An Improved Classification Architecture for Hand Gesture Electromyographic Data that Makes Use of Swarm Intelligence as a Feature Selection

Authors

  • Tejraj, Manvi Chopra, Shubhashish Goswami

DOI:

https://doi.org/10.17762/msea.v71i4.815

Abstract

Electromyography, often known as EMG, has become rather well-known for the contribution it has made to the overall architecture of the categorization of pain associated with a particular muscle or tissue. EMG is often employed both in the assessment of fitness professionals and in the course of the improvement of individuals who have physically difficult conditions. It is required to train a system using the EMG attribute set that is considered to be the most relevant in order to be able to identify EMG data in such a way that it is accurate with regard to any class. This research paper outlines an innovative design approach for enhancing the classification accuracy of the EMG signal as a whole (Rajeswari & Jagannath, 2017).

Downloads

Published

2022-09-16

How to Cite

Tejraj, Manvi Chopra, Shubhashish Goswami. (2022). An Improved Classification Architecture for Hand Gesture Electromyographic Data that Makes Use of Swarm Intelligence as a Feature Selection. Mathematical Statistician and Engineering Applications, 71(4), 2553–2566. https://doi.org/10.17762/msea.v71i4.815

Issue

Section

Articles