Ning Shan, Wojciech Ziarko, Howard J. Hamilton, and Nick Cercone, University of Regina, Canada
An attribute-oriented rough set method for knowledge discovery in databases is described. The method is based on information generalization, which examines the data at various levels of abstraction, followed by the discovery, analysis and simplification of significant data relationships. First, an attribute-oriented concept tree ascension technique is applied to generalize the information; this step substantially reduces the overall computational cost. Then rough set techniques are applied to the generalized information system to derive rules. The rules represent data dependencies occurring in the database. We focus on discovering hidden patterns in the database rather than statistical summaries.