C-Support Vector Classification the Estimation of the MS Subgroups Classification with Selected Kernels and Parameters
Keywords:
C-SVC Kernels, MS Subgroups, MRI, EDSS, ClassificationAbstract
The study has classified the subgroups of Multiple Sclerosis using Support
Vector Machines. C-SVC algorithm, one of the SVM
classifiers of multi class, has been utilized for the classification of MS
subgroups. For this purpose, 120 MS patient and 19 healthy individuals have been
included in our study. Through Magnetic Resonance Imaging (MRI), the number of
lesion diameter and Expanded Disability Status Scale data are applied through C-
Support Vector Classifier (C-SVC). By applying the data onto Radial Basis
Funrtion kernel, Polynomial kernel, Sigmoid kernel and Linear kernel, four of the
kernel type of C-SVC algorithm, the accuracy rates of MS subgroups
classification and the computation time during the training procedure are
computed and compared. Having applied C- Support Vector Classifier on MS
subgroups, classification achievement of Healthy individual and MS subgroups,
namely that of RRMS, SPMS end PPMS has been measured.
Downloads
Additional Files
- b) Linear Model
- a) Nonlinear Model
- Fig. 2. MR image taken from an MS patient
- Fig.1. MR image taken from a healthy individual
- Fig. 3. An Example of Kernel Trick
- Table 1:Age Intervals Based on The Gender of The Patients in the Dataset.
- Table 2: Literature Review on MS.
- Table 3: Description of EDSS Scores [6, 10, 15].
- Table 4: Feature Extracted from MR Images and Representation of Classes and EDSS.
- Table 5: Training Set Vector Size.
- Table 6: Classification Achievement Rates and Classification Computation Time based on Kernel Types for Training Set 1.
- Table 7: Classification Achievement Rates and Classification Computation Time based on Kernel Types for Training Set 2.
Published
Issue
Section
License
Upon acceptance of an article by the European Journal of Pure and Applied Mathematics, the author(s) retain the copyright to the article. However, by submitting your work, you agree that the article will be published under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0). This license allows others to copy, distribute, and adapt your work, provided proper attribution is given to the original author(s) and source. However, the work cannot be used for commercial purposes.
By agreeing to this statement, you acknowledge that:
- You retain full copyright over your work.
- The European Journal of Pure and Applied Mathematics will publish your work under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).
- This license allows others to use and share your work for non-commercial purposes, provided they give appropriate credit to the original author(s) and source.