Feature Selection Algorithm using Fuzzy Rough Sets for Predicting Cervical Cancer Risks

Vandar Kuzhali Jagannathan, Rajendran Govind, Srinivasan V, Siva Kumar Ganapathi

Abstract


Early detection or prediction is very important to reduce the fatalities of Cervical Cancer. Cancer cells affect the Cervix area initially, and then it will spread near by parts. A method using Fuzzy Rough sets is used to analyze the demographic dataset and identify the risk of Cervical Cancer. This method integrates Entropy, Information Gain (IG) and Fuzzy Rough sets for identifying the risk of Cervical Cancer earlier. Risk Factors are identified by IG. Rules are extracted by Fuzzy Rough sets. These rules can be used to identify the risk of Cervical Cancer efficiently that the decision trees. It is found that Human Papilloma Virus (HPV) and having Multiple Sexual Partners (MP) are the major risk factors increase the chances of affecting this cancer. If all the above factors are high the risk of affecting Cervical Cancer is high. Result of this paper will help to improve the clinical practice guidance for analyzing the risk of Cervical Cancer.

Keywords: Cervical Cancer, Entropy, Information Gain, Fuzzy Rough Sets, Demographic Data, Feature selection.


Full Text: PDF

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

Modern Applied Science   ISSN 1913-1844 (Print)   ISSN 1913-1852 (Online)

Copyright © Canadian Center of Science and Education

To make sure that you can receive messages from us, please add the 'ccsenet.org' domain to your e-mail 'safe list'. If you do not receive e-mail in your 'inbox', check your 'bulk mail' or 'junk mail' folders.