LEM2-Based Rule Induction from Data Tables with Imprecise Decision Attribute Values

Abstract

In this paper, we investigate rule induction from imprecise decision tables. Impresice decision tables are data tables whose decision attribute values are specified only imprecisely. We propose a rough set approach to imprecise decision tables. After treatment of imprecise decision attribute values is described, four rule induction schemas are proposed. For each rule induction schema, we apply LEM2-based rule induction algorithm by defining positive object set appropriately. The performances of the proposed rule induction algorithms are examined by numerical experiments.