An improved parallelized mRMR for gene subset selection in cancer classification

Kusairi, R.M. and Kohbalan, Moorthy and Habibollah, Haron and Mohd Saberi, Mohamad and Suhami, Napis and Shahreen, Kasim (2017) An improved parallelized mRMR for gene subset selection in cancer classification. International Journal on Advanced Science, Engineering and Information Technology, 7 (4-2). pp. 1595-1600. ISSN 2088-5334. (Published)

[img]
Preview
Pdf
4. MRMR.pdf

Download (1MB) | Preview

Abstract

DNA microarray technique has become a more attractive tool for cancer classification in the scientific and industrial fields. Based on the previous researchers, the conventional approach for cancer classification is primarily based on morphological appearance of the tumor. The limitations of this approach are bias in identify the tumors by expert and faced the difficulty in differentiate the cancer subtypes due to most cancers being highly related to the specific biological insight. Thus, this study propose an improved parallelized Minimum Redundancy Maximum Relevance (mRMR), which is a particularly fast feature selection method for finding a set of both relevant and complementary features. The mRMR can identify genes more relevance to biological context that leads to richer biological interpretations. The proposed method is expected to achieve accurate classification performance using small number of predictive genes when tested using two datasets from Cancer Genome Project and compared to previous methods.

Item Type: Article
Additional Information: Indexed by Scopus
Uncontrolled Keywords: Feature selection; Cancer classification; MRMR filter method; Parallelized mRMR; Random forest classifier
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
R Medicine > RZ Other systems of medicine
Faculty/Division: Faculty of Computer System And Software Engineering
Depositing User: Dr. Kohbalan Moorthy
Date Deposited: 30 Aug 2018 04:29
Last Modified: 30 Aug 2018 04:29
URI: http://umpir.ump.edu.my/id/eprint/21358
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item