TY - GEN
T1 - Improving BCI performance by modified common spatial patterns with robustly averaged covariance matrices
AU - Kawanabe, M.
AU - Vidaurre, C.
PY - 2009
Y1 - 2009
N2 - EEG single-trial analysis requires methods that are robust against noise and disturbance. In this contribution, based on the framework of robust statistics, we propose a simple modification of Common Spatial Patterns by the robust calculation of covariance estimators against outlying trials caused, for example, by artifacts. We tested the proposed robust filters with EEG recordings from 80 subjects and obtained, not only a significant improvement in performance, but for some subjects, also better neuro-physiologically interpretable filters.
AB - EEG single-trial analysis requires methods that are robust against noise and disturbance. In this contribution, based on the framework of robust statistics, we propose a simple modification of Common Spatial Patterns by the robust calculation of covariance estimators against outlying trials caused, for example, by artifacts. We tested the proposed robust filters with EEG recordings from 80 subjects and obtained, not only a significant improvement in performance, but for some subjects, also better neuro-physiologically interpretable filters.
KW - Brain-Computer Interface BCI
KW - Common Spatial Patterns CSP
KW - Electro-encephalogram EEG
KW - Robust average covariance
UR - https://www.scopus.com/pages/publications/77950438338
U2 - 10.1007/978-3-642-03889-1_75
DO - 10.1007/978-3-642-03889-1_75
M3 - Conference contribution
AN - SCOPUS:77950438338
SN - 9783642038884
T3 - IFMBE Proceedings
SP - 279
EP - 282
BT - World Congress on Medical Physics and Biomedical Engineering
PB - Springer Verlag
T2 - World Congress on Medical Physics and Biomedical Engineering: Neuroengineering, Neural Systems, Rehabilitation and Prosthetics
Y2 - 7 September 2009 through 12 September 2009
ER -