Header logo is

Adapting Spatial Filter Methods for Nonstationary BCIs

2006

Conference Paper

ei


A major challenge in applying machine learning methods to Brain-Computer Interfaces (BCIs) is to overcome the possible nonstationarity in the data from the datablock the method is trained on and that the method is applied to. Assuming the joint distributions of the whitened signal and the class label to be identical in two blocks, where the whitening is done in each block independently, we propose a simple adaptation formula that is applicable to a broad class of spatial filtering methods including ICA, CSP, and logistic regression classifiers. We characterize the class of linear transformations for which the above assumption holds. Experimental results on 60 BCI datasets show improved classification accuracy compared to (a) fixed spatial filter approach (no adaptation) and (b) fixed spatial pattern approach (proposed by Hill et al., 2006 [1]).

Author(s): Tomioka, R. and Hill, JN. and Blankertz, B. and Aihara, K.
Book Title: IBIS 2006
Journal: Proceedings of 2006 Workshop on Information-Based Induction Sciences (IBIS 2006)
Pages: 65-70
Year: 2006
Month: November
Day: 0

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Event Name: 2006 Workshop on Information-Based Induction Sciences
Event Place: Osaka, Japan

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

Links: PDF

BibTex

@inproceedings{4247,
  title = {Adapting Spatial Filter Methods for Nonstationary BCIs},
  author = {Tomioka, R. and Hill, JN. and Blankertz, B. and Aihara, K.},
  journal = {Proceedings of 2006 Workshop on Information-Based Induction Sciences (IBIS 2006)},
  booktitle = {IBIS 2006},
  pages = {65-70},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = nov,
  year = {2006},
  doi = {},
  month_numeric = {11}
}