Comparing EMG Continuous Movement Decoding With Joints Unconstrained and Constrained

Abstract

Electromyography (EMG) signals have been employed for continuous movement decoding in recent years. However, several studies demonstrated that due to physiological factors, the EMG signals of amputees were poorer with respect to that of the able-bodied subjects. Our previous study demonstrated that the joint movements affected the performance of EMG pattern recognition. In this study, we aimed to investigate whether the movement of metacarpophalangeal (MCP) and wrist joints have effects on the performance of EMG continuous movement decoding. Six able-bodied subjects performed MCP and wrist flexion/extension simultaneously or independently with the MCP and wrist joints unconstrained (MWJU) and constrained (MWJC), while the EMG signals of the four forearm muscles were recorded. The musculoskeletal model was used to predict the joint angles from EMG signals. The performance of continuous movement decoding was quantified by the Pearson's correlation coefficient (r) and the normalized root mean square error (NRMSE) between the measured and predicted joint angles. The results showed that the MWJC significantly reduced the prediction performance of continuous movement for all subjects when compared to the MWJU. The average r values of the wrist and MCP flexion/extension decreased from 0.89 to 0.82 and 0.86 to 0.52, respectively. The average NRMSE values of the wrist and MCP flexion/extension increased from 0.18 to 0.21 and 0.22 to 0.31, respectively. The results demonstrated that the movements of the MCP and the wrist joints have a significant effect on the continuous movement decoding. Our study revealed a potential factor inducing the poor performance of continuous movement decoding in amputees.