Predicting Milk Shelf‐life Based on Artificial Neural Networks and Headspace Gas Chromatographic Data

Abstract

ABSTRACT The usefulness of artificial neural networks (ANN) for milk shelf‐life prediction by multivariate interpretation of gas chromatographic profiles and flavor‐related shelf‐life was evaluated and compared to principal components regression (PCR). The training set consisted of dynamic headspace gas chromatographic data collected during storage of pasteurized milk (input information for the neural network used to make a decision) and its corresponding shelflife (prediction or response). ANN had better predictability than PCR. A standard error of the estimate of 2 days in shelf‐life resulting from regression analysis of experimental vs predicted values indicated a high predictability of ANN.