ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

REVIEW OF EMG SIGNAL CLASSIFICATION APPROACHES BASED ON VARIOUS FEATURE DOMAINS

Journal: MATTER: International Journal of Science and Technology (Vol.6, No. 3)

Publication Date:

Authors : ; ;

Page : 123-143

Keywords : EMG; Muscular; Feature; Pattern; Signal Classification;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

Electromyography (EMG) is a widely used analytical practice that relays the health-status of the muscles or the nerve cells by monitoring their electrical impulses. However, it inherits the poor signal-to-noise ratio in addition to occasional signal distortions that significantly challenges the efficacy of this technique. Therefore, since the advent of this technology, numerous researchers have dedicated their study to improve the signal quality by reducing inherent noise in addition to offering its automated classification. In the present work, the authors have presented an overview of various existing researches in the field of electro-myographic signals classification involving various state-of-art techniques. A comprehensive survey has been provided while discussing the EMG signal analytic techniques involving different domains along with their performance. In the process, research not published before 2010 in various authenticated sources, such as Elsevier, PubMed, Springer, IEEE, and other articles and reports that are under the coverage of Web of Science and Google Scholar were analyzed. The review examined the suitability of various existing techniques to empower the healthcare sector based on the interpretation of EMG signals. Detailed comparison of nature-inspired approaches for segmentation is also involved while comparing their demonstrated accuracies. Further, the time domain is also found to be more preferred as compared to the frequency domain for signal evaluation. The authors tried to provide an excellent understanding and evolution of the existing EMG signal classification techniques to guide for more influential, efficient, and flexible applications in the future.

Last modified: 2021-01-22 15:43:48