Sparse spatial filter via a novel objective function minimization with smooth ℓ1 regularization

buir.contributor.authorÇetin, A. Enis
buir.contributor.orcidÇetin, A. Enis|0000-0002-3449-1958
dc.citation.epage288en_US
dc.citation.issueNumber3en_US
dc.citation.spage282en_US
dc.citation.volumeNumber8en_US
dc.contributor.authorOnaran, I.en_US
dc.contributor.authorInce, N. F.en_US
dc.contributor.authorÇetin, A. Enisen_US
dc.date.accessioned2015-07-28T12:05:28Z
dc.date.available2015-07-28T12:05:28Z
dc.date.issued2013-05en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractCommon 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. These spatial projections minimize the Rayleigh quotient (RQ) as the objective function, which is the variance ratio of the classes. The CSP method easily overfits the data when the number of training trials is not sufficiently large and itis 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 to some adequate number. We introduce a spatially sparse projection (SSP) method that exploits the unconstrained minimization of a new objective function with approximated 1 penalty. Unlike the RQ, this new objective function depends on the magnitude of the sparse filter. The SSP method is employed to classify the multiclass ECoG and two class EEG data sets. We compared our results with a recently introduced sparse CSP solution based on 0 norm. Our method outperforms the standard CSP method and provides comparable results to 0 norm based solution and it is associated with less computational complexity. We also conducted several simulation studies on the effect of noisy channel and intersession variability on the performance of the CSP and sparse filters.en_US
dc.identifier.doi10.1016/j.bspc.2012.10.003en_US
dc.identifier.issn1746-8094
dc.identifier.urihttp://hdl.handle.net/11693/13276
dc.language.isoEnglishen_US
dc.publisherElsevieren_US
dc.relation.isversionofhttp://dx.doi.org/10.1016/j.bspc.2012.10.003en_US
dc.source.titleBiomedical Signal Processing and Controlen_US
dc.subjectBrain Machine Interfacesen_US
dc.subjectCommon Spatial Patternsen_US
dc.subjectSparse Spatial Projectionsen_US
dc.subjectRayleigh Quotienten_US
dc.subjectUnconstrained Optimizationen_US
dc.titleSparse spatial filter via a novel objective function minimization with smooth ℓ1 regularizationen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
10.1016-j.bspc.2012.10.003.pdf
Size:
568.02 KB
Format:
Adobe Portable Document Format
Description:
Full printable version