A novel EMG motion pattern classifier based on wavelet transform and nonlinearity analysis method

Jingdong Zhao; Li Jiang; Hegao Cai; Hong Liu; Gerd Hirzinger

doi:10.1109/ROBIO.2006.340150

A novel EMG motion pattern classifier based on wavelet transform and nonlinearity analysis method

Jingdong Zhao^*
, Li Jiang
, Hegao Cai
, Hong Liu
, Gerd Hirzinger

^*Corresponding author for this work

School of Mechatronics Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

12 Scopus citations

Abstract

A novel electromyographic (EMG) motion pattern classifier which combines VLR (variable learning rate) based neural network with wavelet transform and nonlinearity analysis method is presented in this paper. This motion pattern classifier can successfully identify the flexion and extension of the thumb, the index finger and the middle finger, by measuring the surface EMG signals through three electrodes mounted on the flexor digitorum profundus, flexor pollicis longus and extensor digitorum. Furthermore, via continuously controlling single finger's motion, the five-fingered underactuated prosthetic hand can achieve more prehensile postures such as power grasp, centralized grip, fingertip grasp, cylindrical grasp, etc. The experimental results show that the classifier has a great potential application to the control of bionic man-machine systems because of its high recognition capability.

Original language	English
Title of host publication	2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006
Pages	1494-1499
Number of pages	6
DOIs	https://doi.org/10.1109/ROBIO.2006.340150
State	Published - 2006
Event	2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006 - Kunming, China Duration: 17 Dec 2006 → 20 Dec 2006

Publication series

Name	2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006

Conference

Conference	2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006
Country/Territory	China
City	Kunming
Period	17/12/06 → 20/12/06

Keywords

EMG
Neural network
Prosthetic hand
Sample entropy
Wavelet transform

Access to Document

10.1109/ROBIO.2006.340150

Cite this

Zhao, J., Jiang, L., Cai, H., Liu, H., & Hirzinger, G. (2006). A novel EMG motion pattern classifier based on wavelet transform and nonlinearity analysis method. In 2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006 (pp. 1494-1499). Article 4142087 (2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006). https://doi.org/10.1109/ROBIO.2006.340150

@inproceedings{2bf5bf9dad9f46e0b4301b6cb84343b6,

title = "A novel EMG motion pattern classifier based on wavelet transform and nonlinearity analysis method",

abstract = "A novel electromyographic (EMG) motion pattern classifier which combines VLR (variable learning rate) based neural network with wavelet transform and nonlinearity analysis method is presented in this paper. This motion pattern classifier can successfully identify the flexion and extension of the thumb, the index finger and the middle finger, by measuring the surface EMG signals through three electrodes mounted on the flexor digitorum profundus, flexor pollicis longus and extensor digitorum. Furthermore, via continuously controlling single finger's motion, the five-fingered underactuated prosthetic hand can achieve more prehensile postures such as power grasp, centralized grip, fingertip grasp, cylindrical grasp, etc. The experimental results show that the classifier has a great potential application to the control of bionic man-machine systems because of its high recognition capability.",

keywords = "EMG, Neural network, Prosthetic hand, Sample entropy, Wavelet transform",

author = "Jingdong Zhao and Li Jiang and Hegao Cai and Hong Liu and Gerd Hirzinger",

year = "2006",

doi = "10.1109/ROBIO.2006.340150",

language = "英语",

isbn = "1424405718",

series = "2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006",

pages = "1494--1499",

booktitle = "2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006",

note = "2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006 ; Conference date: 17-12-2006 Through 20-12-2006",

}

Zhao, J , Jiang, L, Cai, H, Liu, H & Hirzinger, G 2006, A novel EMG motion pattern classifier based on wavelet transform and nonlinearity analysis method. in 2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006., 4142087, 2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006, pp. 1494-1499, 2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006, Kunming, China, 17/12/06. https://doi.org/10.1109/ROBIO.2006.340150

A novel EMG motion pattern classifier based on wavelet transform and nonlinearity analysis method. / Zhao, Jingdong ; Jiang, Li; Cai, Hegao et al.
2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006. 2006. p. 1494-1499 4142087 (2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A novel EMG motion pattern classifier based on wavelet transform and nonlinearity analysis method

AU - Zhao, Jingdong

AU - Jiang, Li

AU - Cai, Hegao

AU - Liu, Hong

AU - Hirzinger, Gerd

PY - 2006

Y1 - 2006

N2 - A novel electromyographic (EMG) motion pattern classifier which combines VLR (variable learning rate) based neural network with wavelet transform and nonlinearity analysis method is presented in this paper. This motion pattern classifier can successfully identify the flexion and extension of the thumb, the index finger and the middle finger, by measuring the surface EMG signals through three electrodes mounted on the flexor digitorum profundus, flexor pollicis longus and extensor digitorum. Furthermore, via continuously controlling single finger's motion, the five-fingered underactuated prosthetic hand can achieve more prehensile postures such as power grasp, centralized grip, fingertip grasp, cylindrical grasp, etc. The experimental results show that the classifier has a great potential application to the control of bionic man-machine systems because of its high recognition capability.

AB - A novel electromyographic (EMG) motion pattern classifier which combines VLR (variable learning rate) based neural network with wavelet transform and nonlinearity analysis method is presented in this paper. This motion pattern classifier can successfully identify the flexion and extension of the thumb, the index finger and the middle finger, by measuring the surface EMG signals through three electrodes mounted on the flexor digitorum profundus, flexor pollicis longus and extensor digitorum. Furthermore, via continuously controlling single finger's motion, the five-fingered underactuated prosthetic hand can achieve more prehensile postures such as power grasp, centralized grip, fingertip grasp, cylindrical grasp, etc. The experimental results show that the classifier has a great potential application to the control of bionic man-machine systems because of its high recognition capability.

KW - EMG

KW - Neural network

KW - Prosthetic hand

KW - Sample entropy

KW - Wavelet transform

UR - https://www.scopus.com/pages/publications/46249106550

U2 - 10.1109/ROBIO.2006.340150

DO - 10.1109/ROBIO.2006.340150

M3 - 会议稿件

AN - SCOPUS:46249106550

SN - 1424405718

SN - 9781424405718

T3 - 2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006

SP - 1494

EP - 1499

BT - 2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006

T2 - 2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006

Y2 - 17 December 2006 through 20 December 2006

ER -

A novel EMG motion pattern classifier based on wavelet transform and nonlinearity analysis method

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this