概率可视最近邻查询算法

针对不确定对象的可视最近邻查询问题，对不确定Voronoi图的性质进行分析，提出多层邻接生成点和多层不确定Voronoi区域等概念，给出判断概率可视最近邻的理论方法，并提出基于不确定Voronoi图的概率可视最近邻查询算法，该算法通过直接确定参与查询的概率可视最近邻的范围以及参与可视性判断的障碍集的范围，避免了索引遍历时大量的比较计算和剪枝操作，采用真实数据集和模拟数据集对提出的算法进行了性能分析，实验结果表明，提出的算法能够有效地处理不确定对象的可视最近邻查询．

Algorithm of Probabilistic Visible Nearest Neighbor Queries

In consideration of the problem of visible nearest neighbors for uncertain objects, the characteristics of uncertain-voronoi diagram are analyzed. The concepts such as muhilayer adjacent generator and multilayer uncer- tain-voronoi region are proposed. The theories that evaluate the probabilistic visible nearest neighbors are put for- ward, and the algorithm is presented which deals with the probabilistic visible nearest neighbor queries based on uncertain-voronoi diagram. The algorithm can directly determine the scope of probabilistic visible nearest neighbors participated in query processing and the range of obstruction sets participating in visual judgment, which reduced a large number of calculation and pruning operation when traversing index. The performance of the algorithm is ana- lyzed by using both real and synthetic data sets, and the experimental results show that the algorithm presented can deal with the queries of visible nearest neighbors for uncertain objects effectively.