On Discovery of Spatiotemporal Influence-Based Moving Clusters

Abstract

A moving object cluster is a set of objects that move close to each other for a long time interval. Existing works have utilized object trajectories to discover moving object clusters efficiently. In this article, we define a spatiotemporal influence-based moving cluster that captures spatiotemporal influence spread over a set of spatial objects. A spatiotemporal influence-based moving cluster is a sequence of spatial clusters, where each cluster is a set of nearby objects, such that each object in a cluster influences at least one object in the next immediate cluster and is also influenced by an object from the immediate preceding cluster. Real-life examples of spatiotemporal influence-based moving clusters include diffusion of infectious diseases and spread of innovative ideas. We study the discovery of spatiotemporal influence-based moving clusters in a database of spatiotemporal events. While the search space for discovering all spatiotemporal influence-based moving clusters is prohibitively huge, we design a method, STIMer, to efficiently retrieve the maximal answer. The algorithm STIMer adopts a top-down recursive refinement method to generate the maximal spatiotemporal influence-based moving clusters directly. Empirical studies on the real data as well as large synthetic data demonstrate the effectiveness and efficiency of our method.