TY - JOUR
T1 - Combined optimization of spatial and temporal filters for improving brain-computer interfacing
AU - Dornhege, Guido
AU - Blankertz, Benjamin
AU - Krauledat, Matthias
AU - Losch, Florian
AU - Curio, Gabriel
AU - Müller, Klaus Robert
N1 - Funding Information:
Manuscript received October 21, 2005; revised April 3, 2006. The studies were supported by a grant of the Bundesministerium für Bildung und Forschung (BMBF), FKZ 01IBE01A/B. This work was supported in part by the IST Programme of the European Community, under the PASCAL Network of Excellence, IST-2002-506778 and in part by the Deutsche Forschungsgemeinschaft (DFG) under grant FOR 375/B1. This publication only reflects the authors’ views. This work is an extended version of [1]. Asterisk indicates corresponding author. *G. Dornhege is with the Fraunhofer FIRST.IDA, Kekuléstr. 7, 12 489 Berlin, Germany (e-mail: guido.dornhege@first.fraunhofer.de).
PY - 2006/11
Y1 - 2006/11
N2 - Brain-computer interface (BCI) systems create a novel communication channel from the brain to an output device by bypassing conventional motor output pathways of nerves and muscles. Therefore they could provide a new communication and control option for paralyzed patients. Modern BCI technology is essentially based on techniques for the classification of single-trial brain signals. Here we present a novel technique that allows the simultaneous optimization of a spatial and a spectral filter enhancing discriminability rates of multichannel EEG single-trials. The evaluation of 60 experiments involving 22 different subjects demonstrates the significant superiority of the proposed algorithm over to its classical counterpart: the median classification error rate was decreased by 11%. Apart from the enhanced classification, the spatial and/or the spectral filter that are determined by the algorithm can also be used for further analysis of the data, e.g., for source localization of the respective brain rhythms.
AB - Brain-computer interface (BCI) systems create a novel communication channel from the brain to an output device by bypassing conventional motor output pathways of nerves and muscles. Therefore they could provide a new communication and control option for paralyzed patients. Modern BCI technology is essentially based on techniques for the classification of single-trial brain signals. Here we present a novel technique that allows the simultaneous optimization of a spatial and a spectral filter enhancing discriminability rates of multichannel EEG single-trials. The evaluation of 60 experiments involving 22 different subjects demonstrates the significant superiority of the proposed algorithm over to its classical counterpart: the median classification error rate was decreased by 11%. Apart from the enhanced classification, the spatial and/or the spectral filter that are determined by the algorithm can also be used for further analysis of the data, e.g., for source localization of the respective brain rhythms.
KW - Brain-computer interface
KW - Common spatial patterns
KW - EEG
KW - Event-related desynchronization
KW - Single-trial-analysis
UR - http://www.scopus.com/inward/record.url?scp=33746833141&partnerID=8YFLogxK
U2 - 10.1109/TBME.2006.883649
DO - 10.1109/TBME.2006.883649
M3 - Article
C2 - 17073333
AN - SCOPUS:33746833141
SN - 0018-9294
VL - 53
SP - 2274
EP - 2281
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
IS - 11
ER -