PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Efficient Management of Non Redundant Rules in Large Pattern Bases: a Bitmap Approach
François Jacquenet, Christine Largeron and Cédric Udréa
In: International Conference on Enterprise Information Systems, 23-27 May 2006, Paphos, Cyprus.

Abstract

Knowledge Discovery from Databases has more and more impact nowadays and various tools are now available to extract efficiently (in time and memory space) some knowledge from huge databases. Nevertheless, those systems generally produce some large pattern bases and then the management of these one rapidly becomes untractable. Few works have focused on pattern base management systems and researches on that domain are really new. This paper comes within that context, dealing with a particular class of patterns that is association rules. More precisely, we present the way we have efficiently implemented the search for non redundant rules thanks to a representation of rules in the form of bitmap arrays. Some experiments show that the use of this technique increases dramatically the gain in time and space, allowing us to manage large pattern bases.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Information Retrieval & Textual Information Access
ID Code:2755
Deposited By:François Jacquenet
Deposited On:22 November 2006