SPHLU: An Efficient Algorithm for Processing PR k NN Queries on Uncertain Data

Query on uncertain data has received much attention in recent years, especially with the development of Location‐based services (LBS). Little research is focused on reverse k nearest neighbor queries on uncertain data. We study the Probabilistic reverse k nearest neighbor (PR k NN) queries on uncertain data. It is succinctly shown that, PR k NN query retrieves all the points that have higher probabilities than a given threshold value to be the Reverse k ‐nearest neighbor (R k NN) of query data Q . The previous works on this topic mostly process with k> 1. Some algorithms allow the cases for k > 1, but the efficiency is inefficient especially for large k . We propose an efficient pruning algorithm — Spatial pruning heuristic with louer and upper bound (SPHLU) for solving the PR k NN queries for k > 1. The experimental results demonstrate that our algorithm is even more efficient than the existent algorithms especial for a large value of k .