Decomposition of electromyographic signal by principal component analysjs of wavelet coefficjents

Rie Yamada, Junichi Ushiba, Yutaka Tomita, Yoshihisa Masakado

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

16 Citations (Scopus)

Abstract

Electromyographic (EMG) signals are the superposition of activities of multiple motor units (MUS). Therefore it is necessary to decompose the EMG signal in order to reveal the mechanisms pertaining to muscle and nerw control. Various techniques hare been devised with regards to EMG decomposition. A recently proposed method using wavelet analysis required manual selection of appropriate wavelet coefficients for action potential (AP) clustering. However the accuracy of this method depends heavily on the operators' ability to select suitable wavelet coefficients. To avoid this subjective ambiguilty we are proposing a new method ahich employs the principal component analysis on all wavelet coefficients to identify the distinguishable features of APs. The present method can decompose EMG automatically and unambiguously, from data input to clustering. Furthermore, our experimental results have shown that the decomposition accuracy was slightly higher than that of the conventional wavelet method.

Original languageEnglish
Title of host publicationAPBME 2003 - IEEE EMBS Asian-Pacific Conference on Biomedical Engineering 2003
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages118-119
Number of pages2
ISBN (Print)0780379438, 9780780379435
DOIs
Publication statusPublished - 2003
Externally publishedYes
EventIEEE EMBS Asian-Pacific Conference on Biomedical Engineering 2003, APBME 2003 - Kyoto-Osaka-Nara, Japan
Duration: 2003 Oct 202003 Oct 22

Other

OtherIEEE EMBS Asian-Pacific Conference on Biomedical Engineering 2003, APBME 2003
CountryJapan
CityKyoto-Osaka-Nara
Period03/10/2003/10/22

Fingerprint

Decomposition
Wavelet analysis
Principal component analysis
Muscle

Keywords

  • Decomposition
  • Electromyographic (EMG) signal
  • Principal component analysis
  • Wavelet coefficients

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Yamada, R., Ushiba, J., Tomita, Y., & Masakado, Y. (2003). Decomposition of electromyographic signal by principal component analysjs of wavelet coefficjents. In APBME 2003 - IEEE EMBS Asian-Pacific Conference on Biomedical Engineering 2003 (pp. 118-119). [1302612] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APBME.2003.1302612

Decomposition of electromyographic signal by principal component analysjs of wavelet coefficjents. / Yamada, Rie; Ushiba, Junichi; Tomita, Yutaka; Masakado, Yoshihisa.

APBME 2003 - IEEE EMBS Asian-Pacific Conference on Biomedical Engineering 2003. Institute of Electrical and Electronics Engineers Inc., 2003. p. 118-119 1302612.

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

Yamada, R, Ushiba, J, Tomita, Y & Masakado, Y 2003, Decomposition of electromyographic signal by principal component analysjs of wavelet coefficjents. in APBME 2003 - IEEE EMBS Asian-Pacific Conference on Biomedical Engineering 2003., 1302612, Institute of Electrical and Electronics Engineers Inc., pp. 118-119, IEEE EMBS Asian-Pacific Conference on Biomedical Engineering 2003, APBME 2003, Kyoto-Osaka-Nara, Japan, 03/10/20. https://doi.org/10.1109/APBME.2003.1302612
Yamada R, Ushiba J, Tomita Y, Masakado Y. Decomposition of electromyographic signal by principal component analysjs of wavelet coefficjents. In APBME 2003 - IEEE EMBS Asian-Pacific Conference on Biomedical Engineering 2003. Institute of Electrical and Electronics Engineers Inc. 2003. p. 118-119. 1302612 https://doi.org/10.1109/APBME.2003.1302612
Yamada, Rie ; Ushiba, Junichi ; Tomita, Yutaka ; Masakado, Yoshihisa. / Decomposition of electromyographic signal by principal component analysjs of wavelet coefficjents. APBME 2003 - IEEE EMBS Asian-Pacific Conference on Biomedical Engineering 2003. Institute of Electrical and Electronics Engineers Inc., 2003. pp. 118-119
@inproceedings{bb52a5e4dc634bafba498c166958708a,
title = "Decomposition of electromyographic signal by principal component analysjs of wavelet coefficjents",
abstract = "Electromyographic (EMG) signals are the superposition of activities of multiple motor units (MUS). Therefore it is necessary to decompose the EMG signal in order to reveal the mechanisms pertaining to muscle and nerw control. Various techniques hare been devised with regards to EMG decomposition. A recently proposed method using wavelet analysis required manual selection of appropriate wavelet coefficients for action potential (AP) clustering. However the accuracy of this method depends heavily on the operators' ability to select suitable wavelet coefficients. To avoid this subjective ambiguilty we are proposing a new method ahich employs the principal component analysis on all wavelet coefficients to identify the distinguishable features of APs. The present method can decompose EMG automatically and unambiguously, from data input to clustering. Furthermore, our experimental results have shown that the decomposition accuracy was slightly higher than that of the conventional wavelet method.",
keywords = "Decomposition, Electromyographic (EMG) signal, Principal component analysis, Wavelet coefficients",
author = "Rie Yamada and Junichi Ushiba and Yutaka Tomita and Yoshihisa Masakado",
year = "2003",
doi = "10.1109/APBME.2003.1302612",
language = "English",
isbn = "0780379438",
pages = "118--119",
booktitle = "APBME 2003 - IEEE EMBS Asian-Pacific Conference on Biomedical Engineering 2003",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Decomposition of electromyographic signal by principal component analysjs of wavelet coefficjents

AU - Yamada, Rie

AU - Ushiba, Junichi

AU - Tomita, Yutaka

AU - Masakado, Yoshihisa

PY - 2003

Y1 - 2003

N2 - Electromyographic (EMG) signals are the superposition of activities of multiple motor units (MUS). Therefore it is necessary to decompose the EMG signal in order to reveal the mechanisms pertaining to muscle and nerw control. Various techniques hare been devised with regards to EMG decomposition. A recently proposed method using wavelet analysis required manual selection of appropriate wavelet coefficients for action potential (AP) clustering. However the accuracy of this method depends heavily on the operators' ability to select suitable wavelet coefficients. To avoid this subjective ambiguilty we are proposing a new method ahich employs the principal component analysis on all wavelet coefficients to identify the distinguishable features of APs. The present method can decompose EMG automatically and unambiguously, from data input to clustering. Furthermore, our experimental results have shown that the decomposition accuracy was slightly higher than that of the conventional wavelet method.

AB - Electromyographic (EMG) signals are the superposition of activities of multiple motor units (MUS). Therefore it is necessary to decompose the EMG signal in order to reveal the mechanisms pertaining to muscle and nerw control. Various techniques hare been devised with regards to EMG decomposition. A recently proposed method using wavelet analysis required manual selection of appropriate wavelet coefficients for action potential (AP) clustering. However the accuracy of this method depends heavily on the operators' ability to select suitable wavelet coefficients. To avoid this subjective ambiguilty we are proposing a new method ahich employs the principal component analysis on all wavelet coefficients to identify the distinguishable features of APs. The present method can decompose EMG automatically and unambiguously, from data input to clustering. Furthermore, our experimental results have shown that the decomposition accuracy was slightly higher than that of the conventional wavelet method.

KW - Decomposition

KW - Electromyographic (EMG) signal

KW - Principal component analysis

KW - Wavelet coefficients

UR - http://www.scopus.com/inward/record.url?scp=33645233019&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33645233019&partnerID=8YFLogxK

U2 - 10.1109/APBME.2003.1302612

DO - 10.1109/APBME.2003.1302612

M3 - Conference contribution

AN - SCOPUS:33645233019

SN - 0780379438

SN - 9780780379435

SP - 118

EP - 119

BT - APBME 2003 - IEEE EMBS Asian-Pacific Conference on Biomedical Engineering 2003

PB - Institute of Electrical and Electronics Engineers Inc.

ER -