Host: Japan Society for Fuzzy Theory and Intelligent Informatics (SOFT)
Rough set-based interrelationship mining, proposed by the authors, provides an approach to extract characteristics based on interrelationship between different attributes from decision tables. The main idea of interrelationship mining is to clearly represent the interrelationships between attributes with respect to various binary relations between attribute values by newly introduced attributes, however, the number of the new attributes tends to numerous. In this paper, we discuss a method to select binary relations for representing the interrelationships between attributes.