Region of Interest Mining Using Stay Point Detection and Point Region Quadtree

Abstract

Regions of Interest (RoI) mining using Point Region (PR) quadtree on near continuous movement data introduces problems as spatial partitioning process as well as RoI extraction process become computationaly high. To handle this problem, this research, proposes a method to adopt the use of stay point detection on PR quadtree for RoI mining. This research also proposes to use both the spatial and temporal aspects of the data in order to provide spatial and temporal based RoI. The evaluation of the proposed method shows that the adoption of stay point detection on PR quadtree for RoI mining reduces the computational time on spatial partitioning process and RoI extraction process. The proposed method also solves the problem in obtaining more precise RoI mining results. The evaluation also shows that the method can be used to produce more detailed RoIs that are based on both spatial dan temporal aspects of the data. Using this approach, we can see different regions of interest depending on the times of consideration.