扩展 WIT-树融合 Diffset 策略的频繁加权项集快速挖掘算法.

To solve the poor performance of present algorithm in mining frequent weighted itemsets (FWI) from weighted items transaction databases, this paper proposed a fast mining algorithm for FWI based on weighted itemsets-Tidset trees. Firstly, it proposed a WIT-tree structure. Then, it used minimized weighted itemsets threshold value and closed down nature to trim infrequent nodes. Finally, it used Diffset strategy to allow memory rapidly calculate the weighted support itemsets with efficient way. The experimental results show that the mining time of the proposed algorithms is significantly less than several advanced mining algorithms in mining FWI. It can save time consumption with 99.37% comparing with the Apriori-based algorithm. It can save time consumption with 99.06% comparing with weighted frequent item sets generation algorithm based on bit matrix, which indicates that proposed algorithm has clearly improved the efficiency of frequent weighted itemsets mining. [ABSTRACT FROM AUTHOR]