Probabilistic Group Nearest Neighbor Queries in Uncertain Databases

Abstract

The importance of query processing over uncertain data has recently arisen due to its wide usage in many real-world applications. In the context of uncertain databases, previous work have studied many query types such as nearest neighbor query, range query, top-$k$ query, skyline query, and similarity join. In this paper, we focus on another important query, namely probabilistic group nearest neighbor query (PGNN), in the uncertain database, which also has many applications. Specifically, given a set, Q, of query points, a PGNN query retrieves data objects that minimize the aggregate distance (e.g. sum, min, and max) to query set Q. Due to the inherent uncertainty of data objects, previous techniques to answer group nearest neighbor query (GNN) cannot be directly applied to our PGNN problem. Motivated by this, we propose effective pruning methods, namely spatial pruning and probabilistic pruning, to reduce the PGNN search space, which can be seamlessly integrated into our PGNN query procedure. Extensive experiments have demonstrated the efficiency and effectiveness of our proposed approach, in terms of the wall clock time and the speed-up ratio against linear scan.