A novel objective function minimization for sparse spatial filters
2014 22nd Signal Processing and Communications Applications Conference, SIU 2014 - Proceedings
IEEE Computer Society
188 - 191
MetadataShow full item record
Please cite this item using this persistent URLhttp://hdl.handle.net/11693/27463
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 l\ 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 £o norm based solution and it is associated with less computational complexity. © 2014 IEEE.
Showing items related by title, author, creator and subject.
Ural, S. E.; Yilmazer, S. (John Wiley & Sons, 2010-01)In recent studies, contextual situations of applied colours are compared to colours presented as samples or chips. Findings of such studies point out different results in terms of similarities or differences between the ...
Onaran I.; Ince, N.F.; Cetin, A.E. (2013)The common spatial pattern (CSP) method has large number of applications in brain machine interfaces (BMI) to extract features from the multichannel neural activity through a set of linear spatial projections. These spatial ...
Akçay H.G.; Aksoy, S. (2010)We propose an algorithm for automatic detection of buildings with complex shapes and roof structures in very high spatial resolution remotely sensed images. First, an initial oversegmentation is obtained. Then, candidate ...