Related Experiment Video
Updated: Jul 10, 2026
08:15
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
Published on: March 28, 2025
A novel approach to recognize hand movements via sEMG patterns
1Department of Electrical Engineering, Sharif University of Technology, Biomedical Engineering and Robotic Laboratories, Tehran, Iran. khezri@ee.sharif.edu
Summary
This study introduces an improved pattern recognition system for prosthetic arms using surface electromyogram (sEMG) signals. Combining signal features and a fuzzy classifier enhances prosthetic hand movement control and accuracy.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Rehabilitation Technology
Background:
- Surface electromyogram (sEMG) signals reflect muscle contractions and are used in pattern recognition for prosthetic control.
- Current prosthetic hands have limited functionality (e.g., simple open/close), hindering efficacy compared to natural hands.
Purpose of the Study:
- To propose a novel approach for enhancing sEMG pattern recognition systems for prosthetic arm movement.
- To improve the accuracy and capabilities of prosthetic arm movements.
Main Methods:
- Investigated time domain, time-frequency domain, and combined features of sEMG signals.
- Utilized artificial neural networks (ANN) and fuzzy inference systems (FIS) as intelligent classifiers.
- Applied principle component analysis (PCA) for dimensionality reduction.
Main Results:
- Compound sEMG features combined with PCA demonstrated effective dimensionality reduction.
- The fuzzy inference system (FIS) classifier achieved superior performance in sEMG pattern recognition.
Conclusions:
- The proposed novel approach using compound features and PCA, coupled with an FIS classifier, significantly improves sEMG pattern recognition for prosthetic applications.
- This advancement offers potential for more sophisticated and accurate prosthetic arm control.
