EXTRACTING ASSOCIATION RULES FROM DISTRIBUTED ASSOCIATION RULES

Abstract

Mining for associations rules between items in large transactional distributed databases is a central problem in the field of knowledge discovery. When distributed databases are merged at single machine to mining knowledge it will required large capacity of storage, long execution time in addition to that; transferring a huge volume of data over network might take extremely much time and also require an unbearable financial cost.
In this paper proposed algorithm is presented toward saving communication cost
over the network, central storage cost requirements, and accelerating required
execution time. The algorithm consist of two parts: Part one: Extracting Association
Rules for Distributed Association Rules (EAR4DAR) Algorithm; aims to extract
association rules for distributed association rules instead of extracting the
association rules from a huge quantity of distributed data located at several sites.
This is done by collecting the local association rules from each site and storing them
in a file. These Local Association Rules turn in series of operations to produce
association rules over the whole distributed systems. Part two: Association
Rules_map (AR_map) algorithm aims to get association rules by using AND logic
operation which is suitable for representing association relations between items,
since it gives indication for finding a relation or not. Additionally, this algorithm
uses Karnough_map (K_map) propriety to reduce the duplicate and to generate
accurate and logical results with saving time and storage space.