A review of kernels on covariance matrices for BCI applications

作者: Florian Yger

DOI: 10.1109/MLSP.2013.6661972

关键词:

摘要: Recently, covariance matrices have been shown to be interesting features for signal classification and object detection. In this paper, we review compare the existing kernels on explore their use EEG in Brain-Computer Interfaces (BCI). This study addresses both experimental theoretical aspects of problem. Beside apparent complexity kernels, show that approach simplifies whole BCI system. Finally, empirically demonstrate simpler obtains state-of-the-art results competition IV dataset 2a.

参考文章(9)
Z.J. Koles, The quantitative extraction and topographic mapping of the abnormal components in the clinical EEG Electroencephalography and Clinical Neurophysiology. ,vol. 79, pp. 440- 447 ,(1991) , 10.1016/0013-4694(91)90163-X
Maher Moakher, A Differential Geometric Approach to the Geometric Mean of Symmetric Positive-Definite Matrices SIAM Journal on Matrix Analysis and Applications. ,vol. 26, pp. 735- 747 ,(2005) , 10.1137/S0895479803436937
Christian Jutten, Alexandre Barachant, Stéphane Bonnet, Marco Congedo, Classification of covariance matrices using a Riemannian-based kernel for BCI applications Neurocomputing. ,vol. 112, pp. 172- 178 ,(2013) , 10.1016/J.NEUCOM.2012.12.039
Johannes Müller-Gerking, Gert Pfurtscheller, Henrik Flyvbjerg, Designing optimal spatial filters for single-trial EEG classification in a movement task Clinical Neurophysiology. ,vol. 110, pp. 787- 798 ,(1999) , 10.1016/S1388-2457(98)00038-8
G. Pfurtscheller, F.H. Lopes da Silva, Event-related EEG/MEG synchronization and desynchronization: basic principles. Clinical Neurophysiology. ,vol. 110, pp. 1842- 1857 ,(1999) , 10.1016/S1388-2457(99)00141-8
Fabien Lotte, Cuntai Guan, Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms IEEE Transactions on Biomedical Engineering. ,vol. 58, pp. 355- 362 ,(2011) , 10.1109/TBME.2010.2082539
Klaus-Robert Müller, Kazuyuki Aihara, Ryota Tomioka, Logistic Regression for Single Trial EEG Classification neural information processing systems. ,vol. 19, pp. 1377- 1384 ,(2006)