Outlier Detection Using Voronoi Diagram

Outlier detection is an important problem for many domains and has attracted much attention recently. The density-based method LOF is widely used in application. However, the complexity of the method is quadratic to size of the dataset, and it may miss the potential outliers when density distributions in the neighborhood are significantly different. In this paper, we propose a new outlier detection method using the Voronoi diagram, called Voronoi based Outlier Detection (VOD), to provide highly-accurate outlier detection and reduces the time complexity to O(nlogn).