Review article
KNOWLEDGE DISCOVERY IN DATABASES: A COMPARISON OF DIFFERENT VIEWS
Eva Andrassyova
; Department of Cybernetics and Artificial lntelligence, Technical University of Košice, Košice, Slovakia
Jan Paralič
; Department of Cybernetics and Artificial lntelligence, Technical University of Košice, Košice, Slovakia
Abstract
The field of knowledge discovery in databases (KDD) is becoming very popular and il has grown quite alat recently. The large amounts of data collected and stored may contain same information, which could be useful, but it is not easy to recognise it, nor is it trivial to obtain il. There is no human capable of sifting through such large amounts of data and even same of the existing algorithms are inefficient when trying to solve this task. KDD systems incorporate techniques .from a large variety of related fields to utilise their strengths in the process of discovering knowledge. Whilst working on the international GOAL project (Geographic Information On-Line Analysis: GIS - Data Warehouse Integration) we have studied several publications to get an idea of what the KDD (process) is and also an idea of what it is not. We have studied those techniques that are applicable in this process, what tasks are to be solved and which particular steps the process should take. The interdisciplinary nature of KDD causes terminology use to vary from source to source. The aim of this paper is to colt/pare the notions and definitions of KDD within the sources we studied and to point out their similarities and their differences. From all the steps of the KDD process, we will focus on the data mining step. (KDD is often misleadingly called data mining.) An attempt to link together the techniques and the methods as well as the tasks listed in each source under different names is presented here in the form of tables. We have made our conclusions hoping that we have chosen the best views for our later use.
Keywords
knowledge discovery in databases (KOD); the process s of KOD; data mining (OM)
Hrčak ID:
78768
URI
Publication date:
15.12.1999.
Visits: 1.459 *