Application Of An Improved Rough Set Method In Data Mining

Rough set theory, initialized by Professor Z.Pawlak in early 1980's, has been proved to be an excellent mathematical tool dealing with uncertain and vague description of objects, whose basic idea is to derive classification rules of conception by knowledge reduction with the ability of classification unchanged. It may find the hiding and potential rules, that is knowledge, from the data without any preliminary or additional information. In recent years, as an important part of soft computing, rough set theory and its applications have played an important role, especially in the areas of pattern recognition, machine learning, decision analysis, knowledge discovery and knowledge acquisition etc.This paper researches the application of an improved rough set method in data mining. In this paper, rough set theory has been discussed. By analysis and synthesis of data mining algorithms based on rough set theory, three new kinds of attributes reduction algorithms have been presented. Firstly, we constructed a relative difference comparison table based on the rough set theory to effectively and efficiently achieve the better attribute reduction. Then the relative difference comparison table is combined with the heuristic knowledge to design three algorithms respectively: the improved algorithm for attribute reduction, the judge algorithm of attribute reduction, and some improvements for a widely used value reduction method are also achieved in this paper. Finally the new methods are used to reduce the Cleveland Heart Disease Database from the UCI repository of Machine Learning Databases. The experiment results show that the new methods can obtain the better attribute reductions more effectively and efficiently.