Finding Stationary Brain Sources in EEG Data
-
1
Technische Universität Berlin, Machine Learning Group, Germany
-
2
Humboldt-Universität zu Berlin, Bernstein Center for Computational Neuroscience, Germany
Neurophysiological measurements obtained from e.g. EEG or fMRI are inherently non-stationary because theproperties of the underlying brain processes vary over time. Forexample, in Brain-Computer-Interfacing (BCI), deterioratingperformance (bitrate) is a common phenomenon since theparameters determined during the calibration phase can besuboptimal under the application regime, where the brain stateis different, e.g. due to increased tiredness or changes in theexperimental paradigm. We show that Stationary SubspaceAnalysis (SSA), a time series analysis method, can be usedto identify the underlying stationary and non-stationary brain sources from high-dimensional EEG measurements. Restrictingthe BCI to the stationary sources found by SSA can significantlyincrease the performance. Moreover, SSA yields topographicmaps corresponding to stationary- and non-stationary brainsources which reveal their spatial characteristics
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:
Bünau
PV,
Meinecke
FC,
Scholler
S and
Mueller
KR
(2010). Finding Stationary Brain Sources in EEG Data.
Front. Comput. Neurosci.
Conference Abstract:
Bernstein Conference on Computational Neuroscience.
doi: 10.3389/conf.fncom.2010.51.00115
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:
09 Sep 2010;
Published Online:
23 Sep 2010.
*
Correspondence:
Dr. Paul V Bünau, Technische Universität Berlin, Machine Learning Group, Berlin, Germany, buenau@cs.tu-berlin.de