Mozzarella cheese was placed in two types of packaging materials (Cryovac, P1 and linear low density polyethylene/BA/Nylon-6/BA/Low density polyethylene, P2) under 5 different atmospheres, air (A1), vacuum (A2), 100% CO2 (A3), 100% N2 (A4) and mixture of 50% N2 and 50% CO2 (A5). The product was evaluated periodically for microbiological quality. Among the different gases studied, A3 showed minimum microbial count during storage, thus proving superior followed by A5, A4, A2 and A1.

The purpose of this study is to develop artificial neural network (ANN) models for predicting shelf life of processed cheese stored at 7-8ºC. Body & texture, aroma & flavour, moisture and free fatty acids were taken as input parameters, and sensory score as output parameter for developing the models. The developed Cascade single layer ANN models were compared with each other. Bayesian regularization was used for training ANN models. Network was trained with 100 epochs, and neurons in each hidden layer(s) varied from 3 to 20.  Cascade ANN models very well predicted the shelf life of processed cheese.

No abstract

Soft mouth melting milk cakes from water buffalo milk were prepared by using milk collected from Experimental Dairy, National Dairy Research Institute, Karnal, India. This milk was standardized to 6% fat. Time-delay and linear layer (design) intelligent computing expert system models were developed for predicting shelf life of soft mouth melting milk cakes stored at 6 o C. Linear layer (design) model gave best outcomes (MSE: 0.000293366, RMSE: 0.017127919, R 2 : 0.996479613).Regression equations were developed based on these outcomes, shelf life was predicted 49.54 days. The predicted value is close to the experimentally obtained shelf life of 50 days. Therefore, from the study it is concluded that intelligent computing expert system models are effective tool predicting the shelf life of soft mouth melting milk cakes.

No abstract