A spatial outlier detection algorithm based multi-attributive correlation

Spatial outlier is a spatial object whose non-spatial attributive values are significantly different from the values of its neighborhood. Identification of spatial outliers can lead to the discovery of unexpected, useful spatial patterns for further analysis. Drawbacks of the existing methods are that they can only detect outliers under attributes when the attributive correlation is not considered and the normal objects tend to be falsely detected as spatial outliers when their neighborhood contains true spatial outliers. This paper presents a spatial outlier detection algorithm to overcome the disadvantages. In addition, the results demonstrated that our approach could accurately detect spatial outliers when the attributive correlation was calculated, and our approach not only avoided detecting false spatial outliers but also found true spatial outliers ignored by the existing methods in a real-world geographical data set.