Rule discovery using hierarchical classification structure with rough sets
Chul-Heui Lee, Seon-Hak Seo, Sang-Chul Choi · 2002
This paper deals with the simplification of classification rules for data mining using rough set theory combined with the hierarchical granulation structure. In the proposed method, the procedure for a classification rule discovery from data consists of two parts; the reduction of attributes and the rule discovery. Rough set theory is used to classify the objects of interest into the similarity classes and to investigate the granularity of knowledge for reasoning of uncertain concepts, and the hierarchical granulation structure is adopted to find the classification rules effectively. The proposed classification method generates minimal classification rules and an explicit and effective structure is achieved in consequence. Also the computational burden for the classification rule discovery is considerably reduced. Therefore it may offer an easy way to analyze the information system. To show the effectiveness of the proposed method, a simulation is performed on Wisconsin Breast Cancer data. The simulation result shows that the proposed method gives a good performance in spite of very simple rules and short conditionals.