A5100761349- EEG and Brain-Computer Interfaces
- Muscle activation and electromyography studies
- Pelvic floor disorders treatments
- Functional Brain Connectivity Studies
- Neural dynamics and brain function
- Blind Source Separation Techniques
- Urinary Bladder and Prostate Research
- Adaptive Control of Nonlinear Systems
- Fault Detection and Control Systems
- Advanced MRI Techniques and Applications
- Transcranial Magnetic Stimulation Studies
- Machine Learning and ELM
- Optical Imaging and Spectroscopy Techniques
- Botulinum Toxin and Related Neurological Disorders
- Motor Control and Adaptation
- Anorectal Disease Treatments and Outcomes
- Neuroscience and Neural Engineering
- Stroke Rehabilitation and Recovery
- Space Satellite Systems and Control
- Advanced Sensor and Energy Harvesting Materials
- Neurological disorders and treatments
- Gaze Tracking and Assistive Technology
- Advanced Neuroimaging Techniques and Applications
- Heart Rate Variability and Autonomic Control
- Stability and Control of Uncertain Systems
University of Houston
2016-2025
Minzu University of China
2023-2025
University of Miami
2024-2025
Soochow University
2012-2024
Second Affiliated Hospital of Soochow University
2012-2024
Harbin Institute of Technology
2014-2024
Sir Run Run Shaw Hospital
2011-2024
Zhejiang University
2014-2024
Anhui Institute of Information Technology
2024
Southern Medical University Shenzhen Hospital
2021-2024
Electroencephalogram (EEG) signals contain vital information on electrical activities of brain, and are widely used to aid epilepsy analysis. As a challenging effort in diagnosis, accurate classification different epileptic states is particular interest, has been extensively investigated. A new deep learning based methodology, namely EEG signal (EESC), proposed the paper. This methodology first transforms power spectrum density energy diagrams (PSDED), then applies convolutional neural...
Abstract Background New therapies are urgently needed for Alzheimer’s disease (AD). Sodium oligomannate (GV-971) is a marine-derived oligosaccharide with novel proposed mechanism of action. The first phase 3 clinical trial GV-971 has been completed in China. Methods We conducted 3, double-blind, placebo-controlled participants mild-to-moderate AD to assess efficacy and safety. Participants were randomized placebo or (900 mg) 36 weeks. primary outcome was the drug-placebo difference change...
Motor Imagery (MI) paradigm is critical in neural rehabilitation and gaming. Advances brain-computer interface (BCI) technology have facilitated the detection of MI from electroencephalogram (EEG). Previous studies proposed various EEG-based classification algorithms to identify MI, however, performance prior models was limited due cross-subject heterogeneity EEG data shortage for training. Therefore, inspired by generative adversarial network (GAN), this study aims propose an improved...
This paper addresses the problems of observer-based fault reconstruction and fault-tolerant control for Takagi-Sugeno fuzzy descriptor systems subject to time delays external disturbances. A novel learning observer is constructed achieve simultaneous system states actuator faults. Sufficient conditions existence proposed are explicitly provided. Utilizing reconstructed information, a reconfigurable controller based on separation property designed compensate impact faults performance by...
Brain-Computer Interface (BCI) techniques hold a great promise for neuroprosthetic applications. A desirable BCI system should be portable, minimally invasive, and feature high classification accuracy efficiency. As two commonly used non-invasive brain imaging modalities, Electroencephalography (EEG) functional near-infrared spectroscopy (fNIRS) have often been incorporated in the development of hybrid systems, largely due to their complimentary properties. In this study, we aimed...
Support vector machines are powerful tools used to solve the small sample and nonlinear classification problems, but their ultimate performance depends heavily upon selection of appropriate kernel penalty parameters. In this study, we propose using a particle swarm optimization algorithm optimize both parameters in order improve support machines. The optimized classifier was evaluated with motor imagery EEG signals terms prediction. Results show that can significantly accuracy signals.
Emerging evidence indicates that cognitive deficits in Alzheimer's disease (AD) are associated with disruptions brain network. Exploring alterations the AD network is therefore of great importance for understanding and treating disease. This study employs an integrative functional near-infrared spectroscopy (fNIRS) – electroencephalography (EEG) analysis approach to explore dynamic, regional AD-linked FNIRS EEG data were simultaneously recorded from 14 participants (8 healthy controls 6...
Mild cognitive impairment (MCI) is a disorder characterized by memory impairment, wherein patients have an increased likelihood of developing Alzheimer's disease (AD). The classification MCI and different AD stages therefore fundamental for understanding treating the disease. This study aimed to comprehensively investigate hemodynamic response patterns among various subject groups. Functional near-infrared spectroscopy (fNIRS) was employed measure signals from frontal bilateral parietal...
The rapid development of the automotive industry has brought great convenience to our life, which also leads a dramatic increase in amount traffic accidents. A large proportion accidents were caused by driving fatigue. EEG is considered as direct, effective, and promising modality detect In this study, we presented novel feature extraction strategy based on deep learning model achieve high classification accuracy efficiency using for fatigue detection. signals recorded from six healthy...
Emotion recognition is important in the application of brain-computer interface (BCI). Building a robust emotion model across subjects and sessions critical based BCI systems. Electroencephalogram (EEG) widely used tool to recognize different states. However, EEG has disadvantages such as small amplitude, low signal-to-noise ratio, non-stationary properties, resulting large differences subjects. To solve these problems, this paper proposes new method on multi-source associate domain...
Emotion plays crucial roles in human life. Recently, emotion classification from electroencephalogram (EEG) signal has attracted attention by researchers due to the rapid development of brain computer interface (BCI) techniques and machine learning algorithms. However, recent studies on show resource utilization because they use fully-supervised methods. Therefore, this study, we applied self-supervised methods improve efficiency resources usage. We employed a approach train deep multi-task...
The current data scarcity problem in EEG-based emotion recognition tasks leads to difficulty building high-precision models using existing deep learning methods. To tackle this problem, a dual encoder variational autoencoder-generative adversarial network (DEVAE-GAN) incorporating spatiotemporal features is proposed generate high-quality artificial samples. First, EEG for different emotions are preprocessed as differential entropy under five frequency bands and divided into segments with 5s...
The electrical conductivity value of the human skull is important for biophysics research brain. In present study, brain-to-skull ratio was estimated through in vivo experiments utilizing intracranial stimulation two epilepsy patients. A realistic geometry inhomogeneous head model including implanted silastic grids constructed with aid finite element method, and used to estimate ratio. Averaging over 49 sets measurements, mean standard deviation were found be 18.7 2.1, respectively.
A new approach has been developed by combining the K-mean clustering (KMC) method and a modified convolution kernel compensation (CKC) for multichannel surface electromyogram (EMG) decomposition. The KMC was first utilized to cluster vectors of observations at different time instants then estimate initial innervation pulse train (IPT). CKC method, with novel multistep iterative process, conducted update estimated IPT. performance proposed K-means clustering-Modified (KmCKC) evaluated...
The neuroimaging-based computer-aided diagnosis for Parkinson's disease (PD) has attracted considerable attention in recent years, where the classifier plays a critical role. Random vector functional link network (RVFL) shown its effectiveness classification task, while extended version, namely RVFL plus (RVFL+), integrates additional privileged information (PI) about training samples to help more effective classifier. On other hand, it is still popular way adopt only single neuroimaging...
The coupling strength between electroencephalogram (EEG) and electromyography (EMG) signals during motion control reflects the interaction cerebral motor cortex muscles. Therefore, neuromuscular characterization is instructive in assessing function. In this study, to overcome limitation of losing characteristics conventional time series symbolization methods, a variable scale symbolic transfer entropy (VS-STE) analysis approach was proposed for corticomuscular evaluation. Post-stroke...
Background Persistent motor deficits are very common in poststroke survivors and often lead to disability. Current clinical measures for profiling impairment assessing recovery largely subjective lack precision. Objective A multimodal neuroimaging approach was developed based on concurrent functional near-infrared spectroscopy (fNIRS) electroencephalography (EEG) identify biomarkers associated with function document the cortical reorganization. Methods EEG fNIRS data were simultaneously...
Electroencephalography (EEG)-based driving fatigue detection has gained increasing attention recently due to the non-invasive, low-cost, and potable nature of EEG technology, but it is still challenging extract informative features from noisy signals for detection. Radial basis function (RBF) neural network drawn lots as a promising classifier its linear-in-the-parameters structure, strong non-linear approximation ability, desired generalization property. The RBF performance heavily relies...