Surface Electromyography Signal Acquisition and Classification Using Artificial Neural Networks (ANN)

Abstract

An electromyography (EMG) is an analytical tool used to record muscles' electrical activity, which produces an electrical signal proportional to the level of muscle activity. EMG signal plays a vital role in bio-mechatronic engineering for designing intelligent prostheses and other rehabilitation devices. Analysis of EMG signals with powerful and advanced methodologies is an essential requirement in EMG signal processing, as the EMG signal is a complex nonlinear, non-stationary signal in nature. It is required to use advanced signal processing techniques rather than conventional methods to exact EMG signals' features. Fourier transforms (FT) are not the most appropriate tool for analyzing non-stationary signals such as EMG. In this work, we have developed a system that can be useful for disabled persons to get a regular lifestyle using a functioning part of the body. Here, we studied the electrocution gram behavior of human body parts to feature extraction and trained the neural network to simulate the movements of mechanical actuators such as robotic arms. The wavelet transformation has been used to get high-quality feature extraction from electro cardio grapy and develops proper faltering methods for cardio systems' electrical signals. Finally, an artificial neural network (ANN) is used to classify the EMG signals through exacted features. Classification results are presented in this paper.