摘要
利用有向项集图来存储事务数据库中有关频繁项集的信息,提出了有向项集图的三叉链表式存储结构和基于有向项集图的最大频繁项集挖掘算法。它不仅实现了事务数据库的一次扫描,减少了I/O代价,而且可以同时解决好稀疏数据库和稠密数据库的最大频繁项集挖掘问题。
This paper presented the directed itemsets graph to store the information of frequent itemsets of transaction databases, and put forward the trifurcate linked list storage structure of directed itemsets graph, and provided the mining algorithm of maximal frequent itemsets based on directed itemsets graph. It not only realized scanning databases only one time and decreased I/O resources consumption, but also resolved the question of mining maximal frequent itemsets in the sparse and dense databases at the same time.
出处
《计算机应用研究》
CSCD
北大核心
2007年第11期43-45,99,共4页
Application Research of Computers
基金
国家自然科学基金资助项目(70471056)
关键词
数据挖掘
关联规则
最大频繁项集
有向项集图
三叉链表式存储结构
挖掘算法
data mining
association rules
maximal frequent itemsets
directed itemsets graph
trifurcate linked list storage structure
mining algorithm
