sEMG신호기반 2단계 LDA분류기를 이용한 보행단계 인식

초록

In this paper, we propose a gait phase recognition method using sEMG for lower limb amputees. This method can be used to control powered artificial prosthetic. Existing method used the angle and pressure sensors to analyze gait phase whereas the proposed method uses two step LDA classifiers to recognize stance and swing phase. EMG signals are extracted from four body locations of thigh such as Recus femoris, Vastus lateralis, Vastus medialis, Semitendinosus. And then we calculate feature values of the time-domain(MAV, VAR, WL, RMS, SSI) and apply the stance LDA and swing LDA, respectively. Experimental result shows that the average accuracy of the proposed method is 25% less than that of ground method.