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 - Jan 1 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 | Belgium |
| City | Bruges |
| Period | 4/25/12 → 4/27/12 |
Fingerprint
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.