Shelflife Prediction of Processed Cheese Using Artificial Intelligence ANN Technique

Radial Basis (Fewer Neurons) and Multiple Linear Regression (MLR) models were developed and compared for predicting the shelf life of processed cheese stored at 30o C. Soluble nitrogen, pH, Standard plate count, yeast & mould count, and spore count were taken as input parameters, and sensory score as output parameter. Mean square error, Root mean square error, Coefficient of determination (R2) and Nash - Sutcliffocoefficient (E2) were applied in order to compare the prediction ability of the models. Results showed high correlation between the training and validation data with high R2 and E2 values; thus suggesting that the developed models are efficient for predicting the shelf life of processed cheese. From the study, it was revealed that Radial Basis (Fewer Neurons) model was superior over MLR model for predicting the shelf life of processed cheese