Header logo is

Support Vector Channel Selection in BCI

2003

Technical Report

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 [3] and Zero-Norm Optimization [13] which are based on the training of Support Vector Machines (SVM) [11]. These algorithms can provide more accurate solutions than standard filter methods for feature selection [14]. 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.
Number (issue): 120
Year: 2003
Month: December
Day: 0

Department(s): Empirical Inference
Bibtex Type: Technical Report (techreport)

Institution: Max Planck Institute for Biological Cybernetics, Tuebingen, Germany

Digital: 0
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
Web

BibTex

@techreport{2482,
  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.},
  number = {120},
  organization = {Max-Planck-Gesellschaft},
  institution = {Max Planck Institute for Biological Cybernetics, Tuebingen, Germany},
  school = {Biologische Kybernetik},
  month = dec,
  year = {2003},
  doi = {},
  month_numeric = {12}
}