Sparse common spatial patterns in brain computer interface applications

The Common Spatial Pattern (CSP) method is a powerful technique for feature extraction from multichannel neural activity and widely used in brain computer interface (BCI) applications. By linearly combining signals from all channels, it maximizes variance for one condition while minimizing for the other. However, the method overfits the data in presence of dense recordings and limited amount of training data. To overcome this problem we construct a sparse CSP (sCSP) method such that only subset of channels contributes to feature extraction. The sparsity is achieved by a greedy search based generalized eigenvalue decomposition approach with low computational complexity. Our contributions in this study are extension of the greedy search based solution to have multiple sparse filters and its application in a BCI problem. We show that sCSP outperforms traditional CSP in the classification challenge of the multichannel ECoG data set of BCI competition 2005. Furthermore, it achieves nearly similar performance as infeasible exhaustive search and better than that of obtained by L1 norm based sparse solution.

[1]  K.-R. Muller,et al.  Optimizing Spatial filters for Robust EEG Single-Trial Analysis , 2008, IEEE Signal Processing Magazine.

[2]  Michael I. Jordan,et al.  A Direct Formulation for Sparse Pca Using Semidefinite Programming , 2004, NIPS 2004.

[3]  L. Duchene,et al.  An Optimal Transformation for Discriminant and Principal Component Analysis , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Selina Wriessnegger,et al.  Regularised CSP for Sensor Selection in BCI , 2006 .

[5]  Ahmed H. Tewfik,et al.  An ECoG Based Brain Computer Interface with Spatially Adapted Time-Frequency Patterns , 2008, BIOSIGNALS.

[6]  James Demmel,et al.  Applied Numerical Linear Algebra , 1997 .

[7]  Gary E. Birch,et al.  Sparse spatial filter optimization for EEG channel reduction in brain-computer interface , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[8]  Shai Avidan,et al.  Generalized spectral bounds for sparse LDA , 2006, ICML.

[9]  J. Wolpaw,et al.  Multichannel EEG-based brain-computer communication. , 1994, Electroencephalography and clinical neurophysiology.

[10]  Michael S. Lazar,et al.  Spatial patterns underlying population differences in the background EEG , 2005, Brain Topography.

[11]  Boris Reuderink,et al.  Robustness of the Common Spatial Patterns algorithm in the BCI-pipeline , 2008 .

[12]  G Pfurtscheller,et al.  Real-time EEG analysis with subject-specific spatial patterns for a brain-computer interface (BCI). , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.