TOWARDS EFFICIENT INDUCTION MECHANISMS IN DATABASE-SYSTEMS

With the wide availability of huge amounts of data in database systems , the extraction of knowledge in databases by efficient and powerful i nduction or knowledge discovery mechanisms has become an important iss ue in the construction of new generation database and knowledge-base s ystems. In this article, an attribute-oriented induction method for kn owledge discovery in databases is investigated, which provides an effi cient, set-oriented induction mechanism for extraction of different ki nds of knowledge rules, such as characteristic rules, discriminant rul es, data evolution regularities and high level dependency rules in lar ge relational databases. Our study shows that the method is robust in the existence of noise and database updates, is extensible to knowledg e discovery in advanced and/or special purpose databases, such as obje ct-oriented databases, active databases, spatial databases, etc., and has wide applications.