Muscle Fatigue Detection Using sEMG Signals for Enhanced Prosthetic Control

This work explores muscle fatigue detection using surface electromyography (sEMG) signals from multiple muscle channels during prolonged load settings. Four vital temporal features, namely Root Mean Square, Waveform Length, Mean Absolute Value, and Zero Crossing, were examined across eight channels to determine the onset and progression of fatigue. The outcomes highlight the benefits of incorporating amplitude and variability-based features to provide robust real-time fatigue monitoring in Myoelectric Control Systems (MEC) and Human-Computer Interaction (HCI) applications.