TY - JOUR
T1 - Divergence-based framework for common spatial patterns algorithms
AU - Samek, Wojciech
AU - Kawanabe, Motoaki
AU - Muller, Klaus Robert
PY - 2014
Y1 - 2014
N2 - Controlling a device with a brain-computer interface requires extraction of relevant and robust features from high-dimensional electroencephalographic recordings. Spatial filtering is a crucial step in this feature extraction process. This paper reviews algorithms for spatial filter computation and introduces a general framework for this task based on divergence maximization. We show that the popular common spatial patterns (CSP) algorithm can be formulated as a divergence maximization problem and computed within our framework. Our approach easily permits enforcing different invariances and utilizing information from other subjects; thus, it unifies many of the recently proposed CSP variants in a principled manner. Furthermore, it allows to design novel spatial filtering algorithms by incorporating regularization schemes into the optimization process or applying other divergences. We evaluate the proposed approach using three regularization schemes, investigate the advantages of beta divergence, and show that subject-independent feature spaces can be extracted by jointly optimizing the divergence problems of multiple users. We discuss the relations to several CSP variants and investigate the advantages and limitations of our approach with simulations. Finally, we provide experimental results on a dataset containing recordings from 80 subjects and interpret the obtained patterns from a neurophysiological perspective.
AB - Controlling a device with a brain-computer interface requires extraction of relevant and robust features from high-dimensional electroencephalographic recordings. Spatial filtering is a crucial step in this feature extraction process. This paper reviews algorithms for spatial filter computation and introduces a general framework for this task based on divergence maximization. We show that the popular common spatial patterns (CSP) algorithm can be formulated as a divergence maximization problem and computed within our framework. Our approach easily permits enforcing different invariances and utilizing information from other subjects; thus, it unifies many of the recently proposed CSP variants in a principled manner. Furthermore, it allows to design novel spatial filtering algorithms by incorporating regularization schemes into the optimization process or applying other divergences. We evaluate the proposed approach using three regularization schemes, investigate the advantages of beta divergence, and show that subject-independent feature spaces can be extracted by jointly optimizing the divergence problems of multiple users. We discuss the relations to several CSP variants and investigate the advantages and limitations of our approach with simulations. Finally, we provide experimental results on a dataset containing recordings from 80 subjects and interpret the obtained patterns from a neurophysiological perspective.
KW - Brain-computer interfaces
KW - information geometry
KW - spatial filters
UR - http://www.scopus.com/inward/record.url?scp=84899454044&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84899454044&partnerID=8YFLogxK
U2 - 10.1109/RBME.2013.2290621
DO - 10.1109/RBME.2013.2290621
M3 - Article
C2 - 24240027
AN - SCOPUS:84899454044
VL - 7
SP - 50
EP - 72
JO - IEEE Reviews in Biomedical Engineering
JF - IEEE Reviews in Biomedical Engineering
SN - 1937-3333
M1 - 6662468
ER -