TY - GEN
T1 - Invariant common spatial patterns
T2 - 21st Annual Conference on Neural Information Processing Systems, NIPS 2007
AU - Blankertz, Benjamin
AU - Kawanabe, Motoaki
AU - Tomioka, Ryota
AU - Hohlefeld, Friederike U.
AU - Nikulin, Vadim
AU - Müller, Klaus Robert
N1 - Copyright:
Copyright 2012 Elsevier B.V., All rights reserved.
PY - 2009
Y1 - 2009
N2 - Brain-Computer Interfaces can suffer from a large variance of the subject conditions within and across sessions. For example vigilance fluctuations in the individual, variable task involvement, workload etc. alter the characteristics of EEG signals and thus challenge a stable BCI operation. In the present work we aim to define features based on a variant of the common spatial patterns (CSP) algorithm that are constructed invariant with respect to such nonstationarities. We enforce invariance properties by adding terms to the denominator of a Rayleigh coefficient representation of CSP such as disturbance covariance matrices from fluctuations in visual processing. In this manner physiological prior knowledge can be used to shape the classification engine for BCI. As a proof of concept we present a BCI classifier that is robust to changes in the level of parietal α-activity. In other words, the EEG decoding still works when there are lapses in vigilance.
AB - Brain-Computer Interfaces can suffer from a large variance of the subject conditions within and across sessions. For example vigilance fluctuations in the individual, variable task involvement, workload etc. alter the characteristics of EEG signals and thus challenge a stable BCI operation. In the present work we aim to define features based on a variant of the common spatial patterns (CSP) algorithm that are constructed invariant with respect to such nonstationarities. We enforce invariance properties by adding terms to the denominator of a Rayleigh coefficient representation of CSP such as disturbance covariance matrices from fluctuations in visual processing. In this manner physiological prior knowledge can be used to shape the classification engine for BCI. As a proof of concept we present a BCI classifier that is robust to changes in the level of parietal α-activity. In other words, the EEG decoding still works when there are lapses in vigilance.
UR - http://www.scopus.com/inward/record.url?scp=84858790768&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84858790768&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84858790768
SN - 160560352X
SN - 9781605603520
T3 - Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference
BT - Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference
Y2 - 3 December 2007 through 6 December 2007
ER -