Classification of EMG Signals Between Healthy and Stroke Subjects in Upper Limb Muscle Activities

DOI

10.2991/978-94-6463-529-4_8How to use a DOI?

Keywords

Stroke; Electromyography; Feature extraction; Classification; Linear SVM

Abstract

Stroke is a quick loss of brain activity due to the disruption in the blood supply system. Among stroke survivors, losing hand function and finger spasticity are the main ailment. The purpose of this study is to investigate the electromyography (EMG) features in time domain and frequency domain during the shoulder complex and upper arm movement of stroke-affected and healthy muscles, and build a classification model using machine learning algorithm. An online database named “Mendeley” is used in this paper that contains EMG signals of twelve healthy subjects and thirteen stroke survivors from their six muscles (biceps brachii, triceps brachii, anterior deltoid, medial deltoid, posterior deltoid, infraspinatus) of the upper arm and shoulder complex. In this analysis, four time-domain features, namely mean absolute value, variance, root mean square, zero crossing, and three frequency-domain features, namely mean frequency, median frequency, and power spectrum ratio are extracted. A machine learning-based model is developed, which uses those extracted features to classify healthy and stroke groups. Hence, EMG features of upper limb muscles are trained by deploying linear support vector machine (SVM) classifier. Acceptable classification accuracy is noticed while generating the model. For the six muscles listed above, the achieved accuracy percentages are 81.2, 79.8, 77.8, 82.7, 79.4, and 80.6, respectively.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Pallab Das
AU  - Eashita Chowdhury
AU  - Vidit Gedam
AU  - Cheruvu Siva Kumar
AU  - Manjunatha Mahadevappa
PY  - 2024
DA  - 2024/10/04
TI  - Classification of EMG Signals Between Healthy and Stroke Subjects in Upper Limb Muscle Activities
BT  - Proceedings of the International Conference on Signal Processing and Computer Vision (SIPCOV-2023)
PB  - Atlantis Press
SP  - 76
EP  - 85
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-529-4_8
DO  - 10.2991/978-94-6463-529-4_8
ID  - Das2024
ER  -