Classification of chestnuts with experiments on feature selection and noise

In this paper we solve the problem of classifying chestnut plants according to their place of origin; we compare the results obtained by a multi-layer perceptron with C4.5 decision tree and random forest. We will determine which features are meaningful for the classification, the achievable classification accuracy of these three classifiers families with the available features and how much the classifiers are robust to noise. We show that in this botanic domain it is possible to reduce the number of features still maintaining high the classification accuracy. Among the obtained classifiers, neural networks show the greatest robustness to noise.