DSpace logo

Please use this identifier to cite or link to this item: http://dspace.bits-pilani.ac.in:8080/jspui/xmlui/handle/123456789/14708
Title: Diagnosis of Alzheimer's disease using universum support vector machine based recursive feature elimination (USVM-RFE)
Authors: Richhariya, Bharat
Keywords: Computer Science
Universum
Alzheimer's disease
MRI
Feature Selection
Prior information
Support Vector Machine
Issue Date: May-2020
Publisher: Elsevier
Abstract: Alzheimer's disease is one of the most common causes of death in today's world. Magnetic resonance imaging (MRI) provides an efficient and non-invasive approach for diagnosis of Alzheimer's disease. Efficient feature extraction techniques are needed for accurate classification of MRI images. Motivated by the work on support vector machine based recursive feature elimination (SVM-RFE) [16], we propose a novel feature selection technique to incorporate prior information about data distribution in the recursive feature elimination process. Our method is termed as universum support vector machine based recursive feature elimination (USVM-RFE). The proposed method provides global information about data in the RFE process as compared to the local approach of feature selection in SVM-RFE. We also present the application of feature selection and classification algorithms on both voxel based as well as volume based morphometry analysis of structural MRI images (ADNI database). Feature selection is performed using MRI data of brain tissues such as gray matter, white matter, and cerebrospinal fluid. USVM-RFE provides improvement over SVM-RFE in classification of control normal (CN), mild cognitive impairment (MCI), and Alzheimer's disease (AD) subjects. Moreover, better accuracy is obtained by USVM-RFE with lesser number of features in comparison to SVM-RFE. This leads to identification of prominent brain regions for feature selection and classification of MRI images. The highest accuracies obtained by our method for classification of CN vs AD, CN vs MCI, and MCI vs AD are 100%, 90%, and 73.68%, respectively.
URI: https://www.sciencedirect.com/science/article/pii/S1746809420300598#kwd0005
http://dspace.bits-pilani.ac.in:8080/jspui/xmlui/handle/123456789/14708
Appears in Collections:Department of Computer Science and Information Systems

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.