Artificial elbow joint classification using upper arm based on surface-EMG signal

Abstract

This paper proposes a method of elbow joint motions recognition using surface electro-myography (sEMG) signal for disable people with below-elbow amputation. It solves the situation that forearm without muscle cannot control forearm pronation. The pre-processing system processes sEMG signal to remove noise by soft threshold method, then denoising sEMG signal is sent to artificial neural network which trains features to recognize motions. The probability of this method activating 4 motions is 91.78% that was demonstrated by experimental results of recognition motions.