首页|Prediction of fungal infestation in stored barley ecosystems using artificial neural networks
Prediction of fungal infestation in stored barley ecosystems using artificial neural networks
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NSTL
Elsevier
Predictive models describing the kinetics of fungal growth and thus the risk of mycotoxin formation in mass of grain are promising prognostic tools that may be used in postharvest management systems. In the study an artificial neural network (ANN) based on the multilayer perceptron (MLP) topology was used to evaluate the fungal population in barley grain stored under different temperature and water activity conditions (T = 12-30 degrees C and a(w) = 0.78-0.96). The impact of the number of neurons in the hidden layer and the type of activation functions in neurons of the hidden and output layers on the model prediction quality were analysed. The best architecture was the network containing five neurons in the hidden layer and the hyperbolic tangent function in neurons of the hidden layer and the linear one in the output. Statistical criteria used to evaluate the model performance showed its high precision and prediction accuracy. The results indicate that ANNs may be useful tools in predictive modelling of fungal development in a bulk of stored grain that may be used in postharvest management systems.
NSTL
Elsevier
