Application of artificial neural network (AAN) for prediction of sensible and latent heat losses from a cow

Abstract

Artificial Neural Network (ANN) based on feed-forward backpropagation model is used to predict sensible and latent heat losses from the wet-skin surface and fur layer of a cow. A mathematical model is used to generate training data to train the neural network. The predicted skin temperatures, latent, convective, radiative, sensible and total heat losses due to the change in the level of wetness, air velocity, relative humidity and ambient air temperature using ANN agree very closely with those obtained from the mathematical model used in the analysis.