Premium
Estimation of Optimal Measurement Position of Human Forearm EMG Signal by Discriminant Analysis Based on Wilks’ Lambda
Author(s) -
Kiso Atsushi,
Taniguchi Yu,
Seki Hirokazu
Publication year - 2013
Publication title -
electronics and communications in japan
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.131
H-Index - 13
eISSN - 1942-9541
pISSN - 1942-9533
DOI - 10.1002/ecj.11465
Subject(s) - linear discriminant analysis , position (finance) , lambda , discriminant , pattern recognition (psychology) , artificial intelligence , forearm , signal (programming language) , motion (physics) , computer science , mathematics , speech recognition , physics , anatomy , medicine , programming language , finance , optics , economics
SUMMARY This paper describes the estimation of the optimal measurement position by discriminant analysis based on Wilks’ lambda for myoelectric hand control. In previous studies, for motion discrimination, the myoelectric signals were measured at the same positions. However, the optimal measurement positions of the myoelectric signals for motion discrimination differ depending on the remaining muscles of amputees. Therefore, the purpose of this study is to estimate the optimal and fewer measurement positions for precise motion discrimination of a human forearm. This study proposes a method for estimating the optimal measurement positions by discriminant analysis based on Wilks’ lambda, using the myoelectric signals measured at multiple positions. The results of some experiments on the myoelectric hand simulator show the effectiveness of the proposed optimal measurement position estimation method. © 2013 Wiley Periodicals, Inc. Electron Comm Jpn, 96(8): 32–40, 2013; Published online in Wiley Online Library ( wileyonlinelibrary.com ). DOI 10.1002/ecj.11465