Feature selection for ensembles:a hierarchical multi-objective genetic algorithm approach

Feature selection for ensembles has shown to be an effectivestrategy for ensemble creation. In this paper we presentan ensemble feature selection approach based on a hierarchicalmulti-objective genetic algorithm. The first level performsfeature selection in order to generate a set of goodclassifiers while the second one combines them to providea set of powerful ensembles. The proposed method is evaluatedin the context of handwritten digit recognition, usingthree different feature sets and neural networks (MLP) asclassifiers. Experiments conducted on NIST SD19 demonstratedthe effectiveness of the proposed strategy.