An Informed Interactive Query Approach for Knowledge Discovery from Heterogeneous Databases

摘要

Knowledge discovery in databases (KDD) and data mining are very important in many decision-making processes. In this paper, we introduce a new approach to the problem of discovering correlative attributes from heterogeneous databases. The approach uses a cross-reference technical to find coherent set of attributes patterns from large collection of data entries scattered in various distinct databases. A Bayesian network is used to represent the correlations among the data attributes. An informed interactive method is applied to generate the database queries for retrieving those relevant data entries from the data warehouse environment.