Independent component analysis of EMG for posture detection: Sensitivity to variation of posture properties

Nadica Miljković, Goran Bijelić, Gonzalo A. Garcia, Mirjana B. Popović

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

We applied Agglomerative Hierarchical Clustering (AHC) technique on independent components of low back surface electromyography (sEMG) signals, in order to differ sitting and standing postures. Preliminary results from small group of healthy subjects, suggested that presented method might be used to distinguish between two postures in different conditions. Clustering accuracy varied from 60% to 70% due to variation of position properties, even when the muscle activity was very low: from 11% to 23% of Maximal Voluntary Contraction (MVC).

Original languageEnglish
Title of host publication2011 19th Telecommunications Forum, TELFOR 2011 - Proceedings of Papers
Pages47-50
Number of pages4
DOIs
Publication statusPublished - 2011
Event2011 19th Telecommunications Forum, TELFOR 2011 - Belgrade, Serbia
Duration: 22 Nov 201124 Nov 2011

Publication series

Name2011 19th Telecommunications Forum, TELFOR 2011 - Proceedings of Papers

Conference

Conference2011 19th Telecommunications Forum, TELFOR 2011
Country/TerritorySerbia
CityBelgrade
Period22/11/1124/11/11

Keywords

  • clustering
  • EMG
  • ICA
  • posture

Fingerprint

Dive into the research topics of 'Independent component analysis of EMG for posture detection: Sensitivity to variation of posture properties'. Together they form a unique fingerprint.

Cite this