An Incremental Attribute Reduction Algorithm for Decision Information Systems Based on Rough Set

摘要

The attribute reduction is the main subject in the research of the knowledge acquisition,which is based on the rough set theory.The paper divides the rule classes of an information system with decision tables into the set of homogenous rules and the set of non-homogenous rules.Then,we obtain a fast method to determine if the relative positive domain of a conditional attribute subset and the relative positive domain of a whole conditional attribute set are equal.Based on this,we propose an algorithm for incremental attribute reduction.This algorithm can achieve a fast attribute reduction for a dynamically changing information system with decision tables. The effectiveness of the proposed algorithm is verified by simulation results.