Various methods are used to prevent the deterioration of the biotechnological properties of brewer’s yeast during storage. This paper studied the use of artificial neural networks for the mathematical modeling of correcting the biosynthetic activity of brewer’s seed yeast of the C34 race during storage with natural minerals. The input parameters for the artificial neural networks were the suspending medium (water, beer wort, or young beer); the type of the zeolite-containing tuff from Siberian deposits; the tuff content (0.5–4% of the total volume of the suspension); and the duration of storage (3 days). The output parameters were the number of yeast cells with glycogen, budding cells, and dead cells. In the yeast stored with tuffs, the number of budding cells increased by 1.2–2.5 times, and the number of cells with glycogen increased by 9–190% compared to the control sample (without tuff). The presence of kholinskiy zeolite and shivyrtuin tuffs resulted in a significant effect. The artificial neural networks were required for solving the regression tasks and predicting the output parameters based on the input parameters. Four networks were created: ANN1 (mean relative error = 4.869%) modeled the values of all the output parameters; ANN2 (MRE = 1.8381%) modeled the number of cells with glycogen; ANN3 (MRE = 6.2905%) modeled the number of budding cells; and ANN4 (MRE = 4.2191%) modeled the number of dead cells. The optimal parameters for yeast storage were then determined. As a result, the possibility of using ANNs for mathematical modeling of undesired deviations in the physiological parameters of brewer’s seed yeast during storage with natural minerals was proven.

The paper presents the data on lipid fraction extraction from the raw fat of hibernating hunting animals. The processing of valuable raw materials must be maximized. For this purpose, various methods of rendering are used. As a result of temperature exposure, the protein part of raw fat undergoes significant changes. The protein denatures under the influence of temperature, and the dross formed during the rendering process absorbs and retains up to 30% of the fat. The authors propose using proteolytic enzyme preparations for a more complete extraction of fats, as the enzymes will hydrolyze the protein into compounds of lower molecular weight both before and during the rendering process. The experiment proved that the biocatalytic method allows achieving a fat yield of more than 95%. The best result can be obtained if the rendering is carried out at optimal parameters, which can be defined using a mathematical model. Mathematical modeling was carried out using an artificial neural network. During the study, a fully connected neural network was designed; it had eight hidden layers with 64 neurons in each, and its accuracy was measured by mean relative error, which amounted to 5.16%. With the help of the network, the optimal values of applied concentration, temperature and duration of rendering, at which a fat yield of more than 98% is achieved, were determined for each enzyme preparation. After that, the obtained values were confirmed experimentally. Thus, the study showed the efficiency of using artificial neural networks for modeling the biocatalytic method of lipid extraction.

Introduction. Vegetable raw materials have always been and still remain the main raw material for obtaining extracts. The extraction process is the most important stage during the production of extracts and aromatic spirits. The research objective was to study the extraction process of the target substances from fruit and berry raw materials for the production of alcoholic extracts. Study objects and methods. The study featured cranberries, which are widespread in Siberia and have many useful properties. Cranberries are rich in vitamins C, B1, B2, B5, B6, PP and rarer vitamin K1. The studies were conducted using a Soxhlet extractor. The experimental results were processed using the method of multiple regression analysis. The research also exploited generally accepted methods for assessing the quality of samples of alcoholic beverages. Results and discussion. The experiments made it possible to define the optimal technological regime parameters for the production of aromatic cranberry extract. The maximum values of all three processing parameters exerted the greatest effect on the dry matter content in cranberry extract. The recommended conditions resulted in a cranberry extract with a high content of target components. The presented mathematical description of the extraction process in the Soxhlet extractor makes it possible to preliminarily determine the quality indicators of the resulting beverage at the onset of production. Control experiments conducted under these conditions confirmed the calculated values. Conclusion. By using a Soxhlet extractor, the preparation time for alcoholic cranberry extract was reduced to 20 minutes, which differs by one order of magnitude from the classical infusion production method. The Soxhlet extractor made it possible to use less solvent and raw materials, due to the almost maximum completeness of extraction of the target components of fruit and berry raw materials. This fact is bound to decrease the production expenses and the cost of the final product.

Introduction. Artificial neural networks are a popular tool of contemporary research and technology, including food science, where they can be used to model various technological processes. The present research objective was to develop an artificial neural network capable of predicting the content of isogumulone in a hop extract at given technological parameters of the rotary pulse generator. Study objects and methods. The mathematical modeling was based on experimental data. The isogumulone content in the hop extract I (mg/dm3) served as an output parameter. The input variables included: processing temperature t (°C), rotor speed n (rpm), processing time  (min), and the gap between the rotor teeth and stator s (mm). Results and discussion. The resulting model had the following parameters: two hidden layers, 30 neurons each; neuron activation function – GELU; loss function – MSELoss; learning step – 0.001; optimizer – Adam; L2 regularization at 0.00001; training set of four batches, 16 records each; 9,801 epochs. The accuracy of the artificial neural network (1.67%) was defined as the mean relative error. The error of the regression model was also low (2.85%). The neural network proved to be more accurate than the regression model and had a better ability to predict the value of the output variable. The accuracy of the artificial neural network was higher because it used test data not included in the training. The regression model when tested on test data showed much worse results. Conclusion. Artificial neural networks proved extremely useful as a means of technological modeling and require further research and application.

This work aims to use artificial neural networks for mathematical modeling of correcting the biosynthetic activity of yeast during storage with natural minerals. The object of the research is the brewer's seed yeast of the C34 race. Artificial neural networks were created on the basis of experimental data, which were used to solve the problems of regression and prediction of output values. Four networks were created: the first one modeled the values of all output variables, while the second, the third and the fourth modeled the number of yeast cells with glycogen, budding cells and dead cells respectively. Next, the optimal yeast storage parameters were determined. As a result of the study, the possibility of using artificial neural networks for mathematical modeling of undesirable deviations in the physiological parameters of brewer's seed yeast during storage with natural minerals was proved.

Hydroponics is a method of soilless cultivation of plants. It shortens the vegetation period, reduces the risk of disease and insect infestation, and provides a year-round growing cycle. Hydroponics depends on efficient water management. It is associated with a complex design, operation, and maintenance. Neural networks can control complex technological processes in agriculture. The research objective was to use a neural network to increase the efficiency of a home hydroponics system. The study involved a nutrient bed hydroponics setup with ten Lactuca sativa plants. Sensors collected information about the temperature and humidity of air, illumination, and the temperature of the leaf surface. Data processing, neural network training, and microcontroller programming relied on Python 3, PyTorch, and MicroPython. The four-layer perceptron, which is a popular control mechanism, turned out to be the most effective neural network architecture. Fewer layers resulted in a high error rate (≥ 5%). When the number of layers was > 4, the error level remained at that of the four-layer experiment (0.2%). Further practical tests showed an increase in energy efficiency by 32.3%, compared to the classical control algorithm at close values of plant transpiration. Neural net technology could be integrated into energy-saving residential premises and smart home systems in order to increase the self-sufficiency of hydroponics installations.