sEMG-based hand motion recognition system using RMSR and AR model

Surface electromyogram (sEMG) signals have been used to control multifunctional prosthetic hands. Researchers usually focused on the use of several channels with sEMG signals to identify more hand motions without limiting the number of sEMG sensors. However, the residual muscles of an amputee are limited. Therefore, the point of a successful recognition system is to decrease the channels of sEMG signals to classify more hand motions. To achieve this goal, we proposed a hand motion recognition system, in which three channels of sEMG signals can classify nine hand motions. In this recognition system, the time domain features, root mean square ratio (RMSR) and autoregressive (AR) model, were selected to extract the features of the sEMG signals as compared with the time-frequency domain features. Furthermore, the linear discriminant analysis (LDA) was adopted as the classifier. Consequently, the average accuracy rate of the presented system was 91.46%. Therefore, the proposed algorithms in this paper can be reasonably feasible for prosthetic hands.