direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Page Content

Search in All Publications

Search for publications




All Publications by GRK Members

Stationary common spatial patterns for brain-computer interfacing
Citation key Samek2012a
Author Samek, W., Vidaurre, C., Müller, K.-R., and Kawanabe, M.
Pages 026013
Year 2012
DOI 10.1088/1741-2560/9/2/026013
Journal Journal of Neural Engineering
Volume 9
Number 2
Abstract Classifying motion intentions in Brain-Computer Interfacing (BCI) is a demanding task as the recorded EEG signal is not only noisy and has limited spatial resolution but it is also intrinsically non-stationary. The non-stationarities in the signal may come from many different sources, for instance electrode artifacts, muscular activity or changes of task involvement, and often deteriorate classification performance. This is mainly because features extracted by standard methods like Common Spatial Patterns (CSP) are not invariant to variations of the signal properties, thus should also change over time. Although any extensions of CSP were proposed to, for example, reduce the sensitivity to noise or incorporate information from other subjects, none of them tackles the non-stationarity problem directly. In this paper we propose a method which regularizes CSP towards stationary subspaces (sCSP) and show that this increases classification accuracy, especially for subjects who are hardly able to control a BCI. We compare our method with the state-of-the-art approaches on different data sets, show competitive results and analyse the reasons for the improvement.
Link to publication Download Bibtex entry

To top

Import Publication

Upload BibTeX

Export all entries to BibTex

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions