Composite Spatio-Temporal Co-occurrence Pattern Mining

Spatio-temporal co-occurrence patterns (STCOPs) represent subsets of features that are located together in space and time. Mining such patterns is important for many spatio-temporal application domains. However. a co-occurrence analysis across multiple spatio-temporal datasets is computationally expensive When the dimension of the time series and number of locations in the spaces are large. In this paper We first, defined STCOPs and the STCOPs mining problem. We proposed a monotonic composite measure, which is the composition of the spatial prevalence and temporal prevalence measures. A novel and computationally efficient algorithm, COSTCOP+, is presented by applying the composite measure. We proved that the proposed algorithm is correct and complete in finding STCOPs. Using a real dataset, the experiments illustrate that the algorithm is efficient.