New Policy of Maximal Frequent Itemsets in Data Stream Mining

摘要

According to the features of data streams and combined sliding window, a new algorithm A-MFI which is based on self-adjusting and orderly-compound policy for mining maximal frequent itemsets in data stream is proposed. This algorithm which is based on basic window updates information from data stream flow fragments and scans the stream only once to gain and store it in frequent itemsets list when the data stream flows. The core idea of this algorithm: construct self-adjusting and orderly-compound FPtree, use mixed subset pruning techniques to reduce the search space, merge nodes which has equal minsup in the same branch and compress to generate the orderly-compound FP-tree to avoid superset checking when mining maximal frequent itemsets. The experimental results show that the algorithm has higher efficiency in time and space, and also has good scalability.