Header logo is

Support Vector Channel Selection in BCI

2004

Article

ei


Designing a Brain Computer Interface (BCI) system one can choose from a variety of features that may be useful for classifying brain activity during a mental task. For the special case of classifying EEG signals we propose the usage of the state of the art feature selection algorithms Recursive Feature Elimination and Zero-Norm Optimization which are based on the training of Support Vector Machines (SVM). These algorithms can provide more accurate solutions than standard filter methods for feature selection. We adapt the methods for the purpose of selecting EEG channels. For a motor imagery paradigm we show that the number of used channels can be reduced significantly without increasing the classification error. The resulting best channels agree well with the expected underlying cortical activity patterns during the mental tasks. Furthermore we show how time dependent task specific information can be visualized.

Author(s): Lal, TN. and Schröder, M. and Hinterberger, T. and Weston, J. and Bogdan, M. and Birbaumer, N. and Schölkopf, B.
Journal: IEEE Transactions on Biomedical Engineering
Volume: 51
Number (issue): 6
Pages: 1003-1010
Year: 2004
Month: June
Day: 0

Department(s): Empirical Inference
Bibtex Type: Article (article)

Digital: 0
DOI: 10.1109/TBME.2004.827827
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

BibTex

@article{2607,
  title = {Support Vector Channel Selection in BCI},
  author = {Lal, TN. and Schr{\"o}der, M. and Hinterberger, T. and Weston, J. and Bogdan, M. and Birbaumer, N. and Sch{\"o}lkopf, B.},
  journal = {IEEE Transactions on Biomedical Engineering},
  volume = {51},
  number = {6},
  pages = {1003-1010},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = jun,
  year = {2004},
  doi = {10.1109/TBME.2004.827827},
  month_numeric = {6}
}