Abstract
BackgroundSupport 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 FindingsSix 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/SignificanceThe 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.
Highlights
It has long been a great interest of human being to make tremendous efforts to explore the mysterious working of the human brain, especially its possible coding schemes and interactions with the real world
Our results demonstrated that, (1) Voxel selection had an important impact on the performance of the classifiers: in a relative low dimensional feature space, radial basis function (RBF) Support vector machine (SVM) outperformed linear SVM significantly; in a relative high dimensional space, linear SVM performed better than its counterpart; (2) Considering the classification accuracy and the amounts of time needed together, when all the selected voxels were treated as features, an effective classification result could be achieved by linear SVM with large number of voxels; when part of the principal components (PCs) of the input voxel space were kept as features, the computational efficiency was improved, and an effective classification result could be achieved by non-linear radial basis function kernel SVM (RBF SVM) with a small set of voxels
The classification results for linear and RBF SVM under six voxel selection schemes and two types of feature spaces were shown in Figures 1 and 2
Summary
It has long been a great interest of human being to make tremendous efforts to explore the mysterious working of the human brain, especially its possible coding schemes and interactions with the real world. Advances in electrophysiological recording methods nowadays employ intrusive technologies, providing EEG with high topographical resolution, EEG has a poor spatial (centimeter) resolution which makes it inappropriate for the study of high-level cognitive activities involved with multiple cortices. Using the approaches reviewed in Norman et al [5], the fMRI data acquired were used to decode the neural representation of different categories of objects [6,7], to discriminate the orientation of a striped pattern being viewed by a study participant [8,9], or to predict human brain activity associated with the meanings of nouns [10]. Support vector machine (SVM) has been widely used as accurate and reliable method to decipher brain patterns from functional MRI (fMRI) data. 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
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
