semg

Hand Gesture Recognition via sEMG signals with CNNs (Electrical and Computer Engineering - MSc Thesis)

The source code for the real-time hand gesture recognition algorithm based on Temporal Muscle Activation maps of multi-channel surface electromyography (sEMG) signals (ICASSP 2021)

Accompaniment code for 'Hilbert sEMG data scanning for hand gesture recognition based on Deep Learning' published in NCAA.

Source code for multiple parameter modelling of synthetic electromyography data.

A toolbox for offline muscle activity onset/offset detection in multi-channel EMG data

This repository contains sEMG Data of 13 subjects recorded with the Myo Armband.

Decomposition of sEMG signals via Blind Source Separation

My work during the research internship "Automotive Control using Surface Electromyography" at The University of Tokyo, Jun.-Sep. 2020

Biomedical signal (EEG/sEMG/ECG) completion/imputation using diffusion model. "A robust denoising diffusion framework for completing missing regions of multiple biomedical signals"

Bayesian self-adaptive pattern recognition for sEMG

Computationally-free personalization at test time for sEMG gesture classification. Fast (gpu/cpu) ninapro API.

Auto-learning search framework based on a weighted double Q-learning algorithm:"Integrated block-wise neural network with auto-learning search framework for finger gesture recognition using sEMG signals"

Public multichannel sEMG dataset for stroke rehabilitation research, including recordings from healthy participants and stroke patients for hand-gesture recognition, biomedical signal processing, machine learning, and rehabilitation robotics.

This project implements a machine learning model for real-time hand gesture recognition, enabling control of a powered wheelchair. It utilizes regression techniques to interpret hand gestures, allowing users to navigate the wheelchair effortlessly. Built with Matlab.

Python algorithm to assess muscle activation patterns during cyclical movements

Supplementary material for "WP-M2 Net: Wavelet-Perception Macro-Micro Dynamic 1D-CNN for Efficient Sequential Motion Recognition from Sparse sEMG" (IEEE JBHI, doi:10.1109/JBHI.2026.3734535). Code released upon publication.

Movement classification from sEMG signals across different subjects.

Hybrid EEG + sEMG motor imagery BCI for real-time Meta Quest 3 VR avatar arm control. EEGNet CNN + BiLSTM with Softmax Attention Fusion, ONNX/WebSocket inference, and Unity IK integration.

Cross-subject sEMG lower-limb movement classification on SIAT-LLMD (n=40): per-subject normalization beats learned domain adaptation. 85.8% LOSO macro-F1, externally replicated on ENABL3S.

Exploratory sEMG signal acquisition using the MyoWare 2.0 sensor. Proof of concept for peripheral nervous system gesture detection.