Quality investigation of sensor setups in ICA signal deconvolution: Application in gesture analysis based on SEMG bio-signal processing

Ganesh R. Naik, Dinesh K. Kumar, Hans Weghorn

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

Abstract

Surface electromyogram (sEMG) represents a ubiquitous tool for estimating muscle action potentials. For instance, during pre-determined voluntary movements, SEMG analysis can permit knowledge of the muscle activation sequence either in the lower or upper extremities. In general, sEMG sensing is feasible to evaluate muscle activity patterns for function, control and learning. For achieving this, multiple electrical sensors are essential for extracting intrinsic physiological and contextual information from the corresponding sEMG signals. The reason, why more than just one sEMG signal capture has to be used, is as follows: Due to signal propagation inside the human body in terms of an electrical conductor, there cannot be a one-to-one mapping of activities between muscle fibre groups and corresponding SEMG sensing electrodes. Each of such electrodes rather records a composition of many, and widely active-independent signals, and such kind of raw signal capture cannot be efficiently used for pattern matching due to its linear dependency. On the other hand, ICA provides the perfect answer of de-convolving a set of skin surface recordings into a vector (set) of independent muscle actions. Hence, there is need for a method that indicates the quality of the sensor set in sEMG recording. The purpose of this paper is to describe the use of source separation for sEMG based on Independent Component Analysis (ICA). We demonstrate how this can be used in practical sEMG experiments, when the number of recording channels for electrical muscle activities is varied. These results are funded on a wide set of experiments.

Original languageEnglish
Title of host publicationProceedings of Informatics 2009
Subtitle of host publicationPart of the IADIS Multi Conference on Computer Science and Information Systems 2009
PublisherIADIS Press
Pages43-50
Number of pages8
ISBN (Print)9789728924867
Publication statusPublished - 2009
Externally publishedYes
EventIADIS International Conference Informatics 2009, Part of the IADIS Multi Conference on Computer Science and Information Systems, MCCSIS 2009 - Algarve, Portugal
Duration: 17 Jun 200919 Jun 2009

Publication series

NameProceedings of the IADIS International Conference Informatics 2009, Part of the IADIS Multi Conference on Computer Science and Information Systems, MCCSIS 2009

Conference

ConferenceIADIS International Conference Informatics 2009, Part of the IADIS Multi Conference on Computer Science and Information Systems, MCCSIS 2009
CountryPortugal
CityAlgarve
Period17/06/0919/06/09

Keywords

  • Bio-sensors
  • Bio-signal analysis
  • Blind source separation (BSS)
  • Hand gesture sensing
  • Independent Component Analysis (ICA)
  • Surface electromyography (sEMG)

Fingerprint Dive into the research topics of 'Quality investigation of sensor setups in ICA signal deconvolution: Application in gesture analysis based on SEMG bio-signal processing'. Together they form a unique fingerprint.

Cite this