Class-based Reducts in Variable-Consistency and Variable-Precision Dominance-based Rough Set Approaches

Abstract

In order to analyse a decision table with a monotonicity between condition attributes and a decision attribute, the Dominance-based Rough Set Approach (DRSA) has been proposed. Moreover, to tolerate some degree of inconsistency, DRSA has been extended to Variable-Consistency DRSA (VC-DRSA) or Variable-Precision DRSA (VP-DRSA). Attribute reduction is one of the major tools of rough set approaches. In VC-DRSA and VP-DRSA, union-based reducts have been proposed. However, class-based reducts proposed in DRSA has not been studied in VC-DRSA and VP-DRSA. In this paper, we propose class-based reducts in VC-DRSA and VP-DRSA, and investigate relations among reducts.