Clustering Analysis of Moving Objects

Abstract

In many moving objects management applications, realtime data analysis such as clustering analysis is becoming one of the most important requirements. Most spatial clustering algorithms deal with objects in Euclidean space. In many real-life applications, however, the accessibility of spatial objects is constrained by spatial networks (e.g., road networks). It is therefore more realistic to work on clustering objects in a road network. The distance metric in such a setting is redefined by the network distance, which has to be computed by the expensive shortest path distance over the network. The existing methods are not applicable to such cases. Therefore, we use the information of nodes and edges in the network to present two new static clustering algorithms that prune the search space and avoid unnecessary distance computations. In addition, we present the problem of clustering moving objects in spatial networks and propose a unified framework to address it. The goals are to optimize the cost of clustering moving objects and support multiple types of clusters in a single application.