Authors: Bay Vo, Bac Le
Addresses: Faculty of Information Technology, Ho Chi Minh City University of Technology, 144/24 Dien Bien Phu, Binh Thanh, Ho Chi Minh City, Vietnam. ' Faculty of Information Technology, Ho Chi Minh City University of Science, 227 Nguyen Van Cu, District 5, Ho Chi Minh City, Vietnam
Abstract: In this paper, we present an application of frequent itemsets lattice (FIL) to mine minimal non-redundant association rules (MNARs) that reduces a lot of time for mining rules. Our method includes two phases: (1) building FIL and (2) mining MNARs from lattice. we extend the structure of FIL by adding one field to consider whether a lattice node is a minimal generator (mG) or not, and another field to consider whether a lattice node is a frequent closed itemset or not. MNARs are only mined from a minimal generator X to frequent closed itemset Y such that X⊂Y. The experiments show that the mining time from FIL is more effective than that from frequent closed itemsets.
Keywords: frequent closed itemsets; FIL; frequent itemsets lattice; mGs; minimal generators; MNARs; minimal non-redundant association rules; association mining; data mining.
International Journal of Intelligent Systems Technologies and Applications, 2011 Vol.10 No.1, pp.92 - 106
Received: 03 Jan 2010
Accepted: 15 Mar 2010
Published online: 25 Jan 2011 *