Spatial Intensity Map of HDEMG Based Classification of Muscle Fatigue

Area of Science:

• Biomedical Engineering
• Neuroscience
• Sports Science

Background:

• Muscle fatigue assessment is crucial for preventing injuries and optimizing training.
• High-Density Electromyography (HDEMG) offers a detailed spatial view of muscle electrical activity.
• Distinguishing between non-fatigue and fatigue states is essential for performance monitoring.

Purpose of the Study:

• To investigate the use of spatial maps derived from HDEMG signals for identifying muscle fatigue.
• To evaluate the effectiveness of a random forest classifier in differentiating fatigue conditions.
• To explore the potential of spatial analysis of HDEMG for real-life fatigue assessment.

Main Methods:

• Subjects performed plantar flexion at 40% maximum voluntary contraction until fatigue.
• HDEMG signals were recorded from the tibialis anterior muscle.
• Monopolar and bipolar spatial intensity maps were extracted and analyzed using a random forest classifier.

Main Results:

• The random forest classifier successfully distinguished between non-fatigue and fatigue conditions.
• Optimal accuracy of 83.3% was achieved using selected electrodes from the differential intensity map.
• The classifier performed best with 17 trees in its configuration.

Conclusions:

• Spatial analysis of HDEMG signals provides a viable method for detecting muscle fatigue.
• The developed approach demonstrates potential for application in real-world scenarios, such as sports and rehabilitation.
• Further research can refine this technique for more robust and widespread use in fatigue monitoring.