Feature Extraction of Chaotic Characteristics of sEMG

Muscle fatigue can damage health, and the surface electromyography (sEMG) signals can reflect the real-time state of muscles. Extracting features from the sEMG signals and analyzing the trend of feature changes can provide early warning of muscle fatigue. In this paper, the phase space reconstruction of the sEMG is performed to transform the one-dimensional sequence into a two-dimensional spatial signal to analyze the chaotic characteristics of the sEMG. The geometric features of two-dimensional phase space are extracted and the changing trend of geometric features in the process of muscle fatigue is analyzed for muscle fatigue detection. The experimental results show that with the deepening of muscle fatigue, the motion range of surface EMG signals in two-dimensional phase space is increasing, and the trajectory is more complex. Geometric features tend to increase with the deepening of muscle fatigue, which can effectively distinguish the state of muscle fatigue.