Performance Of Generalized Regression,Radial Basis(Fewer Neurons), And Linear Layer (Design) Computational ANN Techniques For Shelf Life Prediction of Processed Cheese

Generalized Regression, Radial Basis(Fewer neurons) and Linear Layer(Design) Artificial Neural Network models were developed and compared with each other for predicting shelf life of processed cheese stored at 30o C. Body and texture, aroma and flavour, moisture, and free fatty acids were input parameters and sensory score was taken as output parameter for all the models. Mean Square Error, Root Mean Square Error, Coefficient of Determination and Nash - Sutcliffo Coefficient were used in order to compare the prediction ability of the developed models. Further regression equations were developed for determining shelf life of the product, which came out to be 29.49 days, as against experimentally determined 30 days. Performance Of Generalized Regression,Radial Basis(Fewer Neurons), And Linear Layer (Design) Computational ANN Techniques For Shelf Life Prediction of Processed Cheese