Modeling, storing and mining moving object databases

Urban areas get more and more congested everyday due to the increasing number of moving vehicles. This imposes the need for efficient analysis, modeling, and processing of traffic data. Moreover, the extraction of additional information about traffic conditions, optional routes and the possible prediction of troublesome situations, such as traffic jams, becomes necessary. In this work, we describe the analysis, pre-processing, modeling, and storage techniques for trajectory data that constitute a Moving Object Database (MOD). MOD is the backbone of the IXNHLambdaATHSigma ('PATH-FINDER' in Greek) system, which specifically focuses on extracting further information about the movement of vehicles in the Athens municipal area. Based on real-world requirements, we initially analyse the traffic data and make modeling decisions to capture these requirements in a MOD. We then design MOD focusing on the spatiotemporal concepts, relations and restrictions among the characteristic concepts of the system - namely, the vehicles, trajectories, and roads. Furthermore, specific, innovative pre-processing, design, and storage techniques for the trajectory data in MOD are given. Then, we present the architecture of IXNHLambdaATHSigma; its core components are the characteriser, cluster finder, and associator, which are used to perform data extraction in MOD. A mining language to accommodate typical data extraction queries is presented, in terms of syntax and semantics. Answers to characteristic, complex questions on MOD, which are based on real-world data about traffic in the Athens Metropolitan Area, show the applicability of the approach.