Data Mining of Multi-categorized Data

At the International Research and Educational Institute for Integrated Medical Sciences (IREIIMS) project, we are collecting complete medical data sets to determine relationships between medical data and health status. Since the data include many items which will be categorized di erently, it is not easy to generate useful rule sets. Sometimes rare rule combinations are ignored and thus we cannot determine the health status correctly. In this paper, we analyze the features of such complex data, point out the merit of categorized data mining and propose categorized rule generation and health status determination by using combined rule sets.

• Type: Conference
• Year: 2007
• Where: ECML
• Authors: Akinori Abe, Norihiro Hagita, Michiko Furutani, Yoshiyuki Furutani, Rumiko Matsuoka
• Keywords: ECML 2007, Health Status, Machine Learning, Medical Data, Rule Sets