Reduction of Information Systems via Rough Set Model

Abstract

Rough sets are efficient for attribute reduction and in extracting rules in data mining. There are many important problems in rough sets and we use algorithms to solve them. An important idea of rough sets is to approximately represent a whole space with a certain subspace. We can use lower and upper operators largely to determine the approximation accuracy. We also study graph representations of lower and upper approximations. This paper will illustrate a medical application by sing right neighborhood and initial neighborhood then core initial neighborhood will be computed.