Cargando…

Comparative Study of SVM Methods Combined with Voxel Selection for Object Category Classification on fMRI Data

BACKGROUND: Support vector machine (SVM) has been widely used as accurate and reliable method to decipher brain patterns from functional MRI (fMRI) data. Previous studies have not found a clear benefit for non-linear (polynomial kernel) SVM versus linear one. Here, a more effective non-linear SVM us...

Descripción completa

Detalles Bibliográficos
Autores principales: Song, Sutao, Zhan, Zhichao, Long, Zhiying, Zhang, Jiacai, Yao, Li
Formato: Texto
Lenguaje:English
Publicado: Public Library of Science 2011
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3040226/
https://www.ncbi.nlm.nih.gov/pubmed/21359184
http://dx.doi.org/10.1371/journal.pone.0017191
_version_ 1782198295828889600
author Song, Sutao
Zhan, Zhichao
Long, Zhiying
Zhang, Jiacai
Yao, Li
author_facet Song, Sutao
Zhan, Zhichao
Long, Zhiying
Zhang, Jiacai
Yao, Li
author_sort Song, Sutao
collection PubMed
description BACKGROUND: Support vector machine (SVM) has been widely used as accurate and reliable method to decipher brain patterns from functional MRI (fMRI) data. Previous studies have not found a clear benefit for non-linear (polynomial kernel) SVM versus linear one. Here, a more effective non-linear SVM using radial basis function (RBF) kernel is compared with linear SVM. Different from traditional studies which focused either merely on the evaluation of different types of SVM or the voxel selection methods, we aimed to investigate the overall performance of linear and RBF SVM for fMRI classification together with voxel selection schemes on classification accuracy and time-consuming. METHODOLOGY/PRINCIPAL FINDINGS: Six different voxel selection methods were employed to decide which voxels of fMRI data would be included in SVM classifiers with linear and RBF kernels in classifying 4-category objects. Then the overall performances of voxel selection and classification methods were compared. Results showed that: (1) Voxel selection had an important impact on the classification accuracy of the classifiers: in a relative low dimensional feature space, RBF SVM outperformed linear SVM significantly; in a relative high dimensional space, linear SVM performed better than its counterpart; (2) Considering the classification accuracy and time-consuming holistically, linear SVM with relative more voxels as features and RBF SVM with small set of voxels (after PCA) could achieve the better accuracy and cost shorter time. CONCLUSIONS/SIGNIFICANCE: The present work provides the first empirical result of linear and RBF SVM in classification of fMRI data, combined with voxel selection methods. Based on the findings, if only classification accuracy was concerned, RBF SVM with appropriate small voxels and linear SVM with relative more voxels were two suggested solutions; if users concerned more about the computational time, RBF SVM with relative small set of voxels when part of the principal components were kept as features was a better choice.
format Text
id pubmed-3040226
institution National Center for Biotechnology Information
language English
publishDate 2011
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-30402262011-02-25 Comparative Study of SVM Methods Combined with Voxel Selection for Object Category Classification on fMRI Data Song, Sutao Zhan, Zhichao Long, Zhiying Zhang, Jiacai Yao, Li PLoS One Research Article BACKGROUND: Support vector machine (SVM) has been widely used as accurate and reliable method to decipher brain patterns from functional MRI (fMRI) data. Previous studies have not found a clear benefit for non-linear (polynomial kernel) SVM versus linear one. Here, a more effective non-linear SVM using radial basis function (RBF) kernel is compared with linear SVM. Different from traditional studies which focused either merely on the evaluation of different types of SVM or the voxel selection methods, we aimed to investigate the overall performance of linear and RBF SVM for fMRI classification together with voxel selection schemes on classification accuracy and time-consuming. METHODOLOGY/PRINCIPAL FINDINGS: Six different voxel selection methods were employed to decide which voxels of fMRI data would be included in SVM classifiers with linear and RBF kernels in classifying 4-category objects. Then the overall performances of voxel selection and classification methods were compared. Results showed that: (1) Voxel selection had an important impact on the classification accuracy of the classifiers: in a relative low dimensional feature space, RBF SVM outperformed linear SVM significantly; in a relative high dimensional space, linear SVM performed better than its counterpart; (2) Considering the classification accuracy and time-consuming holistically, linear SVM with relative more voxels as features and RBF SVM with small set of voxels (after PCA) could achieve the better accuracy and cost shorter time. CONCLUSIONS/SIGNIFICANCE: The present work provides the first empirical result of linear and RBF SVM in classification of fMRI data, combined with voxel selection methods. Based on the findings, if only classification accuracy was concerned, RBF SVM with appropriate small voxels and linear SVM with relative more voxels were two suggested solutions; if users concerned more about the computational time, RBF SVM with relative small set of voxels when part of the principal components were kept as features was a better choice. Public Library of Science 2011-02-16 /pmc/articles/PMC3040226/ /pubmed/21359184 http://dx.doi.org/10.1371/journal.pone.0017191 Text en Song et al. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.
spellingShingle Research Article
Song, Sutao
Zhan, Zhichao
Long, Zhiying
Zhang, Jiacai
Yao, Li
Comparative Study of SVM Methods Combined with Voxel Selection for Object Category Classification on fMRI Data
title Comparative Study of SVM Methods Combined with Voxel Selection for Object Category Classification on fMRI Data
title_full Comparative Study of SVM Methods Combined with Voxel Selection for Object Category Classification on fMRI Data
title_fullStr Comparative Study of SVM Methods Combined with Voxel Selection for Object Category Classification on fMRI Data
title_full_unstemmed Comparative Study of SVM Methods Combined with Voxel Selection for Object Category Classification on fMRI Data
title_short Comparative Study of SVM Methods Combined with Voxel Selection for Object Category Classification on fMRI Data
title_sort comparative study of svm methods combined with voxel selection for object category classification on fmri data
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3040226/
https://www.ncbi.nlm.nih.gov/pubmed/21359184
http://dx.doi.org/10.1371/journal.pone.0017191
work_keys_str_mv AT songsutao comparativestudyofsvmmethodscombinedwithvoxelselectionforobjectcategoryclassificationonfmridata
AT zhanzhichao comparativestudyofsvmmethodscombinedwithvoxelselectionforobjectcategoryclassificationonfmridata
AT longzhiying comparativestudyofsvmmethodscombinedwithvoxelselectionforobjectcategoryclassificationonfmridata
AT zhangjiacai comparativestudyofsvmmethodscombinedwithvoxelselectionforobjectcategoryclassificationonfmridata
AT yaoli comparativestudyofsvmmethodscombinedwithvoxelselectionforobjectcategoryclassificationonfmridata