Semi-structured Decision Rules in Object-Oriented Rough Set Models for Kansei Engineering

Decision rule generation from Kansei data using rough set theory is one of the most hot topics in Kansei engineering. Usually, Kansei data have various types of scheme, however, Pawlak's "traditional" rough set theory treats structured data mainly, that is, decision tables with fixed attributes and no hierarchy among data. On the other hand, Kudo and Murai have proposed the object-oriented rough set model which treats structural hierarchies among objects. In this paper, we propose semi-structured decision rules in the object-oriented rough set model to represent structural characteristics among objects, which enable us to consider characteristics of hierarchical data by rough sets.