PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

An Iterative Algorithm for Spatio-Temporal Filter Optimization
Ryota Tomioka, Guido Dornhege, Kazuyuki Aihara and Klaus-Robert Müller
In: 3rd International Brain-Computer Interface Workshop and Training Course 2006, 21-23 Sep 2006, Graz, Austria.

Abstract

We propose a simultaneous spatiotemporal filter optimization algorithm for single trial ElectroEncephaloGraphy (EEG) classification problem. The algorithm is a generalization of the Common Spatial Pattern (CSP) algorithm, which incorporates non-homogeneous weighting of the spectrum of covariance matrices. The spectral weighting coefficients and the spatial filter are alternately updated. The validation results on 163 motor-imagery BCI datasets shows that the proposed method outperforms wide-band filtered CSP in most datasets and gives comparable accuracy to Common Sparse Spectral Spatial Pattern (CSSSP) with far less computational cost. The proposed method is highly interpretable and modular at the same time because the temporal filter is parameterized in the spectral domain.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Brain Computer Interfaces
ID Code:2278
Deposited By:Guido Dornhege
Deposited On:21 October 2006