LAUSR

The research on muscular activity based human-machine interface (HMI) is of great significance, such as controlling prosthetic hand to improve the life quality of amputee patients. However, the HMI performance is limited by muscular fatigue due to frequent muscle contraction. To overcome the drawback, this paper presents a multi-modal sensing system that can collect surface electromyography (sEMG), near-infrared spectroscopy (NIRS) and mechanomyography (MMG) simultaneously. To evaluate the performance of the multi-modal signal acquisition system, incremental isometric voluntary contractions experiment is carried out. The experimental results show that the proposed system can reliably obtain three kinds of muscle contraction information from the perspective of electrophysiology, oxygen metabolism and low-frequency vibration of myofiber. Furthermore, muscle fatigue induced experiment imitating HMI usage is performed, and it convincingly demonstrates a significantly ( ${p} < 0.01$ ) improved classification accuracy (CA) by using multi-modal features. The CA is compensated by 3.6% ~ 22.9% in the presence of muscular fatigue. These results suggest that multi-modal sensing can improve the HMI performance and robustness. The outcomes of this study have great potential to promote the biomedical and clinical applications of human-machine interaction.