Advanced

EMG pattern recognition using decomposition techniques for constructing multiclass classifiers

Huang, Huaiqi; Li, Tao; Bruschini, Claudio; Enz, Christian; Koch, Volker M.; Justiz, Jorn and Antfolk, Christian LU (2016) 6th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016 In 2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016 p.1296-1301
Abstract

To improve the dexterity of multi-functional myoelectric prosthetic hand, more accurate hand gesture recognition based on surface electromyographic (sEMG) signal is needed. This paper evaluates two types of time-domain EMG features, one independent feature and one combined feature including four features. The selected features from eight subjects with 13 finger movements were tested with four decomposed multi-class support vector machines (SVM), four decomposed linear discriminant analyses (LDA) and a multi-class LDA. The classification accuracy, training, and classification time are compared. The results have shown that the combined features decrease error rate, and binary tree based decomposition multiclass classifiers yield the... (More)

To improve the dexterity of multi-functional myoelectric prosthetic hand, more accurate hand gesture recognition based on surface electromyographic (sEMG) signal is needed. This paper evaluates two types of time-domain EMG features, one independent feature and one combined feature including four features. The selected features from eight subjects with 13 finger movements were tested with four decomposed multi-class support vector machines (SVM), four decomposed linear discriminant analyses (LDA) and a multi-class LDA. The classification accuracy, training, and classification time are compared. The results have shown that the combined features decrease error rate, and binary tree based decomposition multiclass classifiers yield the highest classification success rate (88.2%) with relatively low training and classification time.

(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016
pages
6 pages
publisher
IEEE Computer Society
conference name
6th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016
external identifiers
  • scopus:84983446432
ISBN
9781509032877
DOI
10.1109/BIOROB.2016.7523810
language
English
LU publication?
yes
id
779b71ae-65a6-46ec-a11f-548ec8086899
date added to LUP
2016-12-22 14:47:45
date last changed
2017-04-09 04:53:06
@inproceedings{779b71ae-65a6-46ec-a11f-548ec8086899,
  abstract     = {<p>To improve the dexterity of multi-functional myoelectric prosthetic hand, more accurate hand gesture recognition based on surface electromyographic (sEMG) signal is needed. This paper evaluates two types of time-domain EMG features, one independent feature and one combined feature including four features. The selected features from eight subjects with 13 finger movements were tested with four decomposed multi-class support vector machines (SVM), four decomposed linear discriminant analyses (LDA) and a multi-class LDA. The classification accuracy, training, and classification time are compared. The results have shown that the combined features decrease error rate, and binary tree based decomposition multiclass classifiers yield the highest classification success rate (88.2%) with relatively low training and classification time.</p>},
  author       = {Huang, Huaiqi and Li, Tao and Bruschini, Claudio and Enz, Christian and Koch, Volker M. and Justiz, Jorn and Antfolk, Christian},
  booktitle    = {2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016},
  isbn         = {9781509032877},
  language     = {eng},
  month        = {07},
  pages        = {1296--1301},
  publisher    = {IEEE Computer Society},
  title        = {EMG pattern recognition using decomposition techniques for constructing multiclass classifiers},
  url          = {http://dx.doi.org/10.1109/BIOROB.2016.7523810},
  year         = {2016},
}