Muscle fatigue identification and prediction in motion using wearable device with power and torque-based features

Abstract

Monitoring muscle fatigue is a critical area of research in both the fields of rehabilitation medicine and sports science. Despite its importance, practical measurement remains challenging due to constraints in equipment size and cost. This study leverages a commercially available, wearable high-resolution goniometer to capture joint angles during single-degree-of-freedom curling movements. From these data, we can deduce the torque and power of the biceps in the upper arm using an elbow musculoskeletal model. We proposed nine fatigue indicators, all of which showed significant correlations with the Root Mean Square (RMS) and Median Frequency (MDF) indicators derived from Electromyography (EMG) signals. Spectral clustering was utilized for the identification and classification of fatigue. Subsequently, we employed a K-Nearest Neighbors (KNN) model to predict muscular fatigue, achieving an impressive overall accuracy of 95%, an effective recall rate of 95%, an F1-score of 95%, and an Area Under the Curve (AUC) of 99%. This research presents an innovative and comprehensive approach to the identification and prediction of muscle fatigue.