Papers
6
Total Citations
109
H-Index
6
About
Xiangxin Li is a leading researcher at the intersection of rehabilitation robotics, human-robot interaction, and neural signal processing. Their work focuses on decoding human movement intent from electromyogram (EMG) and electroencephalography (EEG) signals to enable intuitive control of prosthetic limbs and rehabilitation robots. Li’s major contributions include developing a postprocessing strategy that significantly improves the robustness of EMG-pattern recognition for prosthetic control (35 citations), and pioneering the use of deep learning—specifically stacked sparse autoencoders—for EEG-based robotic arm control (19 citations). They have also advanced the field by identifying upper-limb movements from muscle shape changes (19 citations) and creating spatio-temporal descriptors for more accurate limb-movement characterization (15 citations). Li’s work extends to IoT applications, where they have integrated EEG-based brain-computer interfaces with cloud computing using particle swarm optimization for efficient motor imagery classification (11 citations). Notably, their linearly extendible multi-artifact removal approach (10 citations) enhances EEG-based motor imagery decoding for rehabilitation robots. With over 100 total citations, Li’s innovative signal processing and machine learning techniques are paving the way for more reliable, dexterous, and accessible assistive technologies for individuals with limb loss or neuromuscular damage.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6