Stream data arrives dynamically when stream continues, which cannot be reflected by the traditional transaction-based sliding window, so the processing efficiency is low. We build a timestamp-based sliding window model and propose a frequent itemset mining algorithm named FIMS. In this algorithm, we use an enumeration tree to store the data synopsis, as a result, the computational pruning can be conducted. The experimental results over a dataset present that our algorithm is effective and efficient.
展开▼