数据流中一种基于滑动窗口的前K个频繁项集挖掘算法

数据流频繁项集挖掘是当今数据挖掘和知识学习领域重要的研究课题之一。数据流高速性、连续性、无界性、实时性对挖掘算法在时间和空间方面提出了更高的要求。传统的数据挖掘算法由于其存储结构需要频繁地维护,其挖掘方式的精度和速度较低,空间、时间效率不高。在基于粒计算和ECLAT算法的基础上提出一种挖掘数据流滑动窗口中top-K频繁项集算法,采用二进制方式存储项,利用位移运算实现增量更新,实施与运算计算项集支持度,同时利用二分查找法插入到项目序表中,输出前K个频繁项。实验结果表明,该算法在K取值不太高时具有较好的时空高效性。

Alogrithm for mining top-K frequent itemsets over sliding window in data streams

Frequent itemset mining over data streams is a hot topic in data mining and knowledge discovery.The features of data streams,such as consecution,unboundedness and real-time,raise requirements for higher time and space performance of mining algorithms.The storage structure of the present algorithms need to be revised continually.Otherwise,the accuracy and rate of the present algorithms are low.The above two reasons lead up to disadvantage impact on both time and space efficiency.This paper designed a frequen...