Multi-stream join answering for mining significant cross-stream correlations

Abstract

Sliding-window multi-stream join (SWMJ) is a fundamental operation for correlating information from different streams. We provide a solution to the problem of assessing significance of the SWMJ result by focusing on the relative frequency of windows satisfying a given equijoin predicate as the most important parameter of the SWMJ result. In particular, we derive an analytic formula for computing the average relative frequency of windows satisfying a given equijoin predicate that can be evaluated in quadratic time in the window size given a probabilistic model of the multi-stream. In experiments we demonstrated remarkable accuracy of our method, which confirmed our theoretical analysis. © 2010 IEEE.