Multi-objective optimization of base classifiers in StackingC by NSGA-II for intrusion detection

Multiple Classifier Systems are often found to be useful for improving individual results by combining a set of classifier decisions where a single base level classifier may not achieve the same level of results. However not every set of base classifiers improve results, therefore a selection of a set of classifiers is required. The process of selecting base level classifiers for a multiple classifier system may be performed by the use of a Genetic Algorithm. The aim of this work is the selection of optimal sets of base level classifies using an evolutionary computation approach. In addition, a comparative analysis is made of the performance of the generated ensembles against the individual base level classifiers.