A MATLAB-Based Interactive Environment for EMG Signal Decomposition Utilizing Matched Template Filters

Abstract

An interactive software package for analyzing and decomposing electromyographic (EMG) signals is designed, constructed, and implemented using the MATLAB high-level programming language and its interactive environment. EMG signal analysis in the form of signal decomposition into their constituent motor unit potential trains (MUPTs) is considered as a classification task. Matched template filter methods have been employed for the classification of motor unit potentials (MUPs) in which the assignment criterion used for MUPs is based on a combination of MUP shapes and motor unit firing pattern information. The developed software package consists of several graphical user interfaces used to detect individual MUP waveforms from raw EMG signals, extract relevant features, and classify MUPs into MUPTs using matched template filter classifiers. The proposed software package is useful for enhancing the analysis quality and providing a systematic approach to the EMG signal decomposition process. It also worked as a very helpful environment for testing and evaluating algorithms developed for EMG signal decomposition research.