Fast Distributed Algorithm of Mining Global Frequent Itemsets

被引：0

作者：

He, Bo ^{[1
]}

机构：

[1] ChongQing Univ Technol, Sch Comp Sci & Engn, Chongqing 400054, Peoples R China

来源：

ADVANCED RESEARCH ON INFORMATION SCIENCE, AUTOMATION AND MATERIAL SYSTEM, PTS 1-6 | 2011年 / 219-220卷

关键词：

Data mining; Global frequent itemsets; FP-tree;

D O I：

10.4028/www.scientific.net/AMR.219-220.191

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Most distributed algorithms of mining global frequent itemsets worked on net structure network and adopted Apriori-like algorithm. Whereas there were some problems in these algorithmsa: lot of candidate itemsets and heavy communication traffic. Aiming at these problems, this paper proposed a fast distributed algorithm of mining global frequent itemsets, namely, FDMGFI algorithm, which set centre node. FDMGFI algorithm made computer nodes compute local frequent itemsets independently with FP-growth algorithm, then the centre node exchanged data with other computer nodes and combined, finally, global frequent itemsets were gained. FDMGFI algorithm required far less communication traffic by the searching strategies of top-down and bottom-up. Theoretical analysis and experimental results suggest that FDMGFI algorithm is fast and effective.

引用

页码：191 / 194

页数：4