Rules Mining Based on Rough Set of Compatible Relation

Abstract

Rough set model based on tolerance relation, has been widely used to deal with incomplete information systems. However, this model is not so perfect because not all of the elements in a tolerant class are mutually tolerant, but they are all tolerant with the generating element of this class. To mend this limitation, the compatible relation is redefined, and then the concept of maximal complete compatible class in incomplete information system is presented for the purpose that any two elements in the same compatible module are mutually compatible. Furthermore, two methods are put forward in the interest of selecting optimal compatible class for an object, which can be used in knowledge reduction. Besides, coverings on universe produced by tolerance and compatible relations are deeply investigated and compared. Finally, a medical decision table is analyzed, some compact rules are mined.