Feedforward multilayer machine learning artificial neural network (ANN) models were established for predicting shelf life of processed cheese stored at 7-8o C. Soluble nitrogen, pH, standard plate count, yeast & mould count, and spore count were input variables, and sensory score was the output variable. Mean Square Error, Root Mean Square Error, Coefficient of Determination and Nash–Sutcliffe Coefficient were used for comparing the prediction ability of the developed models. Feedforward ANN model with combination of 5à16à16à1 simulated best with high R2: 0.998717294, suggesting that multilayer machine learning models can predict shelf life of processed cheese.
Two new Bulgarian selected hybrid sweet cherry cultivar candidates (El.17-90 ‘Asparuh’ and El.17-37 ‘Tzvetina’ Fruit Growing Institute, Plovdiv, Bulgaria) and one standard cultivar (Bing) were chitosan treated and stored in refrigerator at 4°C for 21 days, up to the endpoint of the experimental shelf-life time. Chitosan-Ca-lactate (multicomponent) and Chitosan-alginate (bi-layer) edible coating treatments were applicate in these experiments. The used coating formulas are bio compatibles, non-toxics and have antimicrobial activities. The sample series (five replicates with thirty fruits from each cultivar and each treatment, and a control) were inspected weekly based on the appearance. The healthy and intact fruits were tested for physical (visual sorting, weight loss and texture of the intact fruits), physico-chemical (refractometrical dry content, antioxidant activity, pH of the pulp), and microbiological properties (total number of microorganisms, E. coli, fungi and yeasts). At th...