Mining at most top-K% mixed-drove spatiotemporal co-occurrence patterns
Zhanquan Wang, Xuanhuang Peng, Chunhua Gu, Bingqiang Huang · 2013
Discovering MDCOPs is an important problem with many spatio-temporal applications such as identifying planning and strategy in battlefield and tracking predator-prey interactions. However, it is hard to determine the appropriate interest measure thresholds. In the paper, the problem of mining at most top-K% MDCOPs without using user-defined thresholds is defined, and a novel mining algorithm based on time aggregated graph is proposed. Analytical and experimental results show that the TopMDCOP Graph Miner without thresholds is correct and complete. Results show the proposed algorithm is computationally more efficient than the naive algorithm by using a new storage method to mine, it's proved to be effective and validate in the real world. This electronic document is a “live” template and already defines the components of your paper [title, text, heads, etc.] in its style sheet.