Skip to Main Content
A data stream is a massive unbounded sequence of data elements continuously generated at a rapid rate. Consequently, the knowledge embedded in a data stream is more likely to be changed as time goes by. Frequent pattern is a kind of data mining techniques discovered knowledge and has been widely studied over the last decade. There are several models and approaches for mining such knowledge, but all previous works only consider a static length of sliding window for mining frequent itemsets. We propose a multiple slidng windows for mining frequent patterns on data stream in this paper. The details of study scope are as follows. We propose an efficient discounting method with different lengths of time-sensitive sliding-window. This discounting method doesn't lose the information about Acount and also saves much memory space. Finally, we implement and evaluate the proposed algorithms for mining frequent itemsets on data stream.
Date of Conference: 22-24 Aug. 2007