Abstract
Introduction: Electromyographic (EMG) activity monitoring constitutes the core of foundational research for the application of EMG signals in medical diagnostics, sports science, and human-machine interaction. However, the current research trend predominantly focuses on the recognition technologies of EMG signals, while the techniques for accurately detecting the onset and offset points of muscle activity-the change-point detection of EMG signals-have not received the necessary attention and thorough investigation. Methods: A novel method for EMG signal activity detection based on a variant version of the Teager-Kaiser energy operator (TKEO), namely the multi-resolution energy operator (MTEO), is proposed. Two strategies for constructing EMG activity monitors using MTEO are presented. One is a threshold-based detector (MEOTD) relying on signal baseline segment information, and the other is a detector mimicking the structure of a convolutional neural network (MEONND) without requiring prior knowledge of the signal. A semi-subjective evaluation model based on the Analytic Hierarchy Process (AHP) is used to evaluate the performance of the monitors on real EMG data. Results and discussion: The results show that the MTEO has stronger preprocessing ability for EMG signals, and that the MTEO-based monitors are more reliable and accurate. In particular, the MEONND can achieve both computational efficiency and accuracy simultaneously. The proposed method for EMG signal activity detection improves both detection quality and efficiency without increasing algorithm complexity. This method can be applied to various fields that involve EMG signal analysis, such as ergonomics, human-machine interaction, and biomedical engineering.