Co-location Detector: A System to Find Interesting Spatial Co-locating Relationships

摘要

Data Mining develops from original transactional data to current spatial data, this trend indicates that the data is getting more complex and the mining algorithms require better performances. Co-location patterns describe the subsets of features whose instances are prevalently located together in geographic space. Co-location mining algorithms are to find prevalent (interesting) co-location patterns with some thresholds given by the user. Co-location Detector is a system which improves the join-less algorithm and optimizes some details, it owns friendly interactive interface and good operational experiences, visualizes the co-location patterns for the user to process the next decision, besides, the user can change his input parameters to compare the results in order to mine more valuable information.