Diversity Role in Designing Multiple Classifier Systems Using MATLAB

Multiple Classi¿ers Systems (MCS) perform in formation fusion of classi¿cation decisions at different levels overcoming limitations of traditional approaches based on single classi¿ers. We address one of the main open issues about the use of Diversity in Multiple Classi¿er Systems: the effectiveness of the explicit use of diversity measures for creation of classi¿er ensembles. So far, diversity measures have been mostly used for ensemble pruning, namely, for selecting a subset of classi¿ers out of an original, larger ensemble. Here we focus on pruning techniques based on forward selection, since they allow a direct comparison with the simple estimation of accuracy of classi¿er ensemble. We empirically carry out this comparison for several diversity measures and bench mark data sets, using bagging as the ensemble construction technique, and majority voting as the fusion rule.