Keyword Search:


Bookmark and Share

Correlation-based feature selection for association rule mining in semantic annotation of mammographic medical images

Abubacker, Nirase Fathima and Azman, Azreen and C. Doraisamy, Shyamala and Azmi Murad, Masrah Azrifah and Elmanna, Mohamed Eltahir Makki and Saravanan, Rekha (2014) Correlation-based feature selection for association rule mining in semantic annotation of mammographic medical images. In: 10th Asia Information Retrieval Societies Conference (AIRS 2014), 3-5 Dec. 2014, Kuching, Sarawak, Malaysia. pp. 482-493.

[img] PDF (Abstract)
34Kb

Abstract

Mining of high dimension data for mammogram image classification is highly challenging. Feature reduction using subset selection plays enormous significance in the field of image mining to reduce the complexity of image mining process. This paper aims at investigating an improved image mining technique to enhance the automatic and semi-automatic semantic image annotation of mammography images using multivariate filters, which is the Correlation-based Feature Selection (CFS). This feature selection method is then applied onto two association rules mining methods, the Apriori and a modified genetic association rule mining technique, the GARM, to classify mammography images into their pathological labels. The findings show that the classification accuracy is improved with the use of CFS in both Apriori and GARM mining techniques.

Item Type:Conference or Workshop Item (Paper)
Keyword:Correlation-based feature selection; Multivariate filters; Association rule mining; Mammographic image classification; Semantic annotation
Faculty or Institute:Faculty of Computer Science and Information Technology
Publisher:Springer
DOI Number:10.1007/978-3-319-12844-3_41
Altmetrics:http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1007/978-3-319-12844-3_41
ID Code:39826
Deposited By: Nursyafinaz Mohd Noh
Deposited On:19 Aug 2015 15:46
Last Modified:28 Jul 2016 16:45

Repository Staff Only: Edit item detail