This PDF file contains the front matter associated with SPIE Proceedings Volume 12637, including the Title Page, Copyright information, Table of Contents and Conference Committee lists.

For the purpose of acquiring precise and trustworthy positioning data for mobile robots during autonomous navigation, we propose a multi-sensor data fusion technique based on the UKF algorithm. The technique combines visual, inertial, and GNSS localization data in a nonlinear optimization framework. In particular, we combine the VI-SLAM localization findings with those from inertial and GNSS fusion in the nonlinear optimization module to eventually acquire precise and trustworthy localization information, accomplishing the high precision localization of the robot in complicated situations. The findings demonstrate that the approach may successfully get around the drawbacks of different sensors and enhance their strengths in order to provide precise and trustworthy location data.

Modern hump car retarder control systems and their technical diagnostic methods are reviewed. Disadvantages of existing analytical methods of technical diagnostics are revealed. Factors, which help to increase the accuracy of technical diagnostics of car retarders, available in existing hump automated control complexes, are shown. The paper suggests to build a new intelligent technical diagnostic system to improve the accuracy of the current ones. The suggested system will use decision trees, created by means of Data Mining approach under conditions of small training set amount. This approach is based on the ideas of intelligent system self-organization. The increase in accuracy of the decision rules is shown on the verification database examples.

Volumetric data subject to visual analysis can occupy hundreds of gigabytes, which excludes the possibility of their visualization with an acceptable frame rate on conventional computers. If the data is segmented, its volume can be significantly reduced by tringulating the surfaces of the segments. This solution works well for opaque segments. This paper proposes an algorithm for packing segmented volumes, which allows the user to dynamically control the transparency of the segments, which facilitates the visual analysis of volumetric data. The algorithm assumes that the direction of observation is fixed. Therefore, if you want to analyze the volume from several angles, packing must be performed for each angle independently.

The article provides a summary of existing concepts and methods for estimating the quality of information use in solving various problems. It is noted that there is a lack of mathematical models and frameworks to explain the measures of information quantity, quality, and information use in relation to human activity outcomes. The aim of the presented research is to suggest concepts and diagrammatic models for developing mathematical models of information use for technological and organizational systems, based on probabilistic activity models. The method of modeling suggested uses the concept of complex state and modeling of their transitions, including details about the possible elementary states and substates of the system, as well as the cause-and-effect relationships between those states and any measures that apply to them. The proposed diagrammatic models aim to close the gap between existing concepts and formalized actionable mathematical models and methods that can be used for discrete and organizational systems in the real world. The concepts of actionable knowledge and information value are highlighted as important concepts in today's knowledge-based economy, where organizations and individuals seek to gain a competitive advantage through the effective use of information and knowledge.

The article examines the potential of soft modeling and expert systems in modern education. There is a growing understanding in the scientific community of the need to use flexible and rather soft mathematics in modeling various complex systems. As a rule, each model reflects the internal organization of any system, its essence, which is determined by the set goals.Non-strict or soft models are of a general nature. Fuzzy set theory and fuzzy logic are the basis for creating fuzzy control systems and fuzzy decision-making systems. The ideas of soft modeling are also applicable to expert systems. The authors of the article consider the solution of such problems in relation to education, in particular, determining the significance of various sections of the course "mathematics" for special professionally oriented disciplines.

The development of new control systems for complex technological facilities that are able of adequately responding to more dynamic and changing external and internal excitatory influences, is one of the main issue of the theory of automatic control. Therefore, it is important to create new automated control system that can provide the required accuracy of quality control. The structure of the control system, which maintains the adaptability characteristics in a wide range for the adjustment of various parameters in technological objects with variable parameters, is proposed and its efficiency is justified by modeling. A logical control algorithm for creating a control effect is provided.

The paper presents a solution for production control after machining based on matching of three-dimensional models of products, presented in the form of point clouds. This solution is designed for automated quality gates equipped with 3D scanners and computer vision system for intelligent control. This development is based on the model of “intelligent quality guarantor” and is included in its composition to expand the possibilities of the quality control process to the tasks of deviances identification. The results of the development were used and tested at machine-building enterprises as part of the control of small-scale production of simple products and the control of manual operations. Based on predetermined quality standards, the delivered system is capable of detecting visual defects corresponding to mechanical damage or manufacturing defects.

This article will consider the impact of the latest technologies on human work. In particular, the influence of the information system on the completion time of the task of creating cable connections. A group of people of different ages was taken for statistical analysis. In the first case, the crossings were carried out without the use of software. In the second case, the group was given the opportunity to use Sunbird Data Center Infrastructure Management. During the analysis, a data model was obtained. Conclusions were drawn based on this model [8].

In connection with the expansion of the scope of renewable energy sources, there is a need to accurately determine their parameters and characteristics. To analyze the nature of the operation of specific renewable energy facilities under various conditions, it is advisable to use simulation methods. In the presented work, simulation modeling of a photovoltaic module in the Matlab Simulink software package is performed. The developed model makes it possible to study the volt-ampere characteristics of photovoltaic modules depending on the level of solar radiation intensity. As a result of the simulation, the current-voltage characteristics and power characteristics for one panel at different values of radiation intensity, graphs of changes in panel illumination, output voltage and power, changes in the output voltage and current of the inverter when the load changes are obtained.

The research is devoted to the use of the decision tree method and artificial neural networks for the analysis of psycho diagnostic data. The possibility of applying these two data mining tools together to obtain additional information is explored. The analysis is carried out on the example of the psychological testing results of preschoolers’ parents. Two widely known tests were used, which allow to assess the relationship between 27 psychological indicators having different numerical scales. The sample consisted of 496 respondents. It is shown that the combined use of the indicated processing techniques allows for the selective and hierarchical assessment of the interrelationships of multidimensional heterogeneous data. The proposed approach is available to a wide range of specialists from different fields of knowledge, since the tools used are included in widespread software.

The article deals with the issue of studying the characteristics of the soil through the collection of data on its respiration. Quantitative characteristics of soil quality are proposed to be obtained by collecting data on soil respiration in the study area. Quantitative characteristics of soil quality are proposed to be obtained by collecting data on soil respiration in the study area. The article proposes to use the concentration gradient method based on Fick's first law. Research using this method require the experimenter to know the current values of such microclimatic parameters as soil and surface layer moisture, soil and surface air temperature, and most importantly, knowledge of the CO2 concentration in the soil and soil layer. An information-measuring system was developed to collect these data. It included four sensor modules, a switching-multiplexing module, a control module and a communication module. For the selected sensors, a scheme for their placement in the device is proposed, which, after experimental tests, if necessary, can be changed and supplemented. All sensors are mass-produced and can be purchased without any restrictions related to import to the Russian Federation. The control module is based on the STM32 microcontroller system. Based on the elemental base of the device (sensors and control module), an approximate cost estimate has been compiled. In the final part of the article, a number of features of the developed installation are described, the impact of which on its widespread implementation can only be assessed during operation, and some prospects for possible development are also outlined.

This article discusses an automation method for configuring IT infrastructure for IT projects based on the use of natural language processing (NLP) algorithms. The paper begins by discussing the relevance of the topic, reviewing existing solutions and third-party research in the field. Next, a mathematical model for implementing the method is proposed, and the architecture and technical implementation of the system are described. The results of the work include an approach for assessing the effectiveness of the system, both with and without automation, and a description of the expected results. In conclusion, the authors summarize their work and offer directions for further development of the proposed method and system. This article is a significant contribution to the field of IT infrastructure setup automation, providing a fast and efficient setup process for projects of varying complexity. It can be useful for developers, engineers, and project managers who want to optimize the process of setting up IT infrastructure and improve the quality of their projects.

The article is devoted to an automatic calculation approach for two important metrics for measuring the effectiveness of data center operations, named total cost of services (TCS) and data center compute efficiency (DCCE). The specification of required information to be gathered for metrics calculation is listed for both metrics. The software architecture that allows to perform TCS and DCCE metrics calculation is presented and implemented in the prototype tool. The results obtained from this experimental tool are presented for the TCS metric for a server on mock data, and for the DCCE metric for a single node represented by a loaded machine.

The dominant approach in contemporary science and industry applications is deep learning. Deep learning consists of many different architectures, including dense, convolutional and recurrent neural networks. In this article we compare deep learning, particularly dense neural networks (DNNs) with the other approach, synergetic models. As a task to compare the mobile application security was chosen. Two datasets were created, sensor values for human beings interacting with smartphones and malicious bot records using emulators. Deep learning and synergetic models were tasked to distinguish them from each other using binary classification. Both models tackled a problem comparatively well, archiving 99% and 85% accuracy respectively. While the deep learning model performed better, the synergetic model excelled in training speed, versatility and results transparency. Pros and cons of both models were addressed in the results section.

Investigation of the possibility of studying the Bauhaus painting heritage with deep learning techniques. The efficiency of this approach is basically limited by the small size of the dataset, limited possibilities of using augmentation and significantly different nature of the images studied in comparison to typical datasets such as ImageNet. The example of classifying World War II posters using transfer learning and fine-tuning of the MobileNetV2 network illustrates the basic points regarding the use of deep learning to solve typical research problems in the Bauhaus heritage. The effects of augmentation, batch size, learning rate, and number of pre-training layers on the quality of learning are investigated. Practical recommendations useful to humanities researchers of art collections are presented.

The article considers the issue of measurements, virtual devices, which is a topical issue of the time. The first step in control industry and technology is to take measurements. Virtual measuring devices have been studied, given that virtual devices are now widely used in industry. Control systems, which are a clear example of modern technology, are an ideal tool for obtaining high quality products in production and industry, as long-used analog control systems give way to digital control systems with high accuracy and wide range of functions. Taking all this into account, simulation modelling of this process was carried out.

The purpose of the study is to develop and test a software and hardware complex for access control and management using face recognition algorithms and neural network technology. A software and hardware complex was used, including turnstiles with swing doors, single-board mini-computers on each turnstile, webcams, sensors, an integrated graphics processor, as well as a software development kit for developers. Siamese neural network “FaceNet” was used for face recognition. When training a neural network, each face image is associated with a feature vector lying on the N-dimensional hyposphere. The study developed and tested photo pre-processing algorithms (to exclude irrelevant images), as well as the biometric PACS algorithm. Approbation of the developed hardware and software system on the campus of the Kemerovo State University (Kemerovo, Kemerovo region – Kuzbass, Russia) showed that the average frame processing speed is high (0.076 seconds per frame), which ensures a fairly fast pass of people. This result is achieved on the basis of the image pre-processing algorithm. During the first test of the software and hardware complex, it was found that 60% of the frames are excluded from the analysis by the neural network. Errors of the first kind (passing people who do not have the right to pass) were observed in 4% of cases. After setting up and calibrating the software and hardware complex, the proportion of such errors decreased to 0.4% of the total number of frames processed by the neural network.

The authors propose definition algorithm of students’ educational program specialization in the field of IT technologies that is based on the methodology of educational data ranking. The algorithm has shown the importance of data mining methods for solving educational problems. This algorithm can be considered as a prototype of a recommender system, so students will be able to make their own decisions: follow the recommendations or make their choice based on other factors that are dominant for them.

Currently, in financing cases concerning state-run mineral resources base reproduction, especially in terms of identifying forecast resources, and in some cases regarding the category of reserves C2, there is an urgent need to develop ranking techniques for subsurface allotments according to their prospects. In such situations, the use of fuzzy logic models will allow formalizing and automating integral estimation calculation of subsurface allotments for the purposes of their ranking. Therefore, the purpose of this work is to develop instructional aspects of ranking subsurface allotments according to prospects based on the use of fuzzy logic. Resulting from the application of this technique it was possible to perform an aggregated assessment of subsurface areas on the territory of the Bryansk region according to geological reports for the period of 2010-2020. The subsurface areas, being subsequently recognized as prospects, were introduced into the model with their expert assessments for this period of work. Thus, we have initiated a methodology for ranking subsurface areas according to their prospects based on the use of fuzzy logic. It provides for the use of the specified production rules to perform the ranking of subsurface allotments taking into account the prospects. Production rules should cover all possible combinations of expert assessments in confidential intervals. Besides, within the implementing techniques it is required to compare subsurface allotments in terms of fuzzy estimates and also clear mathematical sets. This operation is implemented programmatically (Mamdani algorithm) by performing sequential phasification – defasification operations in the Fuzzy logic component of the Matlab software product.

This article discusses the concept of using the Markdown markup language instead of the WYSIWYG approach to create an automated system for the design of scientific texts. The paper demonstrates how the markup language, Markdown and the Pandoc converter, can significantly reduce the time for editing and making edits to scientific papers due to the possibility of automatic linking, bibliography generation and collaboration. The architecture of the system of automated registration of scientific documents is also considered, which allows you to eliminate the problem of registration and transfer it to the shoulders of a program compiling DOCX, PDF or other necessary text format from markup according to pre-written style templates. In general, the use of markup languages is a more flexible and convenient approach for writing scientific papers, such as academic assignments, term papers, articles, and can be widely used in educational institutions, both by students and teaching staff.

In the context of scientific and technological progress, the rapid development of information technologies, the problem of training qualified specialists who are able to work effectively in the new information environment is becoming increasingly urgent. Design and research activities of students are one of the main areas that ensure the development and formation of competencies necessary for professional and research work. Within the framework of the digital transformation that is being carried out in Russia, the use of digital technologies at different stages of research and the organization of design and research activities are the most relevant. The paper presents options for using digital tools and services for organizing work, establishing communication, collaborating, planning and accounting for completed tasks within the framework of the research project.

Based on the principles of fuzzy modeling, the principles and algorithms of a mathematical model for predicting the parameters of oil and gas fields have been created using geological and geophysical information under conditions of uncertainty. Using the Mamdani algorithm, to obtain the final forecast rules, a chain of fuzzy relations between the initial and final forecast parameters was established by combining fuzzy relations, and for the forecast parameters in this case, the uncertainty field was used, since this field is a function of spatial coordinates.

The article deals with the problems of using new digital services to organize the development and implementation of agent-individualized work trajectories of human-machine systems adapted to digital industries in the formation of a digital infrastructure for scientific, technical and industrial activities in Russia and abroad. The overall goal of digitally operating with the intellectual activity of innovative agents (scientists, engineers, managers) is to optimize [through the use of communication technologies implemented based on digital information and computing services] the processes of research, design, production and operation during the life cycle of high-tech equipment for industries industries with high requirements for the reliability of technological processes. A system organization of support for agent-oriented configuration of human-machine systems within agent-oriented associations based on the use of various forms of digital information and computing services to support intellectual activity with a significant creative component is proposed.

The article deals with the problem of multi-criteria assessment and management of the implementation of multi-scenario multi-stage regional environmental projects. The proposed approach involves building a scenario network, each node of which corresponds to a set of activities of a certain stage. The choice of the arc of transition to the next stage (the option of continuing the project) is made on the basis of knowledge about the subject area of the project, represented by a system of linguistic variables and fuzzy production rules linking them. The recommended solution for choosing the continuation of the project is determined based on the fuzzy inference procedure. The final choice of the option to continue the implementation of the environmental project is made by the decision-maker on the basis of their own (often non-formalized) preferences. As an example of the application of the proposed approach, the task of managing regional forest conservation projects is considered. The use of the developed decision support tools for adaptive management of environmental projects makes it possible to increase the scientific validity of management decisions, and, consequently, to reduce costs and increase environmental efficiency in the implementation of these projects.

The concept of a synergistic effect is given - the appearance of properties in the system that are not inherent in its elements separately, that is, the irreducibility of the properties of the system to the sum of the properties of its components. The definition of those factors, components of the participants in the synergistic effect: photosynthesis and mineral nutrition is given. The prerequisites for creating a software algorithm for the implementation of a synergistic effect in the production processes of plants are substantiated. The task of the algorithm is to track the moment when the difference between the temperature of the vegetative organ and the external temperature reaches its maximum, while both conditions for the efficiency of the production process will be observed: the maximum nutrient consumption through the plant and the maximum rate of photosynthesis. This leads to the formation of a synergistic effect. The algorithm provides a search for this difference. A description of the operation of the program algorithm is presented. The purpose of this research is to experimentally verify the operation of the software according to the developed algorithm and the presence of a synergistic effect provided by this algorithm. Lettuce culture "Azart" was used as the object of research. The experiment was carried out from May 31, 2022 to June 28, 2022 with fixation of biometric indicators. The following indicators were taken as indicators: leaf weight (wet), leaf weight (dry), leaf area and number, plant height. Mean scores were calculated from the scores of each of the six plants in the Algorithm/Plant study boxes. A specially designed stand was used for research. The stand consists of two boxes for placing the test samples in them, in one of which the mode was controlled according to the developed algorithm (upper box), and in the other according to the usual scheme that supports the tabular optimal factors for a given culture by air temperature (lower box). Comparison of productivity indicators revealed the presence of a synergistic effect in the management of the modes of production processes according to an algorithm that ensures the cooperative interaction of photosynthesis and effective mineral nutrition. The algorithm operation schedule is given based on the selected experimental values of climatic indicators from 7:12 to 12:00. The graph shows the mode of satisfactory operation of the developed algorithm in real time.

The transition to Industry 4.0 is accompanied by significant progress and change in many areas of society and the economy. Digitalization changes and improves business processes, simplifies and enriches people's lives. Innovation is taking place. New tools provide, among other things, the collection of large amounts of data. In this regard, the problem of big data analysis is urgent. Since this task is associated with a large amount of digital computing and relies heavily on advanced software and server tools, we were faced with the task of conducting such an in-depth analysis with available software tools with high efficiency. The constructed multi-level universal algorithm for obtaining, collecting, processing and visualizing data is implemented in Microsoft Excel using the Power Pivot add-on. The analysis carried out in the study is aimed at identifying and comparing regions in terms of the level of development of spheres of public life, including the level of digitalization in the context of industry 4.0.

This work is devoted to the formation of a mathematical model and a method for statistical research of the digital transformation of corporate training. The purpose of the work is to compare the results of digitalization of training in the company. Several options for digitalized learning (classical LMS systems, microlearning, simulation and gamified courses) were tested on employees with different levels of knowledge in the field of computer science and information technology. The use of mathematical models in this case makes it possible to increase the level of calculations, and statistical models help to calculate the effectiveness of digitalization in a company when introducing information technologies. Conceptual and mathematical models, methods and technologies for studying digital transformation used in practice make it possible to increase the assimilation of information by employees with the further construction of a statistical model to achieve the set goals and solve the identified tasks. Choosing a specific software package for creating a digital environment it is necessary to use modern digital technologies and software tools in the performance of research work and determine the most effective mathematical model that allows you to identify the features and prospects for the formation and development of human capital. After analyzing the results using Fisher Angular Transform, we found that any of the above information technologies are equally well suited for different audiences with different levels of digital skills, but the option that uses technologies that simulate real conditions turned out to be the most effective of them. To increase the effectiveness of corporate training, it is possible to introduce both individual tools and complexes.

This article is devoted to issues of digitalization of the educational system, organization and development of educational processes using digital technologies, which is one of the current problems in the educational system. The need to use digital technologies in providing distance education to students, the need to use the field of distance education and introduce new generation systems of distance education, that it is faster, easier and cheaper to learn new skills or materials related to the subject through the distance education system, is covered in detail. At the same time, the problems hindering the effective implementation of distance education using digital technologies in our country and suggestions and recommendations for their solution are given. Management of higher education processes at the Tashkent pharmaceutical institute, based on the information platform "HEMIS" and distance learning systems "Moodle LMS", a brief description of the principles of organization of online education in teaching all modules of students is presented, and its main capabilities and advantages are indicated. By studying, systematizing and summarizing the existing practice in drawing up scientifically-based conclusions on the introduction of digital technologies in higher education, suggestions are made not only on how they will take an important place in the field of education and in what form they will be introduced.

This article examines the use of machine learning to prevent incidents and occupational hazards at the workplace. The authors have analyzed existing research in this area and have demonstrated the possibility of use of the machine learning to predict risks and prevent incidents. Specifically, the authors studied the methods of logical regression and classification to analyze data on past incidents. The results of the study showed that the use of machine learning can significantly improve the accuracy of risk prediction and enable more effective incident prevention. The importance of introduction of machine learning is discussed in the context of workplace safety and directions for further research are suggested. Overall, the article is an important addition to the general literature on the use of machine learning in the field of workplace safety and provides an opportunity to better understand the background and improve the accuracy of risk prediction and incident prevention at the workplace. The study is of interest to scientists, practitioners and politicians involved in workplace safety, as well as to those who are involved in the development and implementation of machine learning systems.

The analysis of current trends in the implementation of effective socio-economic solutions and their development under the influence of COVID-19 is made. The prospects of using innovative and telecommunication technologies, robotics, big data processing methods and knowledge management methods in the formation and management of global economic clusters were noted. The clustering of delivery robots under pandemic conditions by methods of machine learning was carried out. The peculiarities of COVID-19 assessment as the main formative factor influencing socio-economic decision-making on a global scale are disclosed. The necessity and possible consequences of adopting and implementing new decisions designed to minimize the negative effects of COVID-19 on Russian and global economies are discussed. It is noted that the design and development of innovations in the system of management and transfer of knowledge is an indispensable condition for the successful development of future socio-economic relations. On the basis of the obtained results conclusions are made about the background of the applied solutions, about the vector of their direction and makes it clear what should be paid special attention to when assessing the current situation in society and determine which solutions are most effective and how the social order should be transformed to successfully withstand the new challenges.

The personnel, structural, scientific and methodological support of Kuzbass digital mapping were under study. It was established that traditional digital cartographic and geodetic support in Kuzbass is insufficient for the development of territorial planning, therefore additional semantic information is required, so new principles for its implementation were proposed. Thus, the purpose of the research was to develop a methodology for the development of geoinformation support for Kuzbass territory. This must be based on the development of methodology for forming territorial planning semantic information, which is a complex scientific task. The methodology of forming semantic information includes a systematic approach taking into account territorial planning, economics and ecology. Practical use of the proposed methodology implementation is to expand the usage of digital technologies in making optimal management decisions and improving territorial planning of Kuzbass, as well as to systematize information and gain new knowledge.

The article deals with one of the most important processes in the service business - the task of distributing applications among service specialists, taking into account a large number of requirements, which are often difficult to formalize. The scheme of the algorithm operation is presented, formalized descriptions of the initial data, internal variables of the algorithm are given, the constraints of the problem are presented, the objective function and operators of the genetic algorithm are determined. The developed algorithm will optimize the business process of distributing applications, which will help achieve the strategic goals of the business.

This article has a practical orientation and is devoted to the development of an automated system that searches for profitable investments. It includes blocks that carry out fundamental analysis, rating assessment of the proposed object for investment, a module for analyzing and forecasting profitability, a module that allows you to assess the possible negative consequences of the total investment portfolio using models of the conditional value of risk and audit risk. The implementation of the methodology included in the developed software was carried out on the example of the agro-industrial complex of the Russian Federation.

The article presents a variant of optimizing the learning trajectory management system based on big data processing methods in LMS universities. To build an adaptive learning management system at the university, an integrative structure is proposed and a mathematical model for managing the learning trajectory in the "Big data LMS" module is optimized.

The results of automated processing of scientific publications for the purpose of searching and highlighting term-like phrases in them are presented. The analysis was performed using the PubMed database. The chronological period (time interval) covers 1900-2022. It is shown that in publications there is an expansion of the use of the phrase "circular economy", which indicates the increasing relevance of the subject of research. The results of the analysis showed a chronological dependence on the development of this theoretical concept and its practical application. The methods of thematic modeling and neural networks were used.

The purpose of the study is to identify factors that affect the price of the GOLD-12.21 futures using machine learning and the Python programming language on minute data. Correlation analysis was used to search for causal relationships between the GOLD-12.21 futures rate and 16 independent variables. The study differs from existing scientific articles by analyzing large volumes of minute-by-minute data and automating calculations in order to obtain correlation estimates in real time. It was revealed that on the Moscow Exchange the GOLD-12.21 gold futures rate has a high correlation with the dollar exchange rate against the ruble, as well as with the Amex Gold BUGS Index and the spot gold price. Therefore, to predict the GOLD-12.21 futures rate, it would be advisable to use the dollar rate indicator. Also, this relationship has a time lag. Therefore, the study shows that it is expedient to determine the correlation not between the absolute value of rates, but relative changes in rates in relation to each other. This allows us to estimate how much the GOLD-12.21 gold futures rate will change if the US dollar exchange rate against the ruble changes by 1%.

The optimal organization of the territory of crop rotation fields and arrays allows you to choose the optimal scheme of cotton crop rotation. An analysis of the current level of development of crop rotations in the object under study showed that the agrotechnical foundations of cotton crop rotations have been studied quite fully, and specific recommendations have been developed for individual soil conditions of the region. At the same time, the organizational and economic substantiation of crop rotations has been little studied, taking into account the production and economic conditions of individual farms. This is especially true for the choice of crop rotation system, crop rotation and assessment of the yield of crop rotation fields, as well as linking the placement plan and crop rotation. Implementation allows you to determine in which field a particular crop should be sown. To solve this problem, a genetic algorithm is used. A computational experiment was carried out.

The problem of digital control of regional costs in a large company under conditions of uncertainty, using artificial procedures and taking into account the human intelligence factor, are analyzed. The undesirable activity of managers of the middle (regional) and lower (production) level of the company, associated with the presence of their own goals, was revealed. Such undesirable activity can lead to overestimation of regional costs. In order to minimize these costs, a digital control model is proposed that uses digital learning procedures at the regional and production levels. As a result of research, a mechanism has been developed to reduce regional costs in each period of time. This mechanism includes, firstly, a digital self-learning procedure for a top manager of a company, as well as a procedure for stimulating a middle manager by him to reduce regional costs. Secondly, this mechanism includes a procedure for digitally supervised training of a middle manager, as well as a procedure for stimulating a lower-level manager for reducing production costs. The statement and solution of the problem is illustrated by the example of the application in the maintenance of rolling stock.

Locusts cause great damage to vegetation in many areas of the earth. A mathematical model of propagation of non-linear waves in space in various excitable media is constructed, since they describe the flight of gregarious locusts, the corresponding system of differential equations is qualitatively investigated, and a solution is found that corresponds to the flight regime of gregarious locusts. An analytical solution is obtained, and numerical studies are carried out. Simple approximate analytical expressions for calculating the propagation velocity of the locust population wave and its characteristic length are obtained.

In the paper, the authors described a discrete model of the nonlinear heat transfer process resulting from a local instantaneous ignition in a heterogeneous substrate, using elements of a cellular automata approach. As a result of discretization by a uniform grid, a flat area modeling a section of substrate is presented as an array of cells for which initial states are specified. As a characteristic of the state, we took the temperature difference between the substrate and the environment. One of the array cells is set on fire by an instantaneous impulse. We use a deterministic synchronous cellular automata. It is also possible to take into account the effect of temperature on the thermophysical properties of the substrate. Using the implementation of the described discrete model in the C ++ Builder environment, we performed heat transfer simulations for various substrate properties, boundary conditions, and source properties. The results of the cellular automata model qualitatively correspond to the physical concepts of the processes under consideration and make it possible to create a visual picture of the temperature profile evolution for the selected area of the underlying surface. The approach presented in the paper will expand the capabilities of predictive models in order to take into account the fire-hazardous characteristics of various types of soils.

Estimating the prognostic potential is also based on evaluating the geological potential, taking into account the available geological and economic information on this territory and the existing need for relevant resources. Thus, to make a decision on investing in further exploration on promising subsoil areas, it is necessary to consider a significant number of factors and their corresponding indicators. In such situations, it is customary to use knowledge bases built upon ontological engineering. As a result, it becomes possible to implement the obtained ontological model having a set of geological and economic parameters for estimating expected resources with the integration of the mathematical apparatus of fuzzy logic and set theory. Thus, the authors have considered the methodological aspects of estimating the prospects of the subsoil plots through ontological engineering of geological exploration, taking into account their features, based on using a knowledge base containing a thesaurus of geological and economic indicators by the exploration process stages. The links of geological and economic indicators as part of the subject area thesaurus are determined in order to build an ontological model, which makes it possible to perform factorial economic analysis. The actual evaluation of indicators as part of the thesaurus of the geological and economic assessment of the geological exploration results allows one to characterise the state of the study object and to proceed to estimating the volume of mining commodity output, according to the requirements of the individual territory, region, state (taking into account the volume of exports and imports) of mineral raw materials.

The most important aspect in the production of agricultural and pharmaceutical products is the immediate drying of collected vegetable raw materials to preserve a complex of nutritional and vitamin properties. This paper provides a mathematical kinetic model of the drying process of vegetable raw materials in the electromagnetic field of the SHF range in the medium pressure oscillation mode. A feature of the proposed method is the use of the oscillating drying mode, consisting of SHF heating and vacuuming stages, providing uniform removal of moisture across all layers of the material. Experimental studies and evaluation of design data were carried out on an experimental SHF drying unit. Vegetable raw materials with carotene, namely green lucern, were used as samples. It is established that decrease in the dielectric permittivity of fodder grasses leads to increase in each subsequent drying stage in time. As a result of the experiments, rational operating conditions of drying were determined, ensuring maximum preservation of carotene in the leafy mass, as well as energy parameters of the equipment depending on the volume of machine loading. In order to perform highly efficient drying of biofeedstock in a remote area, the process schedule described in the article was improved and the engineering method for calculating the industrial SHF drying complex was developed.

It is shown that the improvement of industrial safety due to the identification of geodynamic activity of the subsoil of the developed hydrocarbon field is an urgent problem. To solve it, an information technology for identification has been developed based on the construction of aggregated additive-type models and the determination of geodynamic activity in the normalized range from 0 to 1. The results of the study allow us to build an efficiently functioning industrial closed automated system, into which a new main subsystem has been introduced.

The article examines the approaches of using information technologies for grouping objects based on the use of cluster analysis methods. Based on Data Mining mining tools, approaches for cluster analysis are considered. The main methods of cluster analysis are considered. For example, the demand for goods in shopping centers is considered and an analysis of customer preferences is carried out. Clustering of objects was carried out on a sufficiently large set of data (transactions) using the Deductor Studio tool. It is shown that for clustering objects with an unknown number of classes, the g-means method is the most preferable. Clusters with the most popular sets have been identified.

The article presents experimental - theoretical studies of the modulus of elasticity and Poisson's ratio, for the pulp of melon and other plant crops, characterizing the process of cutting with a blade. When using mechanical methods for processing melon fruits (removing the peel, cutting the fruit into slices, removing the testes and plasticizing dried melons), it is impossible to express the essence of the ongoing processes at the current level of theoretical knowledge. Therefore, in order to quantify the technological properties of melon, it is necessary to resort to experimental and theoretical methods that allow us to obtain some relative indices that allow us to measure the modulus of elasticity Е , Poisson's ratio  , breaking stress  р , and coefficients of friction of rest п f and motion д f .