2000 | OriginalPaper | Buchkapitel
Discovery of Generalized Association Rules with Multiple Minimum Supports
verfasst von : Chung-Leung Lui, Fu-Lai Chung
Erschienen in: Principles of Data Mining and Knowledge Discovery
Verlag: Springer Berlin Heidelberg
Enthalten in: Professional Book Archive
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Mining association rules at multiple concept levels leads to the discovery of more concrete knowledge. Nevertheless, setting an appropriate minsup for cross-level itemsets is still a non-trivial task. Besides, the mining process is computationally expensive and produces many redundant rules. In this work, we propose an efficient algorithm for mining generalized association rules with multiple minsup. The method scans appropriately k+1 times of the number of original transactions and once of the extended transactions where k is the largest itemset size. Encouraging simulation results were reported.