Application of Surface Electromyography in Exercise Fatigue: A Review

Area of Science:

• Biomedical Engineering
• Sports Science
• Physiology

Background:

• Exercise fatigue is a common physiological state impacting performance and injury risk.
• Surface electromyography (sEMG) offers a practical method for assessing exercise fatigue.
• Advances in sEMG measurement and interpretation are crucial for understanding muscle activity.

Purpose of the Study:

• To review and consolidate knowledge on sEMG signal processing and feature extraction for exercise fatigue assessment.
• To explore the application of machine learning in classifying exercise fatigue using sEMG data.
• To introduce multisource information fusion techniques for enhanced fatigue detection.

Main Methods:

• Analysis of sEMG signal processing techniques relevant to exercise fatigue.
• Extraction and evaluation of key electromyographic features indicative of fatigue.
• Application of machine learning algorithms for sEMG-based fatigue classification.
• Integration of multisource information fusion for comprehensive fatigue assessment.

Main Results:

• Electromyographic features derived from sEMG signals are practical indicators of exercise fatigue.
• Machine learning significantly enhances the accuracy of exercise fatigue detection from sEMG.
• Multisource information fusion shows promise for more robust fatigue monitoring.

Conclusions:

• sEMG analysis, combined with machine learning, provides a powerful approach for exercise fatigue assessment.
• Future research should focus on advanced signal processing and fusion techniques for real-time fatigue detection.
• Improved fatigue detection can optimize training, enhance performance, and reduce injury risk in athletes.