PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Outlier Detection in Benchmark Classification Tasks
Hongyu Li and Mahesan Niranjan
In: IEEE ICASSP'06, Toulouse, France(2006).


We present a new outlier detection method which is appropriate for classification problems. It combines estimating the overall probability density and sequential ranking of the data according to observed changes in performance on validation sets. The method has been implemented on ten widely used benchmark datasets and a spam email filtering application. Evaluated by six popular machine learning methods, classification performances are shown to improve after removing outliers in comparison to removing the same number of examples at random from the datasets.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:2276
Deposited By:Li Hongyu
Deposited On:16 October 2006