classifying eeg for brain-computer interface learning optimal filters for dynamical system featureseeg对脑机接口分类学习动力系统特性的最优滤波器.pdfVIP

Hindawi Publishing Corporation Computational Intelligence and Neuroscience Volume 2007, Article ID 57180, 11 pages doi:10.1155/2007/57180 Research Article Classifying EEG for Brain-Computer Interface: Learning Optimal Filters for Dynamical System Features Le Song1 and Julien Epps2 1 School of Information Technologies, The University of Sydney, N.S.W. 2006, Australia 2 National ICT Australia, Locked Bag 9013 Alexandria, N.S.W. 1435, Australia Correspondence should be addressed to Le Song, lesong@.au Received 19 February 2007; Accepted 27 May 2007 Recommended by Andrzej Cichocki Classification of multichannel EEG recordings during motor imagination has been exploited successfully for brain-computer in- terfaces (BCI). In this paper, we consider EEG signals as the outputs of a networked dynamical system (the cortex), and exploit synchronization features from the dynamical system for classification. Herein, we also propose a new framework for learning op- timal filters automatically from the data, by employing a Fisher ratio criterion. Experimental evaluations comparing the proposed dynamical system features with the CSP and the AR features reveal their competitive performance during classification. Results also show the benefits of employing the spatial and the temporal filters optimized using the proposed learning approach. Copyright © 2007 L. Song and J. Epps. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. 1. INTRODUCTION Recording devices A brain-computer interface (BCI) is a communication sys- Motor imaginations can be recorded by both