An adaptation strategy of using LDA classifier for EMG pattern recognition

Haoshi Zhang, Yaonan Zhao, Fuan Yao, Lisheng Xu, Peng Shang, Guanglin Li

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

80 Scopus citations

Abstract

The time-varying character of myoelectric signal usually causes a low classification accuracy in traditional supervised pattern recognition method. In this work, an unsupervised adaptation strategy of linear discriminant analysis (ALDA) based on probability weighting and cycle substitution was suggested in order to improve the performance of electromyography (EMG)-based motion classification in multifunctional myoelectric prostheses control in changing environment. The adaptation procedure was firstly introduced, and then the proposed ALDA classifier was trained and tested with surface EMG recordings related to multiple motion patterns. The accuracies of the ALDA classifier and traditional LDA classifier were compared when the EMG recordings were added with different degrees of noise. The experimental results showed that compared to the LDA method, the suggested ALDA method had a better performance in improving the classification accuracy of sEMG pattern recognition, in both stable situation and noise added situation.

Original languageEnglish
Title of host publication2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013
Pages4267-4270
Number of pages4
DOIs
StatePublished - 2013
Externally publishedYes
Event2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013 - Osaka, Japan
Duration: 3 Jul 20137 Jul 2013

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)1557-170X

Conference

Conference2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013
Country/TerritoryJapan
CityOsaka
Period3/07/137/07/13

Fingerprint

Dive into the research topics of 'An adaptation strategy of using LDA classifier for EMG pattern recognition'. Together they form a unique fingerprint.

Cite this