Name
Abstract | ||
|---|---|---|
A support vector machine (SVM) regularized with the Pairwise Elastic Net (PEN) penalty is used to automatically select a sparse set of brain voxel clusters based on the fMRI responses to two stimuli classes. This requires solving the PEN-SVM quadratic program. We show how to design the PEN regularization to encode, in a graph-based fashion, the pairwise similarity structure of the voxel fMRI responses and how to control the spatial locality of the encoding using a voxel searchlight. The voxel similarity encoding is reflected in the sparse structure of the weights of trained PEN-SVM and these weights automatically select a sparse set of voxel clusters. We empirically demonstrate the effectiveness of the approach using a real-world, multi-subject fMRI dataset. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ICASSP.2013.6637807 | Acoustics, Speech and Signal Processing |
Keywords | Field | DocType |
biomedical MRI,brain,image coding,medical image processing,quadratic programming,support vector machines,PEN-SVM quadratic program,automatic FMRI feature selection,brain voxel clusters,graph-based fashion,pairwise elastic net support vector machine,pairwise similarity structure,spatial locality,voxel similarity encoding,Feature Selection,Pairwise Elastic Net,Sparsity,Support Vector Machine,fMRI | Voxel,Pairwise comparison,Pattern recognition,Feature selection,Computer science,Elastic net regularization,Support vector machine,Regularization (mathematics),Artificial intelligence,Quadratic programming,Encoding (memory) | Conference |
ISSN | Citations | PageRank |
1520-6149 | 3 | 0.38 |
References | Authors | |
18 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Alexander Lorbert | 1 | 15 | 3.69 |
| P. J. Ramadge | 2 | 332 | 91.10 |