Principal components of recurrence quantification analysis of EMG

Author

Mewett, David T. ; Reynolds, Karen J. ; Nazeran, Homer

Author_Institution

Sch. of Inf. & Eng., Flinders Univ. of South Australia, Adelaide, SA, Australia

Volume

2

fYear

2001

fDate

2001

Firstpage

1592

Abstract

A nonlinear dynamical signal analysis technique, recurrence quantification analysis (RQA), was applied to surface electromyograms (EMG) recorded during a series of isometric contractions. None of the ten RQA features calculated adequately related the EMG to the force level so principal components analysis was applied to combine these features into a lower number of variables. Linear regression of the first principal component gave similar lines for each subject. However, the error was too great for these lines to he used in predicting force from the principal component.

Keywords

electromyography; feature extraction; inverse problems; medical signal processing; nonlinear dynamical systems; principal component analysis; distance threshold; embedding vectors; ill-posed problem; isometric contractions; linear regression; muscle electrical activity; nonlinear dynamical signal analysis; principal components analysis; recurrence quantification analysis; surface electromyograms; Electromagnetic compatibility; Electromyography; Informatics; Linear regression; Muscles; Neuromuscular; Nonlinear dynamical systems; Principal component analysis; Signal analysis; Signal processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE

ISSN

1094-687X

Print_ISBN

0-7803-7211-5

Type

conf

DOI

10.1109/IEMBS.2001.1020516

Filename

1020516