Mining spatial dynamic co-location patterns

Spatial co-location pattern mining is an important part of spatial data mining, and its purpose is to discover the coexistence spatial feature sets whose instances are frequently located together in a geographic space. So far, many algorithms of mining spatial co-location pattern and their corresponding expansions have been proposed. However, dynamic co-location patterns have not received attention such as the real meaningful pattern {Ganoderma lucidum new, maple tree dead} means that “Ganoderma lucidum“ grows on the “maple tree“ which was already dead. Therefore, in this paper, we propose the concept of spatial dynamic co-location pattern that can reflect the dynamic relationships among spatial features and then propose an algorithm of mining these patterns from the dynamic dataset of spatial new/dead features. Finally, we conduct extensive experiments and the experimental results demonstrate that spatial dynamic co-location patterns are valuable and our algorithm is effective.