RESEARCH ON DYNAMIC GENERATING ALGORITHMS OF LARGE ITEMSETS OF DISTRIBUTIVE DATA MINING ARCHITECTURE

摘要：

Dynamic generating algorithms of association rules mined large itemsets are presented in this paper. According to the distributive data mining calculation architecture, database is replaced by an order set enumerate tree, and the information of all transactions are kept in the dynamic generating trees. Meantime, the generating enumerate trees flowing a local node of transaction orderly is ensured. The storage and communication traffic are reduced greatly.Therefore, the local space is saved, and the disk operation is reduced through the generating algorithms of large itemsets.By examples and performance analysis of the dynamic generating algorithms introduced, the store space of processed nodes is cut down, and the calculation time of support is also reduced through the traversal process of tree. Thereby, the calculation efficiency of search is improved greatly.

关键词： Data mining association rules set enumerate trees generating algorithms

作者: YING-WU FANG YI WANG PENG-YANG LI YAN-JUN LU XIU-BIN ZHAO HUI XU

作者单位: The Telecommunication Engineering Institute, Air Force Engineering University, Xian, 710077, China School of Machinery and Precision Instrument Engineering, Xian University of Technology, Xian, 710

会议类型: 国际会议

会议名称: 2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)

会议地点: 大连

会议语种:英文

页码: 1314-1319

在线出版日期: 2006-08-13（万方平台首次上网日期，不代表论文的发表时间）