ERC - evolutionary resample and combine for adaptive parallel training data set selection

We introduce evolutionary resampling and combine (erc) – a genetic algorithm based selection scheme for training examples for a multilayer perceptron (MLP) classifier. The erc method is compared to various adaptive resample and combine techniques arc-fs, arc-lh and arc-x4. To diminish the dependencies on the size of the training data set (TDS) and the missing consideration of test set performance common to all arc methods we present erc being based on evaluation of performance on a validation data set (VDS). Combination of classifiers is performed by all arc methods so as to reduce classifiers’ variance, thus, erc also utilizes classifier combination schemes. All algorithms are compared for a real–world problem, the classification of high resolution interferometric synthetic aperture radar (InSAR) data into several land–cover classes.