Efficient Mining Algorithm of Frequent Itemsets for Uncertain Data Streams

Abstract

With the rapid development of computer technology, web services has been widely used. In these applications, the uncertain data is in the form of streams. In view of this kind of situation, present a new generalized data structure, that is, PSUF - tree, to store uncertain data streams, all itemsets in recent window are contained in global PStree in a condensed format, establish a header table in which contains dynamic array of expected value whose header table saved the same itemsets. Based on PSUF-tree, present a new mining algorithm for frequent itemsets, that is, PSUF-streaming algorithm, frequent itemsets could be mined by traversing the dynamic array, the maintaining of PSUF-tree just handles the header table corresponds to the oldest batch of itemsets in window. The experimental results show that PSUF-streaming algorithm has good efficiency and scalability, and reduce memory usage to some extent.