Wavelet based neuro-fuzzy classification for EMG control

Xiaowen Zhang; Yupu Yang; Xiaoming Xu; Ming Zhang

doi:10.1109/ICCCAS.2002.1178974

Wavelet based neuro-fuzzy classification for EMG control

Xiaowen Zhang, Yupu Yang, Xiaoming Xu, Ming Zhang

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

24 Citations (Scopus)

Abstract

High accuracy of multiple degrees of freedom in prosthetic control is hard to obtain because uncertainty exists between different movements. Neuro-fuzzy technology is suitable to deal with such problems. We adopt a wavelet based neuro-fuzzy approach to classify EMG signals for movement recognition in order to decrease classification error. EMG signals are analyzed by wavelet transform, and feature vectors are constructed by SVD transform from wavelet coefficients for further movement recognition. A neuro-fuzzy network is designed as classifier, and its initialization and training are also involved. Comparison results for this method and traditional ones are provided to show its efficiency. High recognition and reliability are achieved in preliminary experiments.

Original language	English
Title of host publication	2002 International Conference on Communications, Circuits and Systems and West Sino Exposition, ICCCAS 2002 - Proceedings
Publisher	IEEE
Pages	1087-1089
Number of pages	3
Volume	2
ISBN (Electronic)	0780375475, 9780780375475
DOIs	https://doi.org/10.1109/ICCCAS.2002.1178974
Publication status	Published - 1 Jan 2002
Event	1st International Conference on Communications, Circuits and Systems, ICCCAS 2002 - Tibet Hotel, Chengdu, China Duration: 29 Jun 2002 → 1 Jul 2002

Conference

Conference	1st International Conference on Communications, Circuits and Systems, ICCCAS 2002
Country/Territory	China
City	Chengdu
Period	29/06/02 → 1/07/02

Keywords

EMG Classification
Neuro-Fuzzy Network
Wavelet Transform

ASJC Scopus subject areas

Hardware and Architecture
Computer Networks and Communications
Control and Systems Engineering
Electrical and Electronic Engineering

More information

10.1109/ICCCAS.2002.1178974

Cite this

@inproceedings{a51ae03204db45518a06c7c0db45ac00,

title = "Wavelet based neuro-fuzzy classification for EMG control",

abstract = "High accuracy of multiple degrees of freedom in prosthetic control is hard to obtain because uncertainty exists between different movements. Neuro-fuzzy technology is suitable to deal with such problems. We adopt a wavelet based neuro-fuzzy approach to classify EMG signals for movement recognition in order to decrease classification error. EMG signals are analyzed by wavelet transform, and feature vectors are constructed by SVD transform from wavelet coefficients for further movement recognition. A neuro-fuzzy network is designed as classifier, and its initialization and training are also involved. Comparison results for this method and traditional ones are provided to show its efficiency. High recognition and reliability are achieved in preliminary experiments.",

keywords = "EMG Classification, Neuro-Fuzzy Network, Wavelet Transform",

author = "Xiaowen Zhang and Yupu Yang and Xiaoming Xu and Ming Zhang",

year = "2002",

month = jan,

day = "1",

doi = "10.1109/ICCCAS.2002.1178974",

language = "English",

volume = "2",

pages = "1087--1089",

booktitle = "2002 International Conference on Communications, Circuits and Systems and West Sino Exposition, ICCCAS 2002 - Proceedings",

publisher = "IEEE",

address = "United States",

note = "1st International Conference on Communications, Circuits and Systems, ICCCAS 2002 ; Conference date: 29-06-2002 Through 01-07-2002",

}

Zhang, X, Yang, Y, Xu, X & Zhang, M 2002, Wavelet based neuro-fuzzy classification for EMG control. in 2002 International Conference on Communications, Circuits and Systems and West Sino Exposition, ICCCAS 2002 - Proceedings. vol. 2, 1178974, IEEE, pp. 1087-1089, 1st International Conference on Communications, Circuits and Systems, ICCCAS 2002, Chengdu, China, 29/06/02. https://doi.org/10.1109/ICCCAS.2002.1178974

Wavelet based neuro-fuzzy classification for EMG control. / Zhang, Xiaowen; Yang, Yupu; Xu, Xiaoming et al.
2002 International Conference on Communications, Circuits and Systems and West Sino Exposition, ICCCAS 2002 - Proceedings. Vol. 2 IEEE, 2002. p. 1087-1089 1178974.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Wavelet based neuro-fuzzy classification for EMG control

AU - Zhang, Xiaowen

AU - Yang, Yupu

AU - Xu, Xiaoming

AU - Zhang, Ming

PY - 2002/1/1

Y1 - 2002/1/1

N2 - High accuracy of multiple degrees of freedom in prosthetic control is hard to obtain because uncertainty exists between different movements. Neuro-fuzzy technology is suitable to deal with such problems. We adopt a wavelet based neuro-fuzzy approach to classify EMG signals for movement recognition in order to decrease classification error. EMG signals are analyzed by wavelet transform, and feature vectors are constructed by SVD transform from wavelet coefficients for further movement recognition. A neuro-fuzzy network is designed as classifier, and its initialization and training are also involved. Comparison results for this method and traditional ones are provided to show its efficiency. High recognition and reliability are achieved in preliminary experiments.

AB - High accuracy of multiple degrees of freedom in prosthetic control is hard to obtain because uncertainty exists between different movements. Neuro-fuzzy technology is suitable to deal with such problems. We adopt a wavelet based neuro-fuzzy approach to classify EMG signals for movement recognition in order to decrease classification error. EMG signals are analyzed by wavelet transform, and feature vectors are constructed by SVD transform from wavelet coefficients for further movement recognition. A neuro-fuzzy network is designed as classifier, and its initialization and training are also involved. Comparison results for this method and traditional ones are provided to show its efficiency. High recognition and reliability are achieved in preliminary experiments.

KW - EMG Classification

KW - Neuro-Fuzzy Network

KW - Wavelet Transform

UR - http://www.scopus.com/inward/record.url?scp=84976351355&partnerID=8YFLogxK

U2 - 10.1109/ICCCAS.2002.1178974

DO - 10.1109/ICCCAS.2002.1178974

M3 - Conference article published in proceeding or book

VL - 2

SP - 1087

EP - 1089

BT - 2002 International Conference on Communications, Circuits and Systems and West Sino Exposition, ICCCAS 2002 - Proceedings

PB - IEEE

T2 - 1st International Conference on Communications, Circuits and Systems, ICCCAS 2002

Y2 - 29 June 2002 through 1 July 2002

ER -

Wavelet based neuro-fuzzy classification for EMG control

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this