Related Experiment Video
Updated: Jun 5, 2026

Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography
Published on: January 24, 2025
Evolved pseudo-wavelet function to optimally decompose sEMG for automated classification of localized muscle fatigue
Mohamed R Al-Mulla1, Francisco Sepulveda, M Colley
1School of Computer Science and Electronic Engineering, University of Essex, Colchester, United Kingdom. mrhalm@essex.ac.uk
This study developed an automated algorithm for muscle fatigue detection using surface electromyography (sEMG). The novel approach improved fatigue classification accuracy, offering a new tool for sports science applications.
Area of Science:
- Biomedical Engineering
- Sports Science
- Signal Processing
Background:
- Muscle fatigue detection is crucial for optimizing athletic performance and preventing injuries.
- Automated methods using surface electromyography (sEMG) offer objective and efficient fatigue assessment.
- Existing wavelet-based methods may require further optimization for accurate fatigue classification.
Purpose of the Study:
- To develop and validate an algorithm for automated muscle fatigue detection in sports contexts.
- To optimize a pseudo-wavelet function using genetic algorithms for enhanced sEMG signal analysis.
- To improve the classification accuracy of muscle fatigue compared to existing wavelet functions.
Main Methods:
- Recorded sEMG signals from biceps during semi-isometric contractions until fatigue in ten subjects.
- Utilized a fuzzy classifier with elbow angle and standard deviation for signal labeling (Non-Fatigue/Fatigue).
- Employed a genetic algorithm to evolve a pseudo-wavelet function for fatigue detection in unseen sEMG data.
Main Results:
- The evolved pseudo-wavelet function demonstrated improved muscle fatigue classification by 7.31% to 13.15% over other wavelet functions.
- Achieved an average correct classification rate of 88.41% on unseen sEMG trials.
- The genetic algorithm successfully optimized the pseudo-wavelet for enhanced fatigue detection.
Conclusions:
- The developed algorithm with an evolved pseudo-wavelet function provides a more accurate method for automated muscle fatigue detection.
- This approach has significant potential for application in sports training, performance monitoring, and injury prevention.
- Further research can explore the application of this method to different muscle groups and exercise modalities.
Related Concept Videos
Classification of Skeletal Muscle Fibers
Slow-Twitch Muscle Fibers
Slow oxidative, muscle fibers appear red due to large numbers of capillaries and high levels of...
Muscle Stimulation Frequency
Wave summation
At low firing rates, motor neurons induce individual twitch contractions in muscle fibers. These twitches...
Classification of Skeletal Muscle Relaxants
Peripherally acting skeletal muscle relaxants interfere with the neurotransmission at the neuromuscular end plate to induce paralysis during...
Motor Unit Stimulation
The latent period of contraction marks the onset of excitation-contraction coupling, when the action potential propagates across the sarcolemma, preparing the muscle fibers for contraction. As the fibers enter the contraction phase, the...

