PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Investigating EEG non-stationarities with Robust PCA and its application to improve BCI performance
J Pascual, C Vidaurre and M Kawanabe
International Journal of Bioelectromagnetism 2011.


The analysis of non-stationarities in EEG signals is one of the key challenges in BCI research in order to understand and improve the performance of BCI systems. In this paper we propose a method to visualize spatial patterns of the most prominent variability in the data that automatically identify and rejects outlying non-informative signals. Additionally, it reduces the impact that noise has in the signal and can be used to significantly improve the classification accuracy of Common Spatial Filters.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Brain Computer Interfaces
ID Code:7781
Deposited By:Benjamin Blankertz
Deposited On:17 March 2011