Single-trial classification of P300 speller data
-
1
University of Greifswald, Institute of Mathematics and Informatics, Germany
Brain-computer interfaces (BCIs) like the P300 speller mainly rely on late components of the event-related potentials (ERP). Early components like N200 have also shown to be useful, although they usually reflect visual processing. When the BCI is used for disabled persons, it should not require eye fixation. However, when the BCI is used to assist computer work, use of early components improve the speed and performance.We studied the interplay of visual and cognitive ERP components in the P300 speller. In experiments with a 3 × 3 character matrix, attention and eye fixation was directed either to different characters or to the same character. We investigated the performance of singe-trial classification of the attended and fixated character. Regularized discriminant analysis was applied to original data, to ICA components and wavelet coefficients.Very good discrimination was obtained in the case that attended and fixated character coincide. When they differed, simultaneous single-trial classification for both characters worked well. For most subjects, however, either the fixated or the attended character was recognized better than the other one.
Keywords:
computational neuroscience
Conference:
Bernstein Conference on Computational Neuroscience, Berlin, Germany, 27 Sep - 1 Oct, 2010.
Presentation Type:
Poster Abstract
Topic:
Bernstein Conference on Computational Neuroscience
Citation:
Frenzel
S,
Bandt
C,
Huy
NH and
Kien
LT
(2010). Single-trial classification of P300 speller data.
Front. Comput. Neurosci.
Conference Abstract:
Bernstein Conference on Computational Neuroscience.
doi: 10.3389/conf.fncom.2010.51.00131
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
24 Sep 2010;
Published Online:
24 Sep 2010.
*
Correspondence:
Dr. Stefan Frenzel, University of Greifswald, Institute of Mathematics and Informatics, Greifswald, Germany, frenzel@physik.uni-greifswald.de