A5014332064- EEG and Brain-Computer Interfaces
- Neuroscience and Neural Engineering
- Structural Health Monitoring Techniques
- Advanced Memory and Neural Computing
- Gaze Tracking and Assistive Technology
- Neural dynamics and brain function
- Advanced Adaptive Filtering Techniques
- Optical Imaging and Spectroscopy Techniques
- Functional Brain Connectivity Studies
- Blind Source Separation Techniques
- Non-Invasive Vital Sign Monitoring
- Advanced Manufacturing and Logistics Optimization
- Aeroelasticity and Vibration Control
- Brain Tumor Detection and Classification
- Vibration Control and Rheological Fluids
- Scheduling and Optimization Algorithms
- Quantum chaos and dynamical systems
- Chaos control and synchronization
- Infrared Thermography in Medicine
- Maritime Navigation and Safety
- Medical Image Segmentation Techniques
- Assembly Line Balancing Optimization
- Energy Efficient Wireless Sensor Networks
- Robotic Path Planning Algorithms
- Muscle activation and electromyography studies
Shanghai University
2012-2025
University of Electronic Science and Technology of China
2022-2024
Shanghai Jiao Tong University
2006-2007
Abstract In building a practical and robust brain-computer interface (BCI), the classification of motor imagery (MI) from electroencephalography (EEG) across multiple days is long-standing challenge due to large variability EEG signals. We collected dataset MI 5 different with 25 subjects, first open-access address BCI issues number subjects. The includes session data (2–3 apart) for each subject. Each contains 100 trials left-hand right-hand MI. this report, we provide benchmarking accuracy...
Hybrid brain-computer interface (hBCI) refers to a system composed of single-modality BCI and another system. In this paper, we propose an online hybrid combining steady-state visual evoked potential (SSVEP) eye movements improve the performance systems. Twenty buttons corresponding 20 characters are evenly distributed in five regions GUI flash at same time arouse SSVEP. At end flash, four move different directions, subject continues stare target with eyes generate movements. The CCA method...
Selective attention, essential in discerning visual stimuli, enables the identification of threats such as snakes—a prime evolutionary influence on human system. This phenomenon is encapsulated snake detection theory (SDT), which posits that our ancestors' need to recognize these predators led specialized perceptual abilities. investigation utilizes steady-state evoked potentials (SSVEP) alongside random image structure evolution technique, systematically increases clarity through...
Audio tagging, as a fundamental task in acoustic signal processing, has demonstrated significant advances and broad applications recent years. Spiking Neural Networks (SNNs), inspired by biological neural systems, exploit event-driven computing paradigms temporal information enabling superior energy efficiency. Despite the increasing adoption of SNNs, potential encoding mechanisms for audio tagging remains largely unexplored. This work presents pioneering investigation into strategies...
Due to the significant variances in their shape and size, it is a challenging task automatically segment gliomas. To improve performance of glioma segmentation tasks, this paper proposed multilevel attention pyramid scene parsing network (MLAPSPNet) that aggregates multiscale context features.First, T1 pre-contrast, T2-weighted fluid-attenuated inversion recovery (FLAIR) post-contrast sequences each slice are combined form input. Afterwards, image normalization augmentation techniques...
An improved multi-input multi-output filtered-X least mean square-based vibration control algorithm is proposed to solve the reference signal extraction problem for active system. The constructed by controller parameters and residual extracted directly from vibrating structure, which related external disturbance signal. Meanwhile, an FIR filter adopted online identification adding white noise output as input signal; identified model substituted into algorithm, secondary path realized. Thus,...
Abstract Background The activation degree of the orbitofrontal cortex (OFC) functional area in drug abusers is directly related to craving for drugs and tolerance punishment. Currently, among clinical research on rehabilitation, there has been little analysis OFC individuals abusing different types drugs, including heroin, methamphetamine, mixed drugs. Therefore, it becomes urgently necessary clinically investigate abuse so as explore effects human brain. Methods Based prefrontal...
Background: The adoption of convolutional neural networks (CNNs) for decoding electroencephalogram (EEG)-based motor imagery (MI) in brain-computer interfaces has significantly increased recently. effective extraction features is vital due to the variability among individuals and temporal states. Methods: This study introduces a novel network architecture, 3D-convolutional network-generative adversarial (3D-CNN-GAN), both within-session cross-session imagery. Initially, EEG signals were...
<abstract> <p>Most studies on drug addiction degree are made based statistical scales, addicts' account, and subjective judgement of rehabilitation doctors. No objective, quantified evaluation has been made. This paper uses devises the synchronous bimodal signal collection experimentation paradigm with electroencephalogram (EEG) forehead high-density near-infrared spectroscopy (NIRS) device. The addicts classified into mild, moderate severe groups reference to suggestions...
As a widely used brain-computer interface (BCI) paradigm, steady-state visually evoked potential (SSVEP)-based BCIs have the advantages of high information transfer rates, tolerance for artifacts, and robust performance across diverse users. However, incidence mental fatigue from prolonged, repetitive stimulation is critical issue SSVEP-based BCIs. Music often as convenient, non-invasive means relieving fatigue. This study investigates compensatory effect music on through introduction...
This correspondence focuses on the analysis and implementation of multi-input multi-output (MIMO) filtered-u least mean square (FULMS) algorithm for active vibration suppression a cantilever smart beam with surface bonded lead zirconate titanate patches. By analysing single-input single-output FULMS algorithm, MIMO controller structure is given. Then an control experimental platform established, optimal placement actuators sensors based maximal modal force rule. Simulation contrast most...
Control algorithm is one of the key elements for active vibration suppression space flexible structure based on smart materials. As least mean square (LMS) and recursive (RLS) are two fundamental algorithms adaptive feed-forward filter drawing wide attention, this paper focuses process analysis performance comparison finite impulse response (FIR) structure. The design related characteristic controller given as well realization theoretical analysis. Simulation done using Matlab 7.0 to verify...
After abusing drugs for long, drug users will experience deteriorated self-control cognitive ability, and poor emotional regulation. This paper designs a closed-loop virtual-reality (VR), motorimagery (MI) rehabilitation training system based on brain-computer interface (BCI) (MI-BCI+VR), aiming to enhance the self-control, cognition, regulation of addicts via personalized schemes. is composed two parts. In first part, data 45 (mild: 15; moderate: severe: 15) tested with electroencephalogram...
Unmanned surface vehicles (USVs) as unmanned intelligent devices can replace humans to perform missions more efficiently and safely in dangerous areas. However, due the complex navigation environment special mission requirements, USVs face many challenges emergency response for marine oil spill accidents. To solve these of ‘Sanchi’ tanker collision explosion accident, we designed deployed an USV real-time scanning water sampling shipwreck waters. Compared with previous USVs, our owned...
Objective: For heart transplantation, donor status needs to be evaluated during normothermic exsitu perfusion (ESHP). Left ventricular end-systolic elastance (Ees) measures the left contractile function, but its estimation requires occlusion of atrium line in ESHP, which may cause unnecessary damage heart. We present a novel method quantify E <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">es</sub> based on hemodynamic parameters obtained from...
Abstract This paper proposes a new stepping design method for class of nonlinear systems. Based on this technique, system is simplified greatly because many coupled items can be considered as zero items. applied to general Significantly, we have demonstrated technique in some chaotic systems and achieved good results. Simulation results the Genesio are provided illustrate effectiveness proposed scheme. Copyright © 2010 John Wiley Sons Asia Pte Ltd Chinese Automatic Control Society