摘要
发现最大项目频集是数据挖掘应用中的关键问题。本文提出了一个基于反向矩阵的最大频集的交互式挖掘算法。该算法将事务数据库转换成反向矩阵,缩小了候选子集,利于交互式挖掘。通过对每个频繁项独立建立COFI 树,减少了挖掘中对内存容量的依赖。
Discovering maximal frequent itemsets is a key problem in data mining applications.In this paper ,an algorithm based on inverted matrix for interactive mining is proposed.Using the unique transforming transactional database into inverted matrix ,the number of candidate itemsets is greatly decreased, therefore it is advantageous for interactive mining. According to building independent COFI-tree to frequent itemset, that is less reliance on memory size.
出处
《计算机与现代化》
2005年第3期1-4,共4页
Computer and Modernization
