NEURAL NETWORKS VS PRINCIPAL COMPONENT REGRESSION FOR PREDICTION OF WHEAT-FLOUR LOAF VOLUME IN BAKING TESTS

Neural networks (NN) provide a simple means of predicting outcomes that depend upon complex, possibly nonlinear, relationships between many variables. A trained neural network was created and used to predict loaf volume of breads made from different wheat cultivars. Although creating the NN required specialized skills and considerable computational time, using the ''trained'' NN to estimate remix loaf volume, was very rapid and required only basic computer skills. Random Centroid Optimization (RCO) was also employed to choose the best training parameters: learning rate = 0.820, smoothing factor = 0.723, noise = 0.056, number of hidden neurons = 5. NN was more accurate, faster and easier than Principal Component Regression Analysis.