Using an artificial neural network (ANN), the values of the antiradical potential of 1315 items of food and agricultural raw materials were calculated. We used an ANN with the structure of a “multilayer perceptron” (MLP) and with the hyberbolic tangent (Tanh) as an activation function. Values reported in the United States Food and Nutrient Database for Dietary Studies (FNDDS) were taken as input to the analysis. When training the ANN, 60 parameters were used, such as the content of plastic substances, food calories, the amount of mineral components, vitamins, the composition of fatty acids and additional substances presented in this database. The analysis revealed correlations, namely, a direct relationship between the value of the antiradical potential (ARP) of food and the concentration of dietary fiber (r = 0.539) and a negative correlation between the value of ARP and the total calorie content of food (r = −0.432) at a significance level of p < 0.001 for both values. The average ARP value for 10 product groups within the 95% CI (confidence interval) was ≈23–28 equivalents (in terms of ascorbic acid) per 1 g of dry matter. The study also evaluated the range of average values of the daily recommended intake of food components (according to Food and Agriculture Organization—FAO, World Health Organization—WHO, Russia and the USA), which within the 95% CI, amounted to 23.41–28.98 equivalents per 1 g of dry weight. Based on the results of the study, it was found that the predicted ARP values depend not only on the type of raw materials and the method of their processing, but also on a number of other environmental and technological factors that make it difficult to obtain accurate values.
Mathematization of research is one of the most effective methods of virtual substantiation of foodstuff recipe and technology. This approach allows creating a product that meets consumer's individual needs, i.e. personalized foodstuff (ethnicity, cultural preferences, regional and environmental characteristics, lifestyle), and at the same time reducing the time and cost of decision-making. The article discusses the hypothesis that the “digital twin” of a food product is a virtual model of the product, namely its mathematical model (simulation model). A simulation model is a logical and mathematical description of a food product that is used to conduct a computerized experiment in order to design desired characteristics and properties. The “digital twin” combines all variety of factors from chemical composition, functional and technological properties to organoleptic indicators. The application of the “digital twin” model of the foodstuff will allow: (1) reacting quickly to changes in the composition, properties and types of raw ingredients, (2) adjusting the product recipe in response to changes in consumer preferences, (3) designing products with a given chemical composition, nutritional value and functional orientation, (4) creating functional, specialized products taking into account the metabolism of nutrients (ethnicity, cultural preferences, health status and clinical factors). Products adapted to the needs of small categories of people will help reducing the risks for those who already have diseases, and will meet the needs of those who would like to make their diet more appropriate to individual needs. The proposed approach to creating a model of the “digital twin” of the foodstuff includes several stages. The first stage involves optimization of the nutritional and biological value of the designed product. The second stage is related to designing the food product’s structural forms. But even if the recipe of a food product is optimally selected in the first stage, it does not guarantee its transformation during processing into a stable system with the required structural, mechanical, functional and technological parameters. Evaluation of the developed food product’s efficiency is possible only by analysing numerous and various parameters and indicators. It is convenient to generalize (convolute) many parameters and indicators into a single quantitative dimensionless indicator. To assess the quality and adequacy of the food product, it is suggested to use an integral indicator in the form of additive convolution – the ‘functional’ of the food product quality.
The article summarizes some scientific and practical prerequisites for creating multicomponent foods with desirable quality characteristics and consumer properties. Mathematical methods were used to model a multicomponent product according to the selected parameters of adequacy and quality, depending on the nutritional and biological value of raw materials. The Russian methodology of food design originated in the works of N.N. Lipatov. His six basic principles of designing balanced multicomponent foods are still relevant today. Further development was proposed by A.B. Lisitsyn who took into account individual protein digestibility of every component in the mixture and its effect on the amino acid composition of total protein. At the next stage, Yu.A. Ivashkin improved formulations using the methods of system analysis, modelling, and product range optimization. Modern food chemistry, food biotechnology, and information technologies allow for effective computer design and optimization of multicomponent food formulations for specific population groups. As a result, an increasing number of food scientists are engaged in improving food products. Literature analysis showed that the current stages of designing (modelling) multicomponent foods are mainly based on information and algorithms, using linear, experimental and statistical programming methods or an object-oriented approach. Russian food scientists still use the methodology developed by A.M. Brazhnikov, I.A. Rogov, and N.N. Lipatov. It allows for designing multicomponent foods with specified nutritional indicators and energy value. The Russian Academy of Sciences pointed to a need for “digital nutritiology” (Decree No. 178 of November 27, 2018 “On Current Problems of Optimizing the Population of Russia: Role of Science”). This new scientific direction could enable digital transformation of data on human physiological needs for nutrients, biologically active substances, and energy, as well as the chemical composition of basic foods. There is also a need for computer programs to give personalized recommendations for optimal nutrition.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.