A novel objective function minimization for sparse spatial filters

Common spatial pattern (CSP) method is widely used in brain machine interface (BMI) applications to extract features from the multichannel neural activity through a set of spatial projections. The CSP method easily overfits the data when the number of training trials is not sufficiently large and it is sensitive to daily variation of multichannel electrode placement, which limits its applicability for everyday use in BMI systems. To overcome these problems, the amount of channels that is used in projections, should be limited. We introduce a spatially sparse projection (SSP) method that exploits the unconstrained minimization of a new objective function with approximated ℓ1 penalty. The SSP method is employed to classify the two class EEG data set. Our method outperforms the standard CSP method and provides comparable results to ℓ0 norm based solution and it is associated with less computational complexity.

[1]  J. Miller.  Numerical Analysis , 1966, Nature.

[2]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[3]  Cuntai Guan,et al.  Optimizing the Channel Selection and Classification Accuracy in EEG-Based BCI , 2011, IEEE Transactions on Biomedical Engineering.

[4]  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.

[5]  Ahmed H. Tewfik,et al.  High Accuracy Decoding of Movement Target Direction in Non-Human Primates Based on Common Spatial Patterns of Local Field Potentials , 2010, PloS one.

[6]  Honglak Lee,et al.  Efficient L1 Regularized Logistic Regression , 2006, AAAI.

[7]  Ahmed H. Tewfik,et al.  Sparse common spatial patterns in brain computer interface applications , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  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.

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

[10]  Lester W. Mackey,et al.  Deflation Methods for Sparse PCA , 2008, NIPS.

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

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

[13]  Mark W. Schmidt,et al.  Fast Optimization Methods for L1 Regularization: A Comparative Study and Two New Approaches , 2007, ECML.