Cascade modelling for predicting solubility index of roller dried goat whole milk powder

Abstract

The aim of this work was to investigate the prediction ability of Cascade artificial neural network (ANN) models for solubility index of roller dried goat whole milk powder. The input variables for ANN model were: loose bulk density, packed bulk density, wettability and dispersibility, while solubility index was the output variable. Mean square error, root mean square error, coefficient of determination and Nash - sutcliffo coefficient were used as performance measures. Modelling results indicated very good agreement between the actual and the predicted data, thus confirming that ANN could be used to predict solubility index of roller dried goat whole milk powder.