Neuromuscular disease detection based on feature extraction from time–frequency images of <scp>EMG</scp> signals employing robust hyperbolic Stockwell transform

In this paper, a novel technique for detection of healthy (H), myopathy, (M) and amyotrophic lateral sclerosis (ALS) electromyography (EMG) signals is proposed employing robust hyperbolic Stockwell transform (HST). HST an efficient signal processing to analyze any nonstationary in joint time–frequency (T–F) plane. However, major issue with the optimum selection Gaussian window parameters since resolution T–F plane depends on shape window. Considering aforesaid fact, article, genetic algorithm (GA) based optimized improved EMG analysis Several features were extracted from spectrum high statistical significance selected classification using several benchmark classifiers. It was observed that resulted better accuracy which indicates its potential clinical applications.