Muscle Fatigue Estimation Model Based on EMG Improvement of Versatility Using Physical Features and Multiple Regression Analysis

Previously, to quantify muscle fatigue, the authors derived and defined “muscle fatigue time,” which quantifies muscle fatigue using frequency analysis based on the electromyogram, of the biceps brachii. A muscle fatigue estimation model was constructed based on the relationship between muscle fatigue time and muscle load for each participant. However, as model parameters were participant-dependent, versality is insufficient to universally apply the method to unknown participants. In this study, we aimed to select physical features that influence method parameters and estimate those parameters from selected physical features using multiple regression analysis. Percent body fat and biceps skinfold thickness were selected as physical features, and parameters that yielded data with an error rate of ~9% were determined. Furthermore, when the determined parameters were applied to a muscle fatigue estimation model, the muscle fatigue time was estimated with an error rate of ~27%. These results suggest that the variation in model accuracy between individuals can be eliminated using physical features. In addition, there were differences in the standard partial regression coefficients of the selected physical features obtained by multiple regression analysis. This suggests that accuracy may be improved by adopting a nonlinear equation for parameter determination.