden patients to prevent ulcers and bedsores 1 , highlighting the need for effective sleep posture monitoring. Although Polysomnography (PSG) is the gold standard for sleep posture assessment 2 , its high cost, time consumption, and need for professional oversight limit its practicality for continuous monitoring. Home sleep tests(HST) devices offer practical, cost-effective solutions for monitoring sleep conditions and assessing posture at home. These HST can be categorized into wearable and non-wearable devices. Wearable devices, such as gyroscope-equipped chest straps 3 and accelerometer-integrated smartbands 4 , detect sleep posture and monitor heart rate but may cause hight false positives and discomfort due to limited placement areas (upper limb or thoracic region 5). Non-wearable devices, including camera-based, radar-based, and pressurebased systems, are more suitable for continuous monitoring. Video systems using RGB or RGB-depth images capture detailed postures 6,7 but are sensitive to lighting, and raise privacy concerns. Radar-based devices, such as the BodyCompass system from MIT 8 , detect posture changes via signal reflections 9,10. While effective in detecting posture during long-term monitoring, their performance is limited in short-term scenarios. Recent

NeuroSci, 2024

Detecting stress is important for improving human health and potential, because moderate levels o... more Detecting stress is important for improving human health and potential, because moderate levels of stress may motivate people towards better performance at cognitive tasks, while chronic stress exposure causes impaired performance and health risks. We propose a Brain-Computer Interface (BCI) system to detect stress in the context of high-pressure work environments. The BCI system includes an electroencephalogram (EEG) headband with dry electrodes and an electrocardiogram (ECG) chest belt. We collected EEG and ECG data from 40 participants during two stressful cognitive tasks: the Cognitive Vigilance Task (CVT), and the Multi-Modal Integration Task (MMIT) we designed. We also recorded self-reported stress levels using the Dundee Stress State Questionnaire (DSSQ). The DSSQ results indicated that performing the MMIT led to significant increases in stress, while performing the CVT did not. Subsequently, we trained two different models to classify stress from non-stress states, one using EEG features, and the other using heart rate variability (HRV) features extracted from the ECG. Our EEG-based model achieved an overall accuracy of 81.0% for MMIT and 77.2% for CVT. However, our HRV-based model only achieved 62.1% accuracy for CVT and 56.0% for MMIT. We conclude that EEG is an effective predictor of stress in the context of stressful cognitive tasks. Our proposed BCI system shows promise in evaluating mental stress in high-pressure work environments, particularly when utilizing an EEG-based BCI.

Journal of Neural Engineering, 2024

Objective. Motor imagery (MI) brain-computer interfaces (BCIs) based on electroencephalogram (EEG... more Objective. Motor imagery (MI) brain-computer interfaces (BCIs) based on electroencephalogram (EEG) have been developed primarily for stroke rehabilitation, however, due to limited stroke data, current deep learning methods for cross-subject classification rely on healthy data. This study aims to assess the feasibility of applying MI-BCI models pre-trained using data from healthy individuals to detect MI in stroke patients. Approach. We introduce a new transfer learning approach where features from two-class MI data of healthy individuals are used to detect MI in stroke patients. We compare the results of the proposed method with those obtained from analyses within stroke data. Experiments were conducted using Deep ConvNet and state-of-the-art subject-specific machine learning MI classifiers, evaluated on OpenBMI two-class MI-EEG data from healthy subjects and two-class MI versus rest data from stroke patients. Main results. Results of our study indicate that through domain adaptation of a model pre-trained using healthy subjects' data, an average MI detection accuracy of 71.15% (±12.46%) can be achieved across 71 stroke patients. We demonstrate that the accuracy of the pre-trained model increased by 18.15% after transfer learning (p < 0.001). Additionally, the proposed transfer learning method outperforms the subject-specific results achieved by Deep ConvNet and FBCSP, with significant enhancements of 7.64% (p < 0.001) and 5.55% (p < 0.001) in performance, respectively. Notably, the healthy-to-stroke transfer learning approach achieved similar performance to stroke-to-stroke transfer learning, with no significant difference (p > 0.05). Explainable AI analyses using transfer models determined channel relevance patterns that indicate contributions from the bilateral motor, frontal, and parietal regions of the cortex towards MI detection in stroke patients. Significance. Transfer learning from healthy to stroke can enhance the clinical use of BCI algorithms by overcoming the challenge of insufficient clinical data for optimal training.

Algorithms, 2024

Background. Brain-machine interfaces (BMIs) offer users the ability to directly communicate with ... more Background. Brain-machine interfaces (BMIs) offer users the ability to directly communicate with digital devices through neural signals decoded with machine learning (ML)-based algorithms. Spiking Neural Networks (SNNs) are a type of Artificial Neural Network (ANN) that operate on neural spikes instead of continuous scalar outputs. Compared to traditional ANNs, SNNs perform fewer computations, use less memory, and mimic biological neurons better. However, SNNs only retain information for short durations, limiting their ability to capture long-term dependencies in time-variant data. Here, we propose a novel spike-weighted SNN with spiking long short-term memory (swSNN-SLSTM) for a regression problem. Spike-weighting captures neuronal firing rate instead of membrane potential, and the SLSTM layer captures long-term dependencies. Methods. We compared the performance of various ML algorithms during decoding directional movements, using a dataset of microelectrode recordings from a macaque during a directional joystick task, and also an open-source dataset. We thus quantified how swSNN-SLSTM performed compared to existing ML models: an unscented Kalman filter, LSTM-based ANN, and membrane-based SNN techniques. Result. The proposed swSNN-SLSTM outperforms both the unscented Kalman filter, the LSTM-based ANN, and the membrane based SNN technique. This shows that incorporating SLSTM can better capture long-term dependencies within neural data. Also, our proposed swSNN-SLSTM algorithm shows promise in reducing power consumption and lowering heat dissipation in implanted BMIs.

Brain Sciences, 2024

Emotions are a series of subconscious, fleeting, and sometimes elusive manifestations of the huma... more Emotions are a series of subconscious, fleeting, and sometimes elusive manifestations of the human innate system. They play crucial roles in everyday life-influencing the way we evaluate ourselves, our surroundings, and how we interact with our world. To date, there has been an abundance of research on the domains of neuroscience and affective computing, with experimental evidence and neural network models, respectively, to elucidate the neural circuitry involved in and neural correlates for emotion recognition. Recent advances in affective computing neural network models often relate closely to evidence and perspectives gathered from neuroscience to explain the models. Specifically, there has been growing interest in the area of EEG-based emotion recognition to adopt models based on the neural underpinnings of the processing, generation, and subsequent collection of EEG data. In this respect, our review focuses on providing neuroscientific evidence and perspectives to discuss how emotions potentially come forth as the product of neural activities occurring at the level of subcortical structures within the brain's emotional circuitry and the association with current affective computing models in recognizing emotions. Furthermore, we discuss whether such biologically inspired modeling is the solution to advance the field in EEG-based emotion recognition and beyond.

Future Internet, 2024

Increasingly, urban planners are adopting virtual reality (VR) in designing urban green spaces (U... more Increasingly, urban planners are adopting virtual reality (VR) in designing urban green spaces (UGS) to visualize landscape designs in immersive 3D. However, the psychological effect of green spaces from the experience in VR may differ from the actual experience in the real world. In this paper, we systematically reviewed studies in the literature that conducted experiments to investigate the psychological benefits of nature in both VR and the real world to study nature in VR anchored to nature in the real world. We separated these studies based on the type of VR setup used, specifically, 360-degree video or 3D virtual environment, and established a framework of commonly used standard questionnaires used to measure the perceived mental states. The most common questionnaires include Positive and Negative Affect Schedule (PANAS), Perceived Restorativeness Scale (PRS), and Restoration Outcome Scale (ROS). Although the results from studies that used 360-degree video were less clear, results from studies that used 3D virtual environments provided evidence that virtual nature is comparable to real-world nature and thus showed promise that UGS designs in VR can transfer into real-world designs to yield similar physiological effects.

Sensors, 2024

Sleep quality is heavily influenced by sleep posture, with research indicating that a supine post... more Sleep quality is heavily influenced by sleep posture, with research indicating that a supine posture can worsen obstructive sleep apnea (OSA) while lateral postures promote better sleep. For patients confined to beds, regular changes in posture are crucial to prevent the development of ulcers and bedsores. This study presents a novel sparse sensor-based spatiotemporal convolutional neural network (S 3 CNN) for detecting sleep posture. This S 3 CNN holistically incorporates a pair of spatial convolution neural networks to capture cardiorespiratory activity maps and a pair of temporal convolution neural networks to capture the heart rate and respiratory rate. Sleep data were collected in actual sleep conditions from 22 subjects using a sparse sensor array. The S 3 CNN was then trained to capture the spatial pressure distribution from the cardiorespiratory activity and temporal cardiopulmonary variability from the heart and respiratory data. Its performance was evaluated using three rounds of 10 fold cross-validation on the 8583 data samples collected from the subjects. The results yielded 91.96% recall, 92.65% precision, and 93.02% accuracy, which are comparable to the state-of-the-art methods that use significantly more sensors for marginally enhanced accuracy. Hence, the proposed S 3 CNN shows promise for sleep posture monitoring using sparse sensors, demonstrating potential for a more cost-effective approach.

Brain Sciences, 2023

Research has shown the effectiveness of motor imagery in patient motor rehabilitation. Transcrani... more Research has shown the effectiveness of motor imagery in patient motor rehabilitation. Transcranial electrical stimulation has also demonstrated to improve patient motor and non-motor performance. However, mixed findings from motor imagery studies that involved transcranial electrical stimulation suggest that current experimental protocols can be further improved towards a unified design for consistent and effective results. This paper aims to review, with some clinical and neuroscientific findings from literature as support, studies of motor imagery coupled with different types of transcranial electrical stimulation and their experiments onhealthy and patient subjects. This review also includes the cognitive domains of working memory, attention, and fatigue, which are important for designing consistent and effective therapy protocols. Finally, we propose a theoretical all-inclusive framework that synergizes the three cognitive domains with motor imagery and transcranial electrical ...

Applied Sciences, 2023

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...

Scientific Reports, 2023

Decoding human action intention prior to motion onset with surface electromyograms (sEMG) is an e... more Decoding human action intention prior to motion onset with surface electromyograms (sEMG) is an emerging neuroengineering topic with interesting clinical applications such as intelligent control of powered prosthesis/exoskeleton devices. Despite extensive prior works in the related fields, it remains a technical challenge due to considerable variability of complex multi-muscle activation patterns in terms of volatile spatio-temporal characteristics. To address this issue, we first hypothesize that the inherent variability of the idle state immediately preceding the motion initiation needs to be addressed explicitly. We therefore design a hierarchical dynamic Bayesian learning network model that integrates an array of Gaussian mixture model – hidden Markov models (GMM-HMMs), where each GMM-HMM learns the multi-sEMG processes either during the idle state, or during the motion initiation phase of a particular motion task. To test the hypothesis and evaluate the new learning network, we...

IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022

Although brain-computer interface (BCI) shows promising prospects to help post-stroke patients re... more Although brain-computer interface (BCI) shows promising prospects to help post-stroke patients recover their motor function, its decoding accuracy is still

Scientific Reports, Sep 28, 2022

Brain-computer interfaces (BCIs) have recently been shown to be clinically effective as a novel m... more Brain-computer interfaces (BCIs) have recently been shown to be clinically effective as a novel method of stroke rehabilitation. In many BCI-based studies, the activation of the ipsilesional hemisphere was considered a key factor required for motor recovery after stroke. However, emerging evidence suggests that the contralesional hemisphere also plays a role in motor function rehabilitation. The objective of this study is to investigate the effectiveness of the BCI in detecting motor imagery of the affected hand from contralesional hemisphere. We analyzed a large EEG dataset from 136 stroke patients who performed motor imagery of their stroke-impaired hand. BCI features were extracted from channels covering either the ipsilesional, contralesional or bilateral hemisphere, and the offline BCI accuracy was computed using 10 \times 10-fold cross-validations. Our results showed that most stroke patients can operate the BCI using either their contralesional or ipsilesional hemisphere. Those with the ipsilesional BCI accuracy of less than 60% had significantly higher motor impairments than those with the ipsilesional BCI accuracy above 80%. Interestingly, those with the ipsilesional BCI accuracy of less than 60% achieved a significantly higher contralesional BCI accuracy, whereas those with the ipsilesional BCI accuracy more than 80% had significantly poorer contralesional BCI accuracy. This study suggests that contralesional BCI may be a useful approach for those with a high motor impairment who cannot accurately generate signals from ipsilesional hemisphere to effectively operate BCI.

IEEE Transactions on Affective Computing, 2022

Video summarization is the process of selecting a subset of informative keyframes to expedite sto... more Video summarization is the process of selecting a subset of informative keyframes to expedite storytelling with limited loss of information. In this article, we propose an EEG-Video Emotion-based Summarization (EVES) model based on a multimodal deep reinforcement learning (DRL) architecture that leverages neural signals to learn visual interestingness to produce quantitatively and qualitatively better video summaries. As such, EVES does not learn from the expensive human annotations but the multimodal signals. Furthermore, to ensure the temporal alignment and minimize the modality gap between the visual and EEG modalities, we introduce a Time Synchronization Module (TSM) that uses an attention mechanism to transform the EEG representations onto the visual representation space. We evaluate the performance of EVES on the TVSum and SumMe datasets. Based on the rank order statistics benchmarks, the experimental results show that EVES outperforms the unsupervised models and narrows the performance gap with supervised models. Furthermore, the human evaluation scores show that EVES receives a higher rating than the state-of-the-art DRL model DR-DSN by 11.4% on the coherency of the content and 7.4% on the emotion-evoking content. Thus, our work demonstrates the potential of EVES in selecting interesting content that is both coherent and emotion-evoking.

Frontiers in Neuroergonomics, 2022

Current motor imagery-based brain-computer interface (BCI) systems require a long calibration tim... more Current motor imagery-based brain-computer interface (BCI) systems require a long calibration time at the beginning of each session before they can be used with adequate levels of classification accuracy. In particular, this issue can be a significant burden for long term BCI users. This article proposes a novel transfer learning algorithm, called r-KLwDSA, to reduce the BCI calibration time for long-term users. The proposed r-KLwDSA algorithm aligns the user's EEG data collected in previous sessions to the few EEG trials collected in the current session, using a novel linear alignment method. Thereafter, the aligned EEG trials from the previous sessions and the few EEG trials from the current sessions are fused through a weighting mechanism before they are used for calibrating the BCI model. To validate the proposed algorithm, a large dataset containing the EEG data from 11 stroke patients, each performing 18 BCI sessions, was used. The proposed framework demonstrated a signifi...

Clinical EEG and Neuroscience, 2021

Background. A number of recent randomized controlled trials reported the efficacy of brain-comput... more Background. A number of recent randomized controlled trials reported the efficacy of brain-computer interface (BCI) for upperlimb stroke rehabilitation compared with other therapies. Despite the encouraging results reported, there is a significant variance in the reported outcomes. This paper aims to investigate the effectiveness of different BCI designs on poststroke upper-limb rehabilitation. Methods. The effect sizes of pooled and individual studies were assessed by computing Hedge's g values with a 95% confidence interval. Subgroup analyses were also performed to examine the impact of different BCI designs on the treatment effect. Results. The study included 12 clinical trials involving 298 patients. The analysis showed that the BCI yielded significant superior short-term and long-term efficacy in improving the upper-limb motor function compared to the control therapies (Hedge's g = 0.73 and 0.33, respectively). Based on our subgroup analyses, the BCI studies that used the intention of movement had a higher effect size compared to those used motor imagery (Hedge's g = 1.21 and 0.55, respectively). The BCI studies using band power features had a significantly higher effect size than those using filter bank common spatial patterns features (Hedge's g = 1.25 and-0.23, respectively). Finally, the studies that used functional electrical stimulation as the BCI feedback had the highest effect size compared to other devices (Hedge's g = 1.2). Conclusion. This meta-analysis confirmed the effectiveness of BCI for upper-limb rehabilitation. Our findings support the use of band power features, the intention of movement, and the functional electrical stimulation in future BCI designs for poststroke upper-limb rehabilitation.

Frontiers in Human Neuroscience, Jul 16, 2021

Brain Changes in Stroke After BCI and tDCS but not in the MI-BCI + tDCS group although both group... more Brain Changes in Stroke After BCI and tDCS but not in the MI-BCI + tDCS group although both groups gained significant motor function improvement post-intervention with no group difference. MI-BCI and tDCS may exert differential or even opposing impact on brain functional reorganization during poststroke motor rehabilitation; therefore, the integration of the two strategies requires further refinement to improve efficacy and effectiveness.

IEEE Transactions on Neural Networks and Learning Systems, 2021

The performance of a classifier in a brain-computer interface (BCI) system is highly dependent on... more The performance of a classifier in a brain-computer interface (BCI) system is highly dependent on the quality and quantity of training data. Typically, the training data are collected in a laboratory where the users perform tasks in a controlled environment. However, users' attention may be diverted in reallife BCI applications and this may decrease the performance of the classifier. To improve the robustness of the classifier, additional data can be acquired in such conditions, but it is not practical to record electroencephalogram (EEG) data over several long calibration sessions. A potentially time-and cost-efficient solution is artificial data generation. Hence, in this study, we proposed a framework based on the deep convolutional generative adversarial networks (DCGANs) for generating artificial EEG to augment the training set in order to improve the performance of a BCI classifier. To make a comparative investigation, we designed a motor task experiment with diverted and focused attention conditions. We used an end-to-end deep convolutional neural network for classification between movement intention and rest using the data from 14 subjects. The results from the leaveone subject-out (LOO) classification yielded baseline accuracies of 73.04% for diverted attention and 80.09% for focused attention without data augmentation. Using the proposed DCGANs-based framework for augmentation, the results yielded a significant improvement of 7.32% for diverted attention (p < 0.01) and 5.45% for focused attention (p < 0.01). In addition, we implemented the method on the data set IVa from BCI competition III to distinguish different motor imagery tasks. The proposed method increased the accuracy by 3.57% (p < 0.02). This study shows that using GANs for EEG augmentation can significantly improve BCI performance, especially in real-life applications, whereby users' attention may be diverted.

Scientific Reports, 2021

Stroke leads to both regional brain functional disruptions and network reorganization. However, h... more Stroke leads to both regional brain functional disruptions and network reorganization. However, how brain functional networks reconfigure as task demand increases in stroke patients and whether such reorganization at baseline would facilitate post-stroke motor recovery are largely unknown. To address this gap, brain functional connectivity (FC) were examined at rest and motor tasks in eighteen chronic subcortical stroke patients and eleven age-matched healthy controls. Stroke patients underwent a 2-week intervention using a motor imagery-assisted brain computer interface-based (MI-BCI) training with or without transcranial direct current stimulation (tDCS). Motor recovery was determined by calculating the changes of the upper extremity component of the Fugl–Meyer Assessment (FMA) score between pre- and post-intervention divided by the pre-intervention FMA score. The results suggested that as task demand increased (i.e., from resting to passive unaffected hand gripping and to active ...

Biomimetics, 2025

Brain Research Bulletin, 2025

Scientific Reports, 2025

NeuroSci, 2024

Journal of Neural Engineering, 2024

Algorithms, 2024

Brain Sciences, 2024

Future Internet, 2024

Sensors, 2024

Brain Sciences, 2023

Applied Sciences, 2023

Scientific Reports, 2023

IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022

Scientific Reports, Sep 28, 2022

IEEE Transactions on Affective Computing, 2022

Frontiers in Neuroergonomics, 2022

Clinical EEG and Neuroscience, 2021

Frontiers in Human Neuroscience, Jul 16, 2021

IEEE Transactions on Neural Networks and Learning Systems, 2021

Scientific Reports, 2021

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 15, 2024

Sleep posture, intricately connected to sleep health, has emerged as a crucial focus in sleep med... more Sleep posture, intricately connected to sleep health, has emerged as a crucial focus in sleep medicine. Studies have associated the supine posture with increased frequency and severity of obstructive sleep apnea (OSA), while lateral postures may mitigate these effects. For bedridden patients, regular posture adjustments are essential to prevent ulcers and bedsores, highlighting the need for precise sleep posture detection. In this work, we propose STConvSleepNet, a novel method for detecting sleep posture using piezoelectric sensor pressure data. It employs two shallow CNN2D networks to discriminate spatial features and two CNN1D networks to discriminate temporal features, with each network processing either the heart rate or the respiratory rate. These networks are trained to detect sleep postures from spatial features of the pressure distribution, and temporal features of heart rate and cardiopulmonary activities variability. We collected data from 22 participants with 300-450 samples each, for a total of 8583 samples using a 32-sensor array. We performed 5-fold cross-validation on the data using the proposed method. The results showed that the proposed STConvSleepNet yielded 91.11% recall, 92.89% precision, and 92.39% accuracy. This is comparable to the state-of-the-art method that needs a significantly increased number of sensors to achieve slightly increased accuracy of 96.90%. Hence these results showed promise of using the proposed STConvSleepNet for cost-effective home sleep monitoring using portable devices. Clinical Relevance-This sleep posture detection potentially suits diverse populations for long-term, at home settings.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 15, 2024

In this study, we introduce a novel brain-computer-brain (BCB) system to investigate the aftereff... more In this study, we introduce a novel brain-computer-brain (BCB) system to investigate the aftereffects of individualized, task-dependent transcranial alternating current stimulation (tACS) delivered to the motor cortex. While previous studies utilized either a generic stimulation frequency or matched it to an individual's resting frequency (e.g. individual alpha frequency, iAF), our study employed a trial-by-trial tACS stimulation design wherein the stimulation frequency delivered matches the individual's peak motor imagery (MI) performance frequency. 14 healthy subjects participated in both tACS and tACS-sham on separate days in a within-subject, randomized controlled design. We found that active tACS delivered to subjects receiving alpha (α)-tACS resulted in a decline in MI performance while that with tACS-sham did not differ significantly from baseline. However, subjects receiving beta (β)-tACS showed no significant difference in effect for both active tACS and tACS-sham conditions. These findings indirectly corroborated with that from literature advocating the notion of α tACS as functionally inhibitory; hence the consequential deterioration of MI performance observed only in α-tACS subjects. A more conclusive analysis will be conducted once more data is collected from this ongoing study. Clinical Relevance: The results gathered suggest the differential functional significance of α-and β-tACS in an individualized MI task-specific tACS delivery to the motor cortex with concurrent EEG recording. Although insignificant at the point of data analysis where sample size is small in this ongoing study, tACS-sham (30 Hz) seemed to potentially modulate neural oscillations in the direction of improving MI performance. These findings can inform future tACS study designs based on a system with personalized stimulation delivery for MI task investigations within laboratory and clinical settings potentially beneficial towards upper limb stroke rehabilitation.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 15, 2024

Accelerated intermittent theta burst stimulation (aiTBS) is a novel and effective treatment for d... more Accelerated intermittent theta burst stimulation (aiTBS) is a novel and effective treatment for drug-resistant depression. While past studies have identified encephalography (EEG) features predicting repetitive transcranial magnetic stimulation (rTMS) outcomes, EEG biomarkers specifically for aiTBS in depression patients have not been explored. In this pilot trial on 5 depression patients undergoing aiTBS, we assessed clinical outcome using the Montgomery-Asberg Depression Rating Scale (MADRS) and collected resting-state EEG pre and post-treatment. All patients showed an improvement in MADRS, with 3 having at least 50% improvement. We found significant correlations between MADRS change and pre-treatment frontal beta power, midline frontal Lempel-Ziv Complexity (LZC) and alpha connectivity. We also observed a trend of increased frontal theta power post-treatment. However, no significant correlations emerged between MADRS change and change in EEG feature post-treatment. This preliminary trial highlights the potential for investigating aiTBS-specific EEG biomarkers, paving the way for larger studies to enhance personalized neurostimulation and predict treatment outcomes in drug-resistant depression patients.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 24, 2023

Functional near-infrared spectroscopy (fNIRS) is a neuroimaging method that measures oxygenated h... more Functional near-infrared spectroscopy (fNIRS) is a neuroimaging method that measures oxygenated hemoglobin (HbO) levels in the brain to infer neural activity using nearinfrared light. Measured HbO levels are directly affected by a person's respiration. Hence, respiration cycles tend to confound fNIRS readings in motor imagery-based fNIRS Brain-Computer Interfaces (BCI). To reduce this confounding effect, we propose a method of synchronizing the motor imagery cue timing with the subject's respiration cycle using a breathing sensor. We conducted an experiment to collect 160 single trials from 10 subjects performing motor imagery using an fNIRS-based BCI and the breathing sensor. We then compared the HbO levels in trials with and without respiration synchronization. The results showed that respiration synchronization yielded HbO levels that were less dispersed across trials, and a negative correlation between the dispersion index of HbO levels with MI decoding accuracies was found across the 10 subjects. This showed that synchronizing motor imagery cues to respiration can yield increased HbO level consistency leading to better MI performance. Hence, the proposed method holds promise to improve the decoding performance of fNIRS-BCI by reducing the confounding effects of respiration.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 24, 2023

The brain criticality hypothesis suggests that neural networks and multiple aspects of brain acti... more The brain criticality hypothesis suggests that neural networks and multiple aspects of brain activity selforganize into a critical state, and criticality marks the transition between ordered and disordered states. This hypothesis is appealing from computer science perspective because neural networks at criticality exhibit optimal processing and computing properties while having implications in clinical applications to neurological disorders. In this paper, we introduced brain criticality analysis to track neurodevelopment from childhood to adolescence using the electroencephalogram (EEG) data of 662 subjects aged 5 to 16 years from the Child Mind Institute. We computed brain criticality from long-range temporal correlation (LRTC) using detrended fluctuation analysis (DFA). We also compared the brain criticality analysis with standard EEG power analysis. The results showed a statistically significant increase in brain criticality from childhood to adolescence in the alpha band. A decreasing trend was observed in theta band from EEG power analysis, but a much higher variance was observed compared to the brain criticality analysis. However, the significant results were only observed in some EEG channels, and not observed if the analysis were performed separately with eyes-open and eyes-close condition. Nonetheless, the results suggest that brain criticality may serve as a biomarker of brain development and maturation, but further research is needed to improve brain criticality algorithms and EEG analysis methods. Clinical Relevance-The brain criticality analysis may be used to characterize and predict neurodevelopment in early childhood.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Nov 1, 2022

Implanted microelectrode arrays can directly pick up electrode signals from the primary motor cor... more Implanted microelectrode arrays can directly pick up electrode signals from the primary motor cortex (M1) during movement, and brain-machine interfaces (BMIs) can decode these signals to predict the directions of contemporaneous movements. However, it is not well known how much each individual input is responsible for the overall performance of a BMI decoder. In this paper, we seek to quantify how much each channel contributes to an artificial neural network (ANN)-based decoder, by measuring how much the removal of each individual channel degrades the accuracy of the output. If information on movement direction was equally distributed among channels, then the removal of one would have a minimal effect on decoder accuracy. On the other hand, if that information was distributed sparsely, then the removal of specific information-rich channels would significantly lower decoder accuracy. We found that for most channels, their removal did not significantly affect decoder performance. However, for a subset of channels (16 out of 61), removing them significantly reduced the decoder accuracy. This suggests that information is not uniformly distributed among the recording channels. We propose examining these channels further to optimize BMIs more effectively, as well as understand how M1 functions at the neuronal level.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Nov 1, 2021

There is a strong demand for acquisition, processing and understanding of a variety of physiologi... more There is a strong demand for acquisition, processing and understanding of a variety of physiological and behavioral signals from the measurements in human-robot interface (HRI). However, multiple data streams from these measurements bring considerable challenges for their synchronizations, either for offline analysis or for online HRI applications, especially when the sensors are wirelessly connected, without synchronization mechanisms, such as a network-time-protocol. In this paper, we presented a full wireless multi-modality sensor system comprising biopotential measurements such as EEG, EMG and inertial parameter data of articulated body-limb motions. In the paper, we propose two methods to synchronize and calibrate the transmission latencies from different wireless channels. The first method employs the traditional artificial electrical timing signal. The other one employs the force-acceleration relationship governed by Newton's Second Law to facilitate reconstruction of the sample-to-sample alignment between the two wireless sensors. The measured latencies are investigated and the result show that they could be determined consistently and accurately by the devised techniques.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Nov 1, 2021

Affective Computing is a multidisciplinary area of research that allows computers to perform huma... more Affective Computing is a multidisciplinary area of research that allows computers to perform human emotion recognition, with potential applications in areas such as healthcare, gaming and intuitive human computer interface design. Hence, this paper proposes an affective interaction system using dry EEG-based Brain-Computer Interface and Virtual Reality (BCI-VR). The proposed BCI-VR system integrates existing low-cost consumer devices such as an EEG headband with frontal and temporal dry electrodes for brain signal acquisition, and a low-cost VR headset that houses an Android handphone. The handphone executes an in-house developed software that connects wirelessly to the headband, processes the acquired EEG signals, and displays VR content to elicit emotional responses. The proposed BCI-VR system was used to collect EEG data from 13 subjects while they watched VR content that elicits positive or negative emotional responses. EEG bandpower features were extracted to train Linear Discriminant and Support Vector Machine classifiers. The classification performances of these classifiers on this dataset and the results of a public dataset (SEED-IV) are then evaluated. The results in classifying positive vs negative emotions in both datasets (~66% for 2-class) show promise that positive and negative emotions can be detected by the proposed low cost BCI-VR system, yielding nearly the same performance on the public dataset that used wet EEG electrodes. Hence the results show promise of the proposed BCI-VR system for real-time affective interaction applications in future.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 20, 2020

Mental stress is a prevalent issue in the modern society and a prominent contributing factor to v... more Mental stress is a prevalent issue in the modern society and a prominent contributing factor to various physical and psychological diseases. This paper investigates the feasibility of detecting different stress levels using electroencephalography (EEG), and evaluates the effectiveness of various stress-relief methods. EEG data were collected from 25 subjects while they were at rest and under 3 different levels of stress induced by mental arithmetic tasks. Nine features that correlate with stress from existing literature were extracted. Subsequently, discriminative features were selected by Fisher Ratio and used to train a Linear Discriminant Analysis classifier. Results from 10-fold cross-validation yielded averaged intra-subject classification accuracy of 85.6% for stress versus rest, 71.2% for two levels of stress and rest, and 58.4% for three levels of stress and rest. The results showed high promise of using EEG to detect level of stress, and the features selected showed that Beta brain waves (13-30Hz) and prefrontal relative Gamma power are most discriminative. Five different stress-relief methods were then evaluated, and the method of hugging a pillow was found to be the most effective measure relatively in decreasing the stress level detected using EEG. These results show promise of future research in real-time stress detection and reduction using EEG for stress management and relief.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 20, 2020

Mindfulness interventions are increasingly used in clinical settings. Neurophysiological mechanis... more Mindfulness interventions are increasingly used in clinical settings. Neurophysiological mechanisms underlying mindfulness offer objective evidence that can help us evaluate the efficacy of mindfulness. Recent advances in technology have facilitated the use of functional Near-Infrared Spectroscopy (fNIRS) as a light weight, portable, and relatively lower cost neuroimaging device as compared to functional Magnetic Resonance Imaging (fMRI). In contrast to numerous fMRI studies, there are scanty investigations using fNIRS to study mindfulness. Hence, this study was done to investigate the feasibility of using a continuous-wave multichannel fNIRS system to study cerebral cortex activations on a mindfulness task versus a baseline task. NIRS data from 14 healthy Asian subjects were collected. A statistical parametric mapping toolbox specific for statistical analysis of NIRS signal called NIRS_SPM was used to study the activations. The results from group analysis performed on the contrast of the mindfulness versus baseline tasks showed foci of activations on the left and central parts of the prefrontal cortex. The findings are consistent with prevailing fMRI studies and show promise of using fNIRS system for studying real-time neurophysiological cortical activations during mindfulness practice.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 20, 2020

Brain-machine interfaces (BMIs) allow individuals to communicate with computers using neural sign... more Brain-machine interfaces (BMIs) allow individuals to communicate with computers using neural signals, and Kalman Filter (KF) are prevailingly used to decode movement directions from these neural signals. In this paper, we implemented a multi-layer long short-term memory (LSTM)based artificial neural network (ANN) for decoding BMI neural signals. We collected motor cortical neural signals from a nonhuman primate (NHP), implanted with microelectrode array (MEA) while performing a directional joystick task. Next, we compared the LSTM model in decoding the joystick trajectories from the neural signals against the prevailing KF model. The results showed that the LSTM model yielded significantly improved decoding accuracy measured by mean correlation coefficient (0.84, p < 10 -7 ) than the KF model (0.72). In addition, using a principal component analysis (PCA)-based dimensionality reduction technique yielded slightly deteriorated accuracies for both the LSTM (0.80) and KF (0.70) models, but greatly reduced the computational complexity. The results showed that the LSTM decoding model holds promise to improve decoding in BMIs for paralyzed humans.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 20, 2020

Many prior studies on EEG-based emotion recognition did not consider the spatial-temporal relatio... more Many prior studies on EEG-based emotion recognition did not consider the spatial-temporal relationships among brain regions and across time. In this paper, we propose a Regionally-Operated Domain Adversarial Network (RODAN), to learn spatial-temporal relationships that correlate between brain regions and time. Moreover, we incorporate the attention mechanism to enable cross-domain learning to capture both spatial-temporal relationships among the EEG electrodes and an adversarial mechanism to reduce the domain shift in EEG signals. To evaluate the performance of RODAN, we conduct subject-dependent, subject-independent, and subjectbiased experiments on both DEAP and SEED-IV data sets, which yield encouraging results. In addition, we also discuss the biased sampling issue often observed in EEG-based emotion recognition and present an unbiased benchmark for both DEAP and SEED-IV.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 20, 2020

A large amount of calibration data is typically needed to train an electroencephalogram (EEG)-bas... more A large amount of calibration data is typically needed to train an electroencephalogram (EEG)-based braincomputer interfaces (BCI) due to the non-stationary nature of EEG data. This paper proposes a novel weighted transfer learning algorithm using a dynamic time warping (DTW) based alignment method to alleviate this need by using data from other subjects. DTW-based alignment is first applied to reduce the temporal variations between a specific subject data and the transfer learning data from other subjects. Next, similarity is measured using Kullback Leibler divergence (KL) between the DTW aligned data and the specific subject data. The other subjects' data are then weighted based on their KL similarity to each trials of the specific subject data. This weighted data from other subjects are then used to train the BCI model of the specific subject. An experiment was performed on publicly available BCI Competition IV dataset 2a. The proposed algorithm yielded an average improvement of 9% compared to a subject-specific BCI model trained with 4 trials, and the results yielded an average improvement of 10% compared to naive transfer learning. Overall, the proposed DTW-aligned KL weighted transfer learning algorithm show promise to alleviate the need of large amount of calibration data by using only a short calibration data.

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

One of the major limitations of current electroencephalogram (EEG)-based brain-computer interface... more One of the major limitations of current electroencephalogram (EEG)-based brain-computer interfaces (BCIs) is the long calibration time. Due to a high level of noise and nonstationarity inherent in EEG signals, a calibration model trained using limited number of train data may not yield an accurate BCI model. To address this problem, this paper proposes a novel subject-to-subject transfer learning framework that improves the classification accuracy using limited training data. The proposed framework consists of two steps: The first step identifies if the target subject will benefit from transfer learning using cross-validation on the few available subject-specific training data. If transfer learning is required a novel algorithm for measuring similarity, called the Jensen-Shannon ratio (JSR) compares the data of the target subject with the data sets from previous subjects. Subsequently, the previously calibrated BCI subject model with the highest similarity to the target subject is used as the BCI target model. Our experimental results using the proposed framework obtained an average accuracy of 77% using 40 subject-specific trials, outperforming the subject-specific BCI model by 3%.

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

Among various brain activity patterns, Steady State Visual Evoked Potential (SSVEP) based Brain C... more Among various brain activity patterns, Steady State Visual Evoked Potential (SSVEP) based Brain Computer Inter-face (BCI) requires the least training time while carrying the fastest information transfer rate, making it highly suitable for deploying efficient self-paced BCI systems. In this study, we propose a Spectrum and Phase Adaptive CCA (SPACCA) for subject-and device-specific SSVEP-based BCI. Cross subject heterogeneity of spectrum distribution is taken into consideration to improve the prediction accuracy. We design a library of phase shifting reference signals to accommodate subjective and device-related response time lag. With the flexible reference signal generating approach, the system can be optimized for any specific flickering source, include LED, computer screen and mobile devices. We evaluated the performance of SPACCA using three sets of data that use LED, computer screen and mobile device (tablet) as stimuli sources respectively. The first two data sets are publicly...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 1, 2018

Subject-specific calibration plays an important role in electroencephalography (EEG)-based Brain-... more Subject-specific calibration plays an important role in electroencephalography (EEG)-based Brain-Computer Interface (BCI) for Motor Imagery (MI) detection. A calibration session is often introduced to build a subject specific model, which then can be deployed into BCI system for MI detection in the following rehabilitation sessions. The model is termed as a fixed calibration model. Progressive adaptive models can also be built by using data not only from calibration session, but also from available rehabilitation sessions. It was reported that the progressive adaptive model yielded significant improved MI detection compared to the fixed model in a retrospective clinical study. In this work, we deploy the progressive adaptation model in a BCI-based stroke rehabilitation system and bring it online. We dub this system nBETTER (Neurostyle Brain Exercise Therapy Towards Enhanced Recovery) . A clinical trial using the nBETTER system was conducted to evaluate the performance of 11 stroke patients who underwent a calibration session followed by 18 rehabilitation sessions over 6 weeks. We conduct retrospective analysis to compare the performance of various modeling strategies: the fixed calibration model, the online progressive adaptation model and a light-weight adaptation model, where the second one is generated online by nBETTER system and the other two models are obtained retrospectively. The mean accuracy of the three models across 11 subjects are 68.17%, 74.04% and 74.53% respectively. Statistical test conducted on the three groups using ANOVA yields a p-value of 9.83-e06. The test result shows that the two adaptation models both have significant different mean from fixed mode. Hence our study confirmed the effectiveness of using the progressive adaptive model for EEGbased BCI to detect MI in an online setting.

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

Brain-Computer Interface (BCI) provides an alternate channel of interaction for people with sever... more Brain-Computer Interface (BCI) provides an alternate channel of interaction for people with severe motor disabilities. The Common Spatial Pattern (CSP) algorithm is effective in extracting discriminative features from EEG data for motor imagery-based Brain-Computer Interface (BCI). CSP yields signal from various locations for better performance. In this study, we selected a subset of EEG channels using correlation coefficient of spectral entropy and compared the classification performance using the Filter Bank Common Spatial Pattern (FBCSP) algorithm. We conducted experiments on 4 healthy subjects and one Amyotrophic Lateral Sclerosis (ALS) patient. The results showed that the proposed channel selection method increased classification accuracy of all subjects from 1.25% to 8.22%. Optimal performance was obtained using between 13 to 24 channels, and channels located over the motor cortex zone possess higher probabilities of being selected. Comparing with the channels manually selecte...

Robust Local Field Potential-based Neural Decoding by Actively Selecting Discriminative Channels

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...

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

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 1, 2018

Various adaptation techniques have been proposed to address the non-stationarity issue faced by e... more Various adaptation techniques have been proposed to address the non-stationarity issue faced by electroencephalogram (EEG)-based brain-computer interfaces (BCIs). However, most of these adaptation techniques are only suitable for binary-class BCIs. This paper proposes a supervised multiclass data space adaptation technique (MDSA) to transform the test data using a linear transformation such that the distribution difference between the multiclass train and test data is minimized. The results of using the proposed MDSA on BCI Competition IV dataset 2a improved the classification accuracy by an average of 4.3% when 20 trials per class were used from the test session to estimate adaptation transformation. The results also showed that the proposed MDSA algorithm outperformed the multi pooled mean linear discrimination (MPMLDA) technique with as few as 10 trials per class used for calculating the transformation matrix. Hence the results showed the effectiveness of the proposed MDSA algorithm in addressing non-stationarity issue for multiclass EEG-based BCI.

ArXiv, 2021

Lack of adequate training samples and noisy highdimensional features are key challenges faced by ... more Lack of adequate training samples and noisy highdimensional features are key challenges faced by Motor Imagery (MI) decoding algorithms for electroencephalogram (EEG) based Brain-Computer Interface (BCI). To address these challenges, inspired from neuro-physiological signatures of MI, this paper proposes a novel Filter-Bank Convolutional Network (FBCNet) for MI classification. FBCNet employs a multi-view data representation followed by spatial filtering to extract spectro-spatially discriminative features. This multistage approach enables efficient training of the network even when limited training data is available. More significantly, in FBCNet, we propose a novel Variance layer that effectively aggregates the EEG time-domain information. With this design, we compare FBCNet with stateof-the-art (SOTA) BCI algorithm on four MI datasets: The BCI competition IV dataset 2a (BCIC-IV-2a), the OpenBMI dataset, and two large datasets from chronic stroke patients. The results show that, by...

arXiv (Cornell University), Feb 15, 2019

Current treatments for functional loss of the upper extremity post-stroke remain limited in effic... more Current treatments for functional loss of the upper extremity post-stroke remain limited in efficacy, particularly for those with moderate to severe impairment. The non-invasive treatment of transcranial direct current stimulation (tDCS) is a promising intervention technique being tested widely in clinical trials, however, whether tDCS benefits stroke rehabilitation and how tDCS modulates synaptic plasticity are largely unknown. In this study (www.clinicaltrials.gov, NTC01897025), nineteen chronic stroke patients with moderate-tosevere upper limb disability (Fugl-Meyer assessment = 33.9 ± 8.1, out of 66) were recruited for a two-week treatment of combined bi-hemispherical tDCS (anodal electrode placed over affected M1, while cathode over the unaffected M1) and motor imagery based robotic arm training for stroke rehabilitation. Each patient participated in 10 successive rehabilitation sessions, including 20 minutes real/sham tDCS stimulation, followed by 60 minutes of robot assisted arm movement therapy. The primary outcome measure was the upper extremity component of Fugl-Meyer assessment, while the secondary outcome measures included resting motor threshold (RMT) of stroke affected M1 motor cortex, the whole brain longitudinal activity map, and Granger causality graph derived from task-related functional MRI. The RMT measurements showed tDCS evoked higher excitability (lower RMT) in the motor cortex (DRMT tDCS -DRMT sham = -11.6%, P = 0.04) that enhanced the descending conduction from the lesioned primary motor cortex to the target hand muscle. Granger causality analysis further revealed the enhanced brain circuitry rewiring from lesioned cerebellum to premotor (DF tDCS Cer_L->PreM_R = +0.0112 ± 0.0128, P = 0.0304), and from lesioned premotor to primary motor cortex (DF tDCS PreM_R->PriM_R = +0.0077 ± 0.0100, P = 0.0497) in the tDCS group only owing to the newly formed connections close to the anodal electrode. Rebuilding of these critical pathways was clear via the increase of event related desynchronisation (Laterality tDCS = 0.050, Laterality Sham = -0.063, P = 0.016) and white matter integrity in the same lesioned region. Furthermore, only the tDCS group demonstrated a positive recovery trend in the penumbra regions by the longitudinal functional MRI analysis. To interpret tDCS mechanism, we introduce a polarized GABA theory, where GABA A receptor activity depends on the orientation of dipolar molecule GABA that can be manipulated by tDCS field. Results suggest that tDCS intervention lowers motor excitability via re-orienting GABA, leading to reorganization of the lesioned cortical network, and the motor descending pathway, finally the recovery of motor function.

Any brain–computer interface (BCI) system must translate signals from the users brain into messag... more Any brain–computer interface (BCI) system must translate signals from the users brain into messages or commands (see Fig. 1). Many signal processing and machine learning techniques have been developed for this signal translation, and this chapter reviews the most common ones. Although these techniques are often illustrated using electroencephalography (EEG) signals in this chapter, they are also suitable for other brain signals.