Title :
A new matrix-based association rules mining algorithm
Author_Institution :
Comput. Dept., Shandong Police Coll., Jinan, China
Abstract :
A new association rules mining algorithm is put forward in this paper,The algorithm directly generate k-itemsets using an idea of (k-1)-itemsets vector and the corresponding matrix multiplication sequentially. Realize Itemsets spanning search and connection. The whole process only scans the database once and don´t produce candidate itemsets. Experiment shows that the algorithm greatly improves the efficiency of data mining.
Keywords :
data mining; matrix multiplication; vectors; data mining; itemsets spanning connection; itemsets spanning search; itemsets vector; k-itemsets generation; matrix multiplication; matrix-based association rules mining algorithm; Algorithm design and analysis; Association rules; Indexes; Itemsets; Vectors; association rule; data mining; frequent itemsets; matrix;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery (FSKD), 2012 9th International Conference on
Conference_Location :
Sichuan
Print_ISBN :
978-1-4673-0025-4
DOI :
10.1109/FSKD.2012.6234129
