A Comparison of Rule Sets Generated from Databases by Indiscernibility Relation - A Rough Sets Approach
Vladimir Brtka, Ivana Berković, Edith Stokić, Biljana Srdić · 2007
Rough sets theory (Pawlak 1980s) proved to be an excellent mathematical tool for the task of automated extraction of If –Then rule sets from table-organized data. In this paper, we employ an approach based on the relation of indiscernibility and Rough sets theory in comparison to the method based on pure classification. We have used a well-known ROSETTA software system. The main goal of this work is to compare rule set generated by ROSETTA and rule set generated by method based on pure classification. Comparison is conducted on real–life database from domain of medicine including recently discovered protein hormone Leptin.