An empirical comparison of classification algorithms for diagnosis of depression from brain sMRI scans Kipli, Kuryati, Kouzani, Abbas Z. and Xiang, Yong 2013, An empirical comparison of classification algorithms for diagnosis of depression from brain sMRI scans, in ACSAT 2013 : Proceedings of the 2nd International Conference on Advanced Computer Science Applications and Technologies. 2013, IEEE Computer Society, [Sarawak, Malaysia], pp. 333-336, doi: 10.1109/ACSAT.2013.72. Attached Files Name Description MIMEType Size Downloads kipli-empiricalcomparison-post-2013.pdf Authors' post print application/pdf 765.55KB 68 Title An empirical comparison of classification algorithms for diagnosis of depression from brain sMRI scans Author(s) Kipli, Kuryati Kouzani, Abbas Z. orcid.org/0000-0002-6292-1214 Xiang, Yong orcid.org/0000-0003-3545-7863 Conference name Advanced Computer Science Applications and Technologies. Conference (2nd : 2013 : Sarawak, Malaysia) Conference location Sarawak, Malaysia Conference dates 22-24 Dec. 2013 Title of proceedings ACSAT 2013 : Proceedings of the 2nd International Conference on Advanced Computer Science Applications and Technologies. 2013 Editor(s) [Unknown] Publication date 2013 Conference series Advanced Computer Science Applications and Technologies International Conference Start page 333 End page 336 Total pages 4 Publisher IEEE Computer Society Place of publication [Sarawak, Malaysia] Keyword(s) structural MRI automated depression detection classification brain image analysis Summary To be diagnostically effective, structural magnetic resonance imaging (sMRI) must reliably distinguish a depressed individual from a healthy individual at individual scans level. One of the tasks in the automated diagnosis of depression from brain sMRI is the classification. It determines the class to which a sample belongs (i.e., depressed/not depressed, remitted/not-remitted depression) based on the values of its features. Thus far, very limited works have been reported for identification of a suitable classification algorithm for depression detection. In this paper, different types of classification algorithms are compared for effective diagnosis of depression. Ten independent classification schemas are applied and a comparative study is carried out. The algorithms are: Naïve Bayes, Support Vector Machines (SVM) with Radial Basis Function (RBF), SVM Sigmoid, J48, Random Forest, Random Tree, Voting Feature Intervals (VFI), LogitBoost, Simple KMeans Classification Via Clustering (KMeans) and Classification Via Clustering Expectation Minimization (EM) respectively. The performances of the algorithms are determined through a set of experiments on sMRI brain scans. An experimental procedure is developed to measure the performance of the tested algorithms. A classification accuracy evaluation method was employed for evaluation and comparison of the performance of the examined classifiers. Language eng DOI 10.1109/ACSAT.2013.72 Field of Research 090399 Biomedical Engineering not elsewhere classified 080109 Pattern Recognition and Data Mining Socio Economic Objective 920203 Diagnostic Methods HERDC Research category E1 Full written paper - refereed Copyright notice ©2013, IEEE Free to Read? Yes Persistent URL http://hdl.handle.net/10536/DRO/DU:30061615 Document type: Conference Paper Collections: School of Information Technology School of Engineering Open Access Collection Related Links Link Description Connect to published version (restricted access) Go to link with your DU access privileges     Link to Related Work An empirical comparison of classification algorithms for diagnosis of depression from brain sMRI scans (deposited 11-11-2018) Advanced Computer Science Applications and Technologies (ACSAT) Publisher (deposited 01-04-2014)   Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au. Versions Version Filter Type Tue, 18 Mar 2014, 08:22:52 EST Tue, 18 Mar 2014, 09:50:55 EST Tue, 01 Apr 2014, 13:55:50 EST Wed, 09 Apr 2014, 15:35:46 EST Thu, 10 Apr 2014, 08:00:55 EST Thu, 10 Apr 2014, 11:57:02 EST Thu, 10 Apr 2014, 15:53:34 EST Thu, 10 Apr 2014, 15:55:03 EST Fri, 11 Apr 2014, 11:29:18 EST Tue, 02 Sep 2014, 09:56:15 EST Wed, 03 Sep 2014, 08:14:15 EST Wed, 03 Sep 2014, 08:17:22 EST Wed, 03 Sep 2014, 11:11:03 EST Wed, 03 Sep 2014, 11:20:09 EST Wed, 03 Sep 2014, 11:21:48 EST Wed, 03 Sep 2014, 11:25:10 EST Wed, 03 Sep 2014, 11:27:01 EST Thu, 25 Sep 2014, 13:14:36 EST Thu, 25 Sep 2014, 13:16:24 EST Wed, 21 Oct 2015, 15:00:28 EST Wed, 06 Dec 2017, 06:04:17 EST Fri, 07 Sep 2018, 16:59:34 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 0 times in Scopus Search Google Scholar Access Statistics: 346 Abstract Views, 80 File Downloads  -  Detailed Statistics Created: Tue, 18 Mar 2014, 08:22:52 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.