Discovering Co-location Patterns in Datasets with Extended Spatial Objects

摘要

Co-location mining is one of the tasks of spatial data mining, which focuses on the detection of the sets of spatial features frequently located in close proximity of each other. Previous work is based on transaction-free apriori-like algorithms. The approach we propose is based on a grid transactionization of geographic space and designed to mine datasets with extended spatial objects. A statistical test is used instead of global thresholds to detect significant co-location patterns.