Multilayer perceptron neural networks and radial-basis function networks as tools to forecast accumulation of deoxynivalenol in barley seeds contaminated with Fusarium culmorum

Abstract

The capacity of multi-layer perceptron artificial neural networks (MLP-ANN) and radial-basis function networks (RBFNs) to predict deoxynivalenol (DON) accumulation in barley seeds contaminated with Fusarium culmorum under different conditions has been assessed. Temperature (20-28 °C), water activity (0.94-0.98), inoculum size (7-15 mm diameter), and time were the inputs while DON concentration was the output. The dataset was used to train, validate and test many ANNs. Minimizing the mean-square error (MSE) was used to choose the optimal network. Single-layer perceptrons with low number of hidden nodes proved better than double-layer perceptrons, but the performance depended on the training algorithm. The RBFN reached lower errors and better generalization than MLP-ANN but they required a high number of hidden nodes. Accurate prediction of DON accumulation in barley seeds by F. culmorum was possible using MLP-ANNs or RBFNs. © 2010 Elsevier Ltd.