Classifying EEG for Brain-Computer Interface: Learning Optimal Filters for Dynamical System Features

Classification of multichannel EEG recordings during motor imagination has been exploited successfully for brain-computer interfaces (BCI). In this paper, we consider EEG signals as the outputs of a networked dynamical system (the cortex), and exploit novel features from the collective dynamics of the system for classification. Herein, we also propose a new framework for learning optimal 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.

[1]  Klaus-Robert Müller,et al.  Spatio-spectral filters for improving the classification of single trial EEG , 2005, IEEE Transactions on Biomedical Engineering.

[2]  Thomas Hofmann,et al.  A brain computer interface with online feedback based on magnetoencephalography , 2005, ICML.

[3]  E. Gysels,et al.  Phase synchronization for the recognition of mental tasks in a brain-computer interface , 2004, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[4]  P. Nunez,et al.  Spatial filtering and neocortical dynamics: estimates of EEG coherence , 1998, IEEE Transactions on Biomedical Engineering.

[5]  F. Perrin,et al.  Spherical splines for scalp potential and current density mapping. , 1989, Electroencephalography and clinical neurophysiology.

[6]  K.-R. Muller,et al.  Linear and nonlinear methods for brain-computer interfaces , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[7]  F. L. D. Silva,et al.  Event-related EEG/MEG synchronization and desynchronization: basic principles , 1999, Clinical Neurophysiology.

[8]  Le Song.  Phase Synchrony Rate for the Recognition of Motor Imagery in BCI , 2005 .

[9]  Le Song,et al.  Improving Separability of Eeg Signals During Motor Imagery With An Efficient Circular Laplacian , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[10]  Jürgen Kurths,et al.  Synchronization - A Universal Concept in Nonlinear Sciences , 2001, Cambridge Nonlinear Science Series.

[11]  Le Song,et al.  Phase Synchrony Rate for the Recognition of Motor Imagery in Brain-Computer Interface , 2005, NIPS.

[12]  G. Pfurtscheller,et al.  Optimal spatial filtering of single trial EEG during imagined hand movement. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[13]  Le Song,et al.  Classifying EEG for brain-computer interfaces: learning optimal filters for dynamical system features , 2006, ICML 2006.

[14]  Klaus-Robert Müller,et al.  Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms , 2004, IEEE Transactions on Biomedical Engineering.

[15]  Klaus-Robert Müller,et al.  Optimizing spatio-temporal filters for improving Brain-Computer Interfacing , 2005, NIPS.