Effect of VMD decomposition of soleus muscle EMG in SVM classification

V. M. Akhil, Jobin Varghese, P. K. Rajendrakumar, K. S. Sivanandan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Electromyography (EMG) is widely used for diagnosis in the field of bio-medical research. The EMG signal from the soleus muscle is utilized in this study to understand the effect of variational mode decomposition (VMD) in signal classification. In this work forward and backward walking in even and uneven surfaces with inclinations of 0° and 10° were considered. Ten time domain features were extracted from both raw surface EMG signal, and VMD decomposed EMG signal. Scatter plot of features in all walking condition is analyzed to understand the variation within the scatter group. The features extracted from VMD based components were shown to perform better in accuracy during Support Vector Machines (SVM) classification than the raw signal.

Original languageEnglish
Title of host publication2019 2nd International Conference on Advanced Computational and Communication Paradigms, ICACCP 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538679890
DOIs
Publication statusPublished - 02-2019
Externally publishedYes
Event2nd International Conference on Advanced Computational and Communication Paradigms, ICACCP 2019 - Gangtok, Sikkim, India
Duration: 25-02-201828-02-2018

Publication series

Name2019 2nd International Conference on Advanced Computational and Communication Paradigms, ICACCP 2019

Conference

Conference2nd International Conference on Advanced Computational and Communication Paradigms, ICACCP 2019
CountryIndia
CityGangtok, Sikkim
Period25-02-1828-02-18

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Artificial Intelligence
  • Computer Networks and Communications
  • Instrumentation

Fingerprint Dive into the research topics of 'Effect of VMD decomposition of soleus muscle EMG in SVM classification'. Together they form a unique fingerprint.

Cite this