A Brief Review of Strategies Used for EMG Signal Classification

This article presents a brief review of machine learning/classification strategies for the classification of EMG signals in the context of Myoelectric controlled prosthesis. It focuses on certain parameters adopted for machine learning such as selecting the size of windows and frequency range adopted for different filters, the filters of three domains including time domain, frequency domain and time-frequency domain, and the classifiers commonly used and that of different statistical tests performed for evaluating the significant difference between the EMG and performance of features and classifiers. Also, the comparative analysis of different EMG related studies has been done in this article. The paper would contribute to selecting the parameters before evaluating the results using machine learning. The criteria for selection of the papers to present the review is set by looking at the frequently used features and classifiers that have been used by the researchers for EMG signals analysis in the past 2 decades.