频繁项集快速挖掘及更新算法

为了克服Apriori发现频繁项集存在的问题,提出了一种基于三维项集矩阵和向量(TIMV)的频繁项集挖掘算法.该算法摆脱了Apriori框架的束缚,仅需扫描数据库一次,不产生候选项目集.当事务数据库和最小支持度发生变化时,该算法只需重新遍历一次项集矩阵,即可得到新的频繁项集.实验结果表明,算法能有效提高频繁项目集的挖掘和更新效率.

Fast Mining and Updating Frequent Itemsets

In order to overcomee the drawbacks of Apriori algorithm for mining maximum frequent itemsets,TIMV algo- rithm was proposed,which use three-dimensional itemsets matrix and vectors.TIMV only needs scan the database one time,does not create candidate item.sets.The algorithm can get the new frequent itemsets through search three-dimen- sional itemsets matrix,when the database and the minimum support are changed.Theory analysis and experimental re- sults show the feasibility and effectiveness of the algorithm.