A Novel Multi-objective Affinity Set Classification System: An Investigation of Delayed Diagnosis Detection

Abstract

This paper proposed a novel multi-objective affinity set (MO affinity set) classification system comparing with Ant colony optimization (ACO) and affinity set theory on delayed diagnosis dataset classification. The output of MO affinity set classification rules has the higher accuracy than ACO and traditional affinity set. Furthermore, our MO affinity set classification skips the traditional affinity set k-core method, and has fewer rules. It is better and more easily to apply or to construct a support system if the number of rules is smaller.