作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2008, Vol. 34 ›› Issue (3): 29-31. doi: 10.3969/j.issn.1000-3428.2008.03.011

• 博士论文 • 上一篇    下一篇

基于CAN-树的高效关联规则增量挖掘算法

邹力鹍,张其善   

  1. (北京航天航空大学电子信息工程学院,北京 100083)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-02-05 发布日期:2008-02-05

Efficient Incremental Association Rules Mining Algorithm Based on CAN-tree

ZOU Li-kun, ZHANG Qi-shan   

  1. (School of Electronics and Information Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100083)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-02-05 Published:2008-02-05

摘要: 关联规则是数据挖掘领域的一个重要研究方向。针对关联规则的增量挖掘问题,该文提出一种快速算法FIAFAR。算法使用CAN-树存储原始交易数据库,弥补了FP-树的不足,适应于增量挖掘以及最小支持度变化的情况。采用子父节点指针的设计,可以快速生成条件模式树,提高算法的效率。实验验证了算法的有效性。

关键词: 数据挖掘, 关联规则, 条件模式树, 指针

Abstract: Finding association rules is a major aspect of data mining research. An efficient algorithm FIAFAR is proposed to deal with incremental mining of association rules. Algorithm is based on the CAN-tree structure, overcomes the shortcomings of FP-tree which it is not suitable for incremental mining and minimum support varying. The children to parent pointer is used in algorithm instead of parent to children pointer. It helps algorithm FIAFAR build conditional pattern tree effectively and improves the efficiency of algorithm in consequence. Experimental results show that the new algorithm is effective for large databases.

Key words: data mining, association rule, condition pattern tree, pointer

中图分类号: