A Time-Varying Eigenspectrum/SVM Method for Semg Classification of Reaching Movements in Healthy and Stroke Subjects

Author

Chiang, Joyce ; Wang, Z. Jane ; McKeown, Martin J.

Author_Institution

Dept. of Electr. & Comput. Eng., British Columbia Univ.

Volume

2

fYear

2006

fDate

14-19 May 2006

Abstract

A method for classification of sEMG recordings based on the time-varying covariance patterns between sEMG muscle channels is proposed. The proposed eigenspectral feature vector appears to enhance classification of sEMG patterns with an SVM classifier. The method is shown to be more reliable, robust and enhances classification between stroke and normal subjects, compared to standard analysis methods that examine each muscle individually. This simple, easily-implemented, biologically-inspired approach appears to be a promising means to monitor motor performance in healthy and disease subjects

Keywords

eigenvalues and eigenfunctions; electromyography; medical signal processing; pattern classification; signal classification; support vector machines; SVM classifier; SVM method; biologically-inspired approach; eigenspectral feature vector; healthy subjects; pattern classification; reaching movements; sEMG classification; sEMG muscle channels; stroke subjects; time-varying covariance patterns; time-varying eigenspectrum; Diseases; Electrodes; Feature extraction; Histograms; Monitoring; Muscles; Pattern classification; Robustness; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on

Conference_Location

Toulouse

ISSN

1520-6149

Print_ISBN

1-4244-0469-X

Type

conf

DOI

10.1109/ICASSP.2006.1660561

Filename

1660561