Presentation 2012-03-09
Human Interface Using EMG-Based Motion Recognition Method
Masahiro YOSHIKAWA, Yoshio MATSUMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we report an EMG-based motion recognition method using support vector machines (SVMs). This method uses EMG signal patterns which consist of integrated EMG signals and cepstral coefficients to recognize hand motions. To verify the effectiveness of the method, experiments to recognize seven hand motions with eight subjects were performed. The experimental results showed that the average recognition rate across eight subjects was 95.8%. The method could adapt subject's EMG patterns in about 30 seconds. By using a myoelectric interface based on the method, a three-dimensional computer graphics robotic hand could be controlled as intended.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) EMG / Motion Recognition / Robotic hand / Support Vector Machine / prosthetic hand
Paper # WIT2011-80
Date of Issue

Conference Information
Committee WIT
Conference Date 2012/3/2(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Well-being Information Technology(WIT)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Human Interface Using EMG-Based Motion Recognition Method
Sub Title (in English)
Keyword(1) EMG
Keyword(2) Motion Recognition
Keyword(3) Robotic hand
Keyword(4) Support Vector Machine
Keyword(5) prosthetic hand
1st Author's Name Masahiro YOSHIKAWA
1st Author's Affiliation Intelligent Systems Research Institute, AIST()
2nd Author's Name Yoshio MATSUMOTO
2nd Author's Affiliation Intelligent Systems Research Institute, AIST
Date 2012-03-09
Paper # WIT2011-80
Volume (vol) vol.111
Number (no) 472
Page pp.pp.-
#Pages 4
Date of Issue