Predicting Total Acceptance of Ice Cream Using Artificial Neural Network

Artificial neural network (ANN) models were used to predict the total acceptance of ice cream. The experimental sensory attributes (appearance, flavor, body and texture, coldness, firmness, viscosity, smoothness and liquefying rate) were used as inputs and independent total acceptance was output of ANN. Thirty, ten and sixty percent of the sensory attributes data were used to train, validate and test the ANN model, respectively. It was found that ANN with one hidden layer comprising 10 neurons gives the best fitting with the experimental data, which made it possible to predict total acceptance with acceptable mean absolute errors (0.27) and correlation coefficients (0.96). Sensitivity analysis results showed that flavor and texture were the most sensitive sensory attribute for prediction of total acceptance of ice cream. These results indicate that ANN model could potentially be used to estimate total sensory acceptance of ice cream. Practical Applications ANN techniques appear to be very applicable tools to overcoming some of the difficulties in sensory evaluation. The overall agreement between ANN predictions and experimental data was very good for sensory acceptance of ice cream. Therefore, this method can be applied to relevant sensory projects with satisfactory results.