Feature extraction for evaluation of Muscular Atrophy

Electromyography (EMG) signal is electrical manifestation of neuromuscular activation by which physiological processes are accessible. The bio-mechanical phenomenon induces the muscle to generate force and produce movement and help to interact with the world. Classification of EMGs is a big challenge due to its non stationary nature. Various features like root mean square, spectrogram, kurtosis, entropy and power are extracted from EMG signals of isometric contraction of two different abnormalities namely ALS (Amyotrophic Lateral Sclerosis) which is coming under Neuropathy and Myopathy. The classification accuracy is found to be satisfactory to design EMG signal classifier for various applications like knowledge-based expert system design and disease diagnosis.