Classification of Hand Movements Based on EMG Signals using Topological Features

Hand movement classification based on Electromyo-graphy (EMG) signals has been extensively investigated in the past decades as a promising approach used for controlling upper prosthetics or robotics. Topological data analysis is relatively new and increasingly popular tool science that uses mathematical techniques from topology to analyze understand complex sets. This paper proposes method classifying hand movements EMG using topological features crafted with tools of TDA. The main findings this work are follows: (1) effective outperform other time domain tested experiments; (2) 0-th Betti numbers more than 1-st numbers; (3) amplitude stable powerful feature discussed paper. Additionally, curves were visualize patterns EMG.