COMPLEXITY ANALYSIS OF SURFACE ELECTROMYOGRAPHY SIGNALS UNDER FATIGUE USING HJORTH PARAMETERS AND BUBBLE ENTROPY

Abstract

This work aims to analyze the complexity of surface electromyography (sEMG) signals under muscle fatigue conditions using Hjorth parameters and bubble entropy (BE). Signals are recorded from the biceps brachii muscle of 25 healthy males during dynamic and isometric contraction exercises. These signals are filtered and segmented into 10 equal parts. The first and tenth segments are considered as nonfatigue and fatigue conditions, respectively. Activity, mobility, complexity, and BE features are extracted from both segments and classified using support vector machine (SVM), Naïve bayes (NB), k-nearest neighbor (kNN), and random forest (RF). The results indicate a reduction in signal complexity during fatigue. The parameter activity is found to increase under fatigue for both dynamic and isometric contractions with mean values of 0.35 and 0.22, respectively. It is observed that mobility, complexity, and BE are lowest during fatigue for both contractions. Maximum accuracy of 95.00% is achieved with the kNN and Hjorth parameters for dynamic signals. It is also found that the reduction of signal complexity during fatigue is more significant in dynamic contractions. This study confirms that the extracted features are suitable for analyzing the complex nature of sEMG signals. Hence, the proposed approach can be used for analyzing the complex characteristics of sEMG signals under various myoneural conditions.