The practical algorithm for core in decision system

Abstract

As the basis of attribute reduction, core computation is one of the key issues in rough set theory. Actually, decision system is continuously changing, which leads to the inconsistent system. To deal with the problem before core computation, based on bucket sort and equivalence class partition, a new algorithm with time complexity of O(|P||U|) is proposed. After that, an effective approach is proposed to make universe consistent and smaller. According to involved theorems and equivalent propositions, an algorithm for core on the discordant index is proposed also and its time performance is O(|C|2|U/C|). The theoretical analysis and experiment show that the ways proposed here not only can simplify the relevant operations but also can give accurate core results.