Performance Analysis of Artificial Neural Network for Hand Movement Detection from EMG Signals

Abstract

This paper emphasizes on the hand movement recognition using artificial neural network (ANN). It shows the methodology that analyses and classifies the electromyography (EMG) signals using neural networks to control multifunction prostheses. The control of these prostheses can be made using myoelectric signals taken from surface electrodes. The linear neural network was employed in the EMG signal classification system as EMG signals contain many artifacts and noise, so linear classification helps to give the accurate classification results which can be further used for myoelectric controls. The experimental results show a promising performance in the classification of hand movements based on EMG pattern. The hand movements used were Flexion and Extension of wrist, Flexion and Extension of elbow, Closing and opening of hand, and the Supination and Pronation of forearm.