CLOUD CLASSIFICATION USING ERROR-CORRECTING OUTPUT CODES

Novel artificial intelligence methods are used to classify 16x16 pixel regions (obtained from Advanced Very High Resolution Radiometer (AVHR R) images) in terms of cloud type (e.g., stratus, cumulus). We previou sly reported that intelligent feature selection methods, combined with nearest neighbor classifiers, can dramatically improve classification accuracy on this task. Our subsequent analyses of the confusion matri ces revealed that a small number of confusable classes (e.g., cirrus a nd cirrostratus) dominated the classification errors. We conjectured t hat, if the class labels in the data were re-represented so that these cloud classes are more easily distinguished, then additional accuracy gains might result. We explored this hypothesis by replacing each cla ss label with a set of error-correcting output codes, a general techni que applicable to any classification algorithm for tasks with at least three classes. Our initial results are promising; error correcting co des significantly increased classification accuracy compared with usin g standard representations for class labels. To our knowledge, this is the first successful integration of a k-nearest neighbor classifier a nd error-correcting output codes (i.e., where k is, effectively, small ). One conclusion is that environmental scientists should always selec t, for their classification tasks, a classifier that reduces both vari ance and learning bias.