Arquitecturas de Integración del Proceso de Descubrimiento de Conocimiento con Sistemas de Gestión de Bases de Datos: Un Estado del Arte

Abstract

Researches on Knowledge Discovery in Databases (KDD) was initially oriented toward the definition of new pattern discovery models and the development of the corresponding algorithms. At present, research has focused on issues related to integrating KDD with database systems, to generate systems and tools for KDD whose architectures can be classified in one of three categories: loosely coupled, middly coupled and tightly coupled with a Database Management System (DBMS). In this paper a review of the state of the art on architectures for the process of integrating Knowledge Discovery with a DBMS is presented. It is part of the proposal doctoral research "New primitives SQL for Knowledge Discovery on tightly coupled architectures with a DBMS" that at the moment it is developed by the author of this paper in the program of Ph.D. in Engineering in Computer Science area of emphasis of University of Valley.