Every day, new and existing spatial databases, are populated by data from sensors, satellites and other devices providing spatial references. In this enormous flow of data, valuable and interesting patterns can be hidden. For researchers, one of the common tasks is to discover spatial collocations, i.e. subsets of spatial features that are frequently located together in space. The most widely known algorithm has been proposed by Shekhar et al. It is based on a step of spatial neighborhood materialization and a join-less generation of candidate instances, which are filtered in the remaining algorithm steps. We identified one of these steps to be a potential bottleneck of the algorithm. In this paper, we address the problem of efficient filtering of non clique instances and we propose to expand this task by applying hash join techniques. We have implemented and tested the aforementioned solution and shown that it results in better performance of the algorithm.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.