SEMG Signal Processing using DWT for Neuromuscular Disorders Detection

Abstract

The Electromyogram (EMG) signals arising from muscle activities have become a useful tool for clinical diagnosis, rehabilitation medicine and sport medicine. These signals are essentially non-stationary may contain indicators of current category, or even warnings about impending events. Wavelet analysis is often very effective because it provides a simple approach for dealing with local aspects of a signal. It is shown that wavelet representation can be practical in detecting particular spikes in EMG signals and may be constructive for the detection of active segments. This manuscript presents a signal analysis based on the wavelet transform which
describes an approach for classifying Electromyography (EMG) signals via Matlab between three types of muscle diseases. Three diverse cases of EMG signals have been considered, filtered and compared with the Butterworth filter results. The present work describes the application of Wavelet Transform to provide a more accurate picture of the localized time-scale features indicative of disease abnormalities. The first step includes Processing and Filtering of EMG signal. The second step includes the comparison of the signal under DWT filter and Butterworth filter.