EMG pattern recognition using decomposition techniques for constructing multiclass classifiers

Huaiqi Huang, Tao Li, Claudio Bruschini, Christian Enz, Volker M. Koch, Jorn Justiz, Christian Antfolk

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingpeer-review

18 Citations (SciVal)

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 highest classification success rate (88.2%) with relatively low training and classification time.

Original languageEnglish
Title of host publication2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016
PublisherIEEE Computer Society
Pages1296-1301
Number of pages6
ISBN (Electronic)9781509032877
DOIs
Publication statusPublished - 2016 Jul 26
Event6th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016 - Singapore, Singapore
Duration: 2016 Jun 262016 Jun 29

Conference

Conference6th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2016
Country/TerritorySingapore
CitySingapore
Period2016/06/262016/06/29

Subject classification (UKÄ)

  • Electrical Engineering, Electronic Engineering, Information Engineering
  • Other Medical Sciences not elsewhere specified

Fingerprint

Dive into the research topics of 'EMG pattern recognition using decomposition techniques for constructing multiclass classifiers'. Together they form a unique fingerprint.

Cite this