Automatic selection of the number of spatial filters for motor-imagery BCI

Y. Yang; S. Chevallier; J. Wiart; I. Bloch

Automatic selection of the number of spatial filters for motor-imagery BCI

Y. Yang, S. Chevallier, J. Wiart, I. Bloch

Physical Therapy and Human Movement Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

15 Scopus citations

Abstract

Common spatial pattern (CSP) is widely used for constructing spatial filters to extract features for motor-imagery-based BCI. One main parameter in CSP-based classification is the number of spatial filters used. An automatic method relying on Rayleigh quotient is presented to estimate its optimal value for each subject. Based on an existing dataset, we validate the contribution of the proposed method through a study of the effect of this parameter on the classification performance. The evaluation on testing data shows that the estimated subject-specific optimal values yield better performances than the recommended value in the literature.

Original language	English (US)
Title of host publication	ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Publisher	i6doc.com publication
Pages	109-114
Number of pages	6
ISBN (Print)	9782874190490
State	Published - 2012
Event	20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012 - Bruges, Belgium Duration: Apr 25 2012 → Apr 27 2012

Publication series

Name	ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Other

Other	20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012
Country/Territory	Belgium
City	Bruges
Period	4/25/12 → 4/27/12

ASJC Scopus subject areas

Information Systems
Artificial Intelligence

Cite this

Yang, Y., Chevallier, S., Wiart, J., & Bloch, I. (2012). Automatic selection of the number of spatial filters for motor-imagery BCI. In ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (pp. 109-114). (ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning). i6doc.com publication.

Yang, Y. ; Chevallier, S. ; Wiart, J. ; Bloch, I. / Automatic selection of the number of spatial filters for motor-imagery BCI. ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. i6doc.com publication, 2012. pp. 109-114 (ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning).

@inproceedings{d6a2539847dd4a64a9088d68fc2890a8,

title = "Automatic selection of the number of spatial filters for motor-imagery BCI",

abstract = "Common spatial pattern (CSP) is widely used for constructing spatial filters to extract features for motor-imagery-based BCI. One main parameter in CSP-based classification is the number of spatial filters used. An automatic method relying on Rayleigh quotient is presented to estimate its optimal value for each subject. Based on an existing dataset, we validate the contribution of the proposed method through a study of the effect of this parameter on the classification performance. The evaluation on testing data shows that the estimated subject-specific optimal values yield better performances than the recommended value in the literature.",

author = "Y. Yang and S. Chevallier and J. Wiart and I. Bloch",

note = "Publisher Copyright: {\textcopyright} 2012, i6doc.com publication. All rights reserved.; 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012 ; Conference date: 25-04-2012 Through 27-04-2012",

year = "2012",

language = "English (US)",

isbn = "9782874190490",

series = "ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning",

publisher = "i6doc.com publication",

pages = "109--114",

booktitle = "ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning",

}

Yang, Y, Chevallier, S, Wiart, J & Bloch, I 2012, Automatic selection of the number of spatial filters for motor-imagery BCI. in ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, i6doc.com publication, pp. 109-114, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012, Bruges, Belgium, 4/25/12.

Automatic selection of the number of spatial filters for motor-imagery BCI. / Yang, Y.; Chevallier, S.; Wiart, J.; Bloch, I.

ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. i6doc.com publication, 2012. p. 109-114 (ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Automatic selection of the number of spatial filters for motor-imagery BCI

AU - Yang, Y.

AU - Chevallier, S.

AU - Wiart, J.

AU - Bloch, I.

PY - 2012

Y1 - 2012

N2 - Common spatial pattern (CSP) is widely used for constructing spatial filters to extract features for motor-imagery-based BCI. One main parameter in CSP-based classification is the number of spatial filters used. An automatic method relying on Rayleigh quotient is presented to estimate its optimal value for each subject. Based on an existing dataset, we validate the contribution of the proposed method through a study of the effect of this parameter on the classification performance. The evaluation on testing data shows that the estimated subject-specific optimal values yield better performances than the recommended value in the literature.

AB - Common spatial pattern (CSP) is widely used for constructing spatial filters to extract features for motor-imagery-based BCI. One main parameter in CSP-based classification is the number of spatial filters used. An automatic method relying on Rayleigh quotient is presented to estimate its optimal value for each subject. Based on an existing dataset, we validate the contribution of the proposed method through a study of the effect of this parameter on the classification performance. The evaluation on testing data shows that the estimated subject-specific optimal values yield better performances than the recommended value in the literature.

UR - http://www.scopus.com/inward/record.url?scp=84885642888&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885642888&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84885642888

SN - 9782874190490

T3 - ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

SP - 109

EP - 114

BT - ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

PB - i6doc.com publication

T2 - 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2012

Y2 - 25 April 2012 through 27 April 2012

ER -

Yang Y, Chevallier S, Wiart J, Bloch I. Automatic selection of the number of spatial filters for motor-imagery BCI. In ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. i6doc.com publication. 2012. p. 109-114. (ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning).

Automatic selection of the number of spatial filters for motor-imagery BCI

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this