Join us   Log in   ijesmj@gmail.com  


INTERNATIONAL JOURNAL OF ENGINEERING, SCIENCE AND - Volume 6, Issue 8,, December 2017 (Special Issue)

Pages: 139-145

Date of Publication: 24-Dec-2017


Print Article   Download XML  Download PDF

An Empirical Comparison Of Attribute Reduction, Rough Set Theory And Machine Learning Algorithms

Author: M.Sudha? A.Kumaravel??

Category: Engineering, Science and Mathematics

Abstract:

An increasing amount of data is becoming available on the internet. Each and every one of us is constantly producing and releasing data about something. Big Data can develop into a problem when different sources of data are match up for commercial use in targeted advertising processes. Rough set theory is a new mathematical approach to imperfect knowledge. It was proposed by Pawlak(1982).The benefit of rough set theory in data analysis is that it can easily find the reducts using approximations without need any preliminary or additional information about data. The proposed approach provides efficient algorithms for deducting unseen patterns in data. We tested medical data set Thyroid using Rough set based tool inordertoreducethe attributes without loss of informationand to extractdecisionrules.Theresultsofthisstudyprovidetherelatedmembersanddecisionmakerstoreduceandpreventthe hypothyroid problemof patientsby predicting them.

Keywords: Rough set theory; Attribute reductuion; Rule induction; Prediction accuracy; Mining classifiers.