No abstract

Spatiotemporal databases emerge as an evolving scientific field due to a great variety of applications, tracking mobile objects being one of them. For this purpose, a number of methods have been proposed to efficiently organize and index moving objects and answer spatiotemporal queries. The majority of all these methods are addressing either the past or the future movement of the moving objects. Up until now, addressing both the past and the future movement of the objects in an integrated manner has rarely appeared in the literature. In the current paper, based on a spatiotemporal access method, the XBR-tree, we propose algorithms for the efficient processing of spatiotemporal window (past) and timestamp (past, present and future) queries. Moreover, we experimentally study the efficiency of processing these queries based on the XBR-tree against using an existing structure, the R P P F -tree.

Tracking of mobile objects trajectories is one of many modern applications supported by Spatiotemporal databases. Within the context of this application, queries about the present, future or past positions of the objects need to be answered. Several indexing methods have been proposed to efficiently handle such spatiotemporal queries. In the current paper, we propose a method for indexing the historic (past) positions of moving objects called XBR-tree, a quadtree-like technique that is able to handle both timestamp and window queries. Moreover, we compare experimentally this with other methods proposed in the literature for the same purpose. In particular, we compare XBR-trees with PMR-trees, structures also related to quadtrees and MV3R-trees, R-tree based structures.

No abstract

In databases of moving objects it is important to answer queries that concern the future positions of the objects. An important query type in such an environment is the nearest-neighbor query, which asks for the k closest objects of a query object during a time interval [t s , t e ]. However, there are cases where the (k+1)-th nearest-neighbor is requested after the execution of the k-NN query. In such a case, either the query must be evaluated again, or we can exploit the previous result and use an incremental method to determine the new answer. We focus on the second alternative and present efficient incremental algorithms that outperform the trivial method which is based on complete re-execution of the query. In addition, we study the problem of keeping the query result consistent in the presence of object insertions, deletions and updates which are very common in a dynamic moving-object environment.