The aim of the study was to compare the ability of multiple linear regression (MLR) and Artificial Neural Network (ANN) to predict the overall quality of spreadable Gouda cheese during storage at 8 °C, 20 °C and 30 °C. The ANN used five factors selected by Principal Component Analysis, which was used as input data for the ANN calculation. The datasets were divided into three subsets: a training set, a validation set, and a test set. The multiple regression models were highly significant with high determination coefficients: R 2 = 0.99, 0.87 and 0.87 for 8, 20 and 30 °C, respectively, which made them a useful tool to predict quality deterioration. Simultaneously, the artificial neural networks models with determination coefficient of R 2 = 0.99, 0.96 and 0.96 for 8, 20 and 30 °C, respectively were built. The models based on ANNs with higher values of determination coefficients and lower RMSE values proved to be more accurate. The best fit of the model to the experimental data was found for processed cheese stored at 8 °C.

The aim of the study was to prepare mathematical models based on the Arrhenius equation as predictive tools for the assessment of changes in quality parameters during the storage of spreadable Gouda cheese at temperatures of 8, 20 and 30 °C. The activation energy value and the chemical reaction rate constant enabled the construction of kinetic models, which helped to estimate the direction and rate of changes. Moreover, the activation energy (Ea) of the quality parameters was used to determine the sequence of their vulnerability during storage. The value of activation energy corresponding to temperature changes resulted in the following order of susceptibility of the quality parameters: ΔC > ΔE ≈ water activity > texture parameters > pH > colour > sensory parameters > rheological parameters. The research showed limited applicability of the mathematical models for estimation of quality parameters referring to spreadable processed Gouda cheese.

Background. Food spoilage is a process in which the quality parameters decrease and products are no longer edible. This is a cumulative effect of bacteria growth and their metabolite production, which is a factor limiting shelf life. Thus, the aim of the study was to evaluate whether microbiological growth models for total viable count (TVC) and Clostridium strain bacteria are reliable tools for prediction of microbiological changes in spreadable processed cheese. Material and methods. Investigations were conducted for two types of bacteria: TVC and Clostridium in following temperature: 8°C, 20°C and 30°C. A total number of aerobic bacteria was determined based on standard PN-EN ISO 4833:2004 and Clostridium was detected by using microbiological procedure for sulphite-reducing anaerobic spore-bacteria with a selective nourishment. During the analysis nonlinear regression and Baranyi and Roberts primary model were used. Results. For temperatures 20°C and 30°C, Baranyi and Roberts model, for total viable count showed determination coeffi cient of 70%. The models prepared for Clostridium, in these temperatures, showed much lower R