- Muscle activation and electromyography studies
- Stroke Rehabilitation and Recovery
- Prosthetics and Rehabilitation Robotics
- Advanced Neural Network Applications
- Integrated Circuits and Semiconductor Failure Analysis
- EEG and Brain-Computer Interfaces
- Physical Unclonable Functions (PUFs) and Hardware Security
- Neuroscience and Neural Engineering
- Robotics and Sensor-Based Localization
- UAV Applications and Optimization
- Advanced Decision-Making Techniques
- Simulation and Modeling Applications
- Advanced Algorithms and Applications
- Remote Sensing and Land Use
- Autonomous Vehicle Technology and Safety
- Robotic Path Planning Algorithms
- Online Learning and Analytics
- Evaluation Methods in Various Fields
- Gait Recognition and Analysis
- Advanced Memory and Neural Computing
- Image and Signal Denoising Methods
- ECG Monitoring and Analysis
- Safety and Risk Management
- Advanced Image Fusion Techniques
- Balance, Gait, and Falls Prevention
Beijing Institute of Technology
2020-2023
Sun Yat-sen University
2018-2022
Texas Tech University
2021-2022
Sun Yat-sen University Cancer Center
2021
Jinan Maternity And Care Hospital
2012
Wuhan University of Technology
2006
Various rehabilitation robots have been employed to recover the motor function of stroke patients. To improve effect rehabilitation, should promote patient participation and provide compliant assistance. This paper proposes an adaptive admittance control scheme (AACS) consisting filter, inner position controller, electromyography (EMG)-driven musculoskeletal model (EDMM). The filter generates subject's intended motion according joint torque estimated by EDMM. controller tracks motion, its...
By revisiting, improving, and extending recent neural-network based modeling attacks on XOR Arbiter PUFs from the literature, we show that PUFs, (XOR) Feed-Forward Interpose can be attacked faster, up to larger security parameters, with an order of magnitude fewer challenge-response pairs than previously known both in simulation silicon data. To support our claim, discuss differences similarities recently proposed offer a fair comparison performance these by implementing all them using...
The synchronization of output torque is an important issue during human-robot interaction. Since the may be affected by delay between human's voluntary and robot's assistive when a sensor applied to detect human intention, electromyography (EMG)-based admittance controller (EAC) was proposed improve compared with that achieved use torque-sensing-based (TAC). Simulations experiments were conducted investigate performance EAC TAC. simulation results indicated exoskeleton significantly degraded...
Control schemes based on electromyography (EMG) have demonstrated their superiority in human-robot cooperation due to the fact that motion intention can be well estimated by EMG signals. However, there are several limitations noisy nature of signals and inaccuracy EMG-force/torque estimation, which might deteriorate stability movement. To improve movement stability, an EMG-based admittance control scheme (EACS) was proposed, comprised EMG-driven musculoskeletal model (EDMM), filter inner...
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Objective:</i> Although existing assist-as-needed (AAN) controllers have been designed to adapt the robotic assistance patients' movement performance, they ignore patient's active participation. This study proposed a voluntary AAN (VAAN) controller considering both performance and participation for an ankle rehabilitation robot. xmlns:xlink="http://www.w3.org/1999/xlink">Methods:</i> According...
Distance learning has dramatically increased in recent years because of advanced technology. In addition, numerous universities had to offer courses online mode 2020 and 2021 the COVID-19 pandemic. However, there are more challenges distance than traditional method (e.g., feedback interaction). Recently, researchers started using simple EEG headsets identify confused students during based on machine approaches. they faced unpleasant accuracy algorithms or nondeep neural networks. this paper,...
Functional electrical stimulation (FES) is important in gait rehabilitation for patients with dropfoot. Since there are time-varying velocities during FES-assisted walking, it difficult to achieve a good movement performance walking. To account the walking velocities, seven poststroke subjects were recruited and fuzzy logic control linear model applied enable intensity- duration-adaptive (IDAS) In this study, of IDAS was evaluated using kinematic data, compared under no (NS), triggered by...
In order to expand the application fields of micro-UAVs, ability land mark recognition and autonomous landing is one key technologies for UAVs flighting in complex environment. For achieving more robust precise relative pose estimation, we propose apply an ellipse feature-based estimation method instead QR code features. Considering poor calculating on-board, algorithms based on deep learning are difficult be used micro-UAVs. Hence, put forward a new strategy target by taking advantage...
Internet of Things (IoT) have broad and deep penetration into our society, many them are resource-constrained, calling for lightweight security protocols. Physical unclonable functions (PUFs) leverage physical variations circuits to produce responses unique individual devices, hence not reproducible even by their manufacturers. Implementable with simplistic operable low energy, PUFs promising candidates as primitives resource-constrained IoT devices. Arbiter PUF (APUF) its variants in...
Driver classification is used recently for vehicle anti-burglary and fake driver accounts based on driving behavior. Anti-burglary a challenging problem as it leans external devices to defend against theft. Several researchers analyzed the behavior identify drivers, but they faced several challenges produce stable model cold start medium-long sequences. In addition, some approaches had an unpleasant performance when action space increased (> 2 drivers). this paper, we propose novel approach...
For industrial robot manipulator system, PD control theory is extensively used in the dynamic characteristics controlling. A robust controller introduced to optimize stability and convergence of traditional avoid excess initial driving torque for two-link system. By co-simulation on ADAMS Matlab/ Simulink, paper designs a under given upper bound disturbance completes track trial. Through result comparison analysis, superiority verified.