Use of sEMG in identification of low level muscle activities : features based on ICA and Fractal dimension

Ganesh R. Naik; Dinesh K. Kumar; Sridhar Arjunan

doi:10.1109/IEMBS.2009.5332489

Use of sEMG in identification of low level muscle activities : features based on ICA and Fractal dimension

Ganesh R. Naik
, Dinesh K. Kumar
, Sridhar Arjunan

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

11 Citations (Scopus)

Abstract

This paper has experimentally verified and compared features of sEMG (Surface Electromyogram) such as ICA (Independent Component Analysis) and Fractal Dimension (FD) for identification of low level forearm muscle activities. The fractal dimension was used as a feature as reported in the literature. The normalized feature values were used as training and testing vectors for an Artificial neural network (ANN), in order to reduce inter-experimental variations. The identification accuracy using FD of four channels sEMG was 58%, and increased to 96% when the signals are separated to their independent components using ICA.

Original language	English
Title of host publication	Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine (EMBC 2009): Minneapolis, Minnesota, USA, 3-6 September 2009
Publisher	IEEE
Pages	364-367
Number of pages	4
ISBN (Print)	9781424432967
DOIs	https://doi.org/10.1109/IEMBS.2009.5332489
Publication status	Published - 2009
Event	IEEE Engineering in Medicine and Biology Society. Annual Conference - Duration: 30 Apr 2015 → …

Conference

Conference	IEEE Engineering in Medicine and Biology Society. Annual Conference
Period	30/04/15 → …

Keywords

electromyography
fractals
human information processing
independent component analysis
multivariant analysis
muscles
neural networks (computer science)

Access to Document

10.1109/IEMBS.2009.5332489

Cite this

Naik, G. R., Kumar, D. K., & Arjunan, S. (2009). Use of sEMG in identification of low level muscle activities : features based on ICA and Fractal dimension. In Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine (EMBC 2009): Minneapolis, Minnesota, USA, 3-6 September 2009 (pp. 364-367). IEEE. https://doi.org/10.1109/IEMBS.2009.5332489

Naik, Ganesh R. ; Kumar, Dinesh K. ; Arjunan, Sridhar. / Use of sEMG in identification of low level muscle activities : features based on ICA and Fractal dimension. Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine (EMBC 2009): Minneapolis, Minnesota, USA, 3-6 September 2009. IEEE, 2009. pp. 364-367

@inproceedings{523a3c1dfdfd4d6ba0d9e9fc23a4431e,

title = "Use of sEMG in identification of low level muscle activities : features based on ICA and Fractal dimension",

abstract = "This paper has experimentally verified and compared features of sEMG (Surface Electromyogram) such as ICA (Independent Component Analysis) and Fractal Dimension (FD) for identification of low level forearm muscle activities. The fractal dimension was used as a feature as reported in the literature. The normalized feature values were used as training and testing vectors for an Artificial neural network (ANN), in order to reduce inter-experimental variations. The identification accuracy using FD of four channels sEMG was 58\%, and increased to 96\% when the signals are separated to their independent components using ICA.",

keywords = "electromyography, fractals, human information processing, independent component analysis, multivariant analysis, muscles, neural networks (computer science)",

author = "Naik, \{Ganesh R.\} and Kumar, \{Dinesh K.\} and Sridhar Arjunan",

year = "2009",

doi = "10.1109/IEMBS.2009.5332489",

language = "English",

isbn = "9781424432967",

pages = "364--367",

booktitle = "Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine (EMBC 2009): Minneapolis, Minnesota, USA, 3-6 September 2009",

publisher = "IEEE",

note = "IEEE Engineering in Medicine and Biology Society. Annual Conference ; Conference date: 30-04-2015",

}

Naik, GR, Kumar, DK & Arjunan, S 2009, Use of sEMG in identification of low level muscle activities : features based on ICA and Fractal dimension. in Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine (EMBC 2009): Minneapolis, Minnesota, USA, 3-6 September 2009. IEEE, pp. 364-367, IEEE Engineering in Medicine and Biology Society. Annual Conference, 30/04/15. https://doi.org/10.1109/IEMBS.2009.5332489

Use of sEMG in identification of low level muscle activities : features based on ICA and Fractal dimension. / Naik, Ganesh R.; Kumar, Dinesh K.; Arjunan, Sridhar.
Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine (EMBC 2009): Minneapolis, Minnesota, USA, 3-6 September 2009. IEEE, 2009. p. 364-367.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Use of sEMG in identification of low level muscle activities : features based on ICA and Fractal dimension

AU - Naik, Ganesh R.

AU - Kumar, Dinesh K.

AU - Arjunan, Sridhar

PY - 2009

Y1 - 2009

N2 - This paper has experimentally verified and compared features of sEMG (Surface Electromyogram) such as ICA (Independent Component Analysis) and Fractal Dimension (FD) for identification of low level forearm muscle activities. The fractal dimension was used as a feature as reported in the literature. The normalized feature values were used as training and testing vectors for an Artificial neural network (ANN), in order to reduce inter-experimental variations. The identification accuracy using FD of four channels sEMG was 58%, and increased to 96% when the signals are separated to their independent components using ICA.

AB - This paper has experimentally verified and compared features of sEMG (Surface Electromyogram) such as ICA (Independent Component Analysis) and Fractal Dimension (FD) for identification of low level forearm muscle activities. The fractal dimension was used as a feature as reported in the literature. The normalized feature values were used as training and testing vectors for an Artificial neural network (ANN), in order to reduce inter-experimental variations. The identification accuracy using FD of four channels sEMG was 58%, and increased to 96% when the signals are separated to their independent components using ICA.

KW - electromyography

KW - fractals

KW - human information processing

KW - independent component analysis

KW - multivariant analysis

KW - muscles

KW - neural networks (computer science)

UR - http://handle.westernsydney.edu.au:8081/1959.7/uws:44536

U2 - 10.1109/IEMBS.2009.5332489

DO - 10.1109/IEMBS.2009.5332489

M3 - Conference Paper

SN - 9781424432967

SP - 364

EP - 367

BT - Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine (EMBC 2009): Minneapolis, Minnesota, USA, 3-6 September 2009

PB - IEEE

T2 - IEEE Engineering in Medicine and Biology Society. Annual Conference

Y2 - 30 April 2015

ER -

Naik GR, Kumar DK, Arjunan S. Use of sEMG in identification of low level muscle activities : features based on ICA and Fractal dimension. In Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine (EMBC 2009): Minneapolis, Minnesota, USA, 3-6 September 2009. IEEE. 2009. p. 364-367 doi: 10.1109/IEMBS.2009.5332489

Use of sEMG in identification of low level muscle activities : features based on ICA and Fractal dimension

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this