A LRT framework for fast spatial anomaly detection

Given a spatial data set placed on an n ? n grid, our goal is to find the rectangular regions within which subsets of the data set exhibit anomalous behavior. We develop algorithms that, given any usersupplied arbitrary likelihood function, conduct a likelihood ratio hypothesis test (LRT) over each rectangular region in the grid, rank all of the rectangles based on the computed LRT statistics, and return the top few most interesting rectangles. To speed this process, we develop methods to prune rectangles without computing their associated LRT statistics. Categories and Subject Descriptors H.2.8 [Database Management]: Database application--data mining, spatial databases and GIS General Terms Algorithms, Experimentation

• Type: Conference
• Year: 2009
• Where: KDD
• Authors: Mingxi Wu, Xiuyao Song, Chris Jermaine, Sanjay Ranka, John Gums
• Keywords: Arbitrary Likelihood Function, Computed Lrt Statistics, Data Mining, KDD 2009, Likelihood Ratio Hypothesis