J4

• 计算机科学 • 上一篇    下一篇

关联规则最大频繁项目集的快速发现算法

刘大有1,2, 刘亚波1,2, 尹治东3   

  1. 1. 吉林大学计算机科学与技术学院, 长春 130012;2. 吉林大学符号计算与知识工程教育部重点实验室, 长春 130012;3. 吉林出入境检验检疫局, 长春 130062
  • 收稿日期:2003-09-28 修回日期:1900-01-01 出版日期:2004-04-26 发布日期:2004-04-26
  • 通讯作者: 刘亚波

Fast algorithm for discovering maximum frequent itemsets of association rules

LIU Da-you1,2, LIU Ya-bo1,2, YIN Zhi-dong3   

  1. 1. College of Computer Science and Technology, Jilin University, Changchun 130012, China;2. Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University,Changchun 130012, China; 3. Jilin Entry-Exit Inspection and Quarantine Bureau, Changchun 130062, China
  • Received:2003-09-28 Revised:1900-01-01 Online:2004-04-26 Published:2004-04-26
  • Contact: LIU Ya-bo

摘要: 提出一种快速发现最大频繁项目集的算法, 该算法对集 合枚举树进行改进, 结合自底向上与自顶向下的搜索策略, 利用非频繁项目集对候选最大频 繁项目集进行剪枝和降维, 减少了不必要候选最大频繁项目集的数量, 显著提高了发现的效 率.

关键词: 关联规则, 集合枚举树, 最大频繁项目集

Abstract: The present paper presents an efficient algorithm that improves set-enumeration tree and finds maximum frequent itemsets. By combining bottom-up and top-down searches in set-enumeration tree and making use of th e infrequent itemsets to prune candidates of the maximum frequent itemsets, the algorithm reduces the number of candidates of the maximum frequent itemsets gene rated by it so that the efficiency is increased.

Key words: association rule, set-enumeration tree, maximum freque nt itemset

中图分类号: 

  • TP311