The paper provides an overview of research in the field of modeling the heights of urban areas. The diversification of building heights leads to an uneven distribution of urban climate parameters. Building height maps can help improve urban management. The reviewed papers outline methods for urban scale modeling based on image recognition. Urban geometric models are built for the cities of the United Arab Emirates, China, Germany, and Japan. The research shows that both radar and optical models can be used to predict building height, but a synergistic combination of both data sources produces the best results. However, there is currently no globally agreed spatially detailed survey of the distribution and concentration of the building stock. Understanding of vertical urbanization should complement the horizontal urbanization and help sustainable land use and urban planning.

Keywords: high-rise buildings, urbanization, urban scale modeling, urban morphology, urban microclimate, Google Earth, air flow, thermal environment, wind environment, calculation of building heights

The article presents an analysis of the problems of diagnosis and restoration of the human respiratory system after diseases, including COVID-19. The review of analogues of small-sized spirometers is carried out. On the basis of which an individual small-sized device has been developed for effective training of the respiratory system. The functional scheme of the pneumatic trainer is described and the main simulator-game scenarios for achieving a therapeutic effect are analyzed.

Keywords: respiratory system, COVID-19, pneumatic trainer, portable device, pressure sensor, MEMS technology

The paper discusses specific reasons for strengthening footings and reinforcing foundations and explores the principal technologies for installing auger cast piles used for reconstruction of building systems. In order to identify the key benefits of using auger cast piles, the existing technologies are analyzed based on the study of domestic and foreign patents. The main principles are set out underlying an economically sound, technically and technologically justified choice of foundation reinforcement technology.

Keywords: reconstruction, bearing capacity, strengthening, reinforcement, piles, anchors, patent search, drawbacks and benefits

This paper describes the process of developing machine learning models for predicting problem states. The formation of decision support systems in problem situations is based on the using of ensemble methods of machine learning: bagging, boosting and stacking. The algorithms of undersampling and oversampling is applied for improving the quality of the models. Using of complex machine learning models reduces the ability to explain the result obtained, therefore various ways of interpreting the constructed models are given. Based on the results of the study, a method for predicting problem states was formed. This approach contributes to the gradual solution of the identified problem situation and the consistent achievement of the goal.

Keywords: machine learning, bagging, boosting, stacking, problem states, data balancing, shap-values

In this work, the basic relations of relativistic rocket dynamics in the case of a multicomponent jet jet are obtained and investigated. Various types of relativistic rockets with a single-component jet jet are considered as special cases of the general theory. The limiting transition to nonrelativistic rocket dynamics has been made.

Keywords: relativistic dynamics, multicomponent jet stream, ion engine, photon rocket

This article discusses the problem of choosing a monitoring system for the IT infrastructure. A comparative analysis of monitoring systems applied to various types of IT infrastructures was carried out and a solution was selected for a specific IT infrastructure of the company.

Keywords: monitoring, infrastructure, Zabbix, Grafana, Kubernetes, metrics

The article looks into the influence of energy and optical factors on the quality of laser cutting of thick sheet metal. The authors describe the advantages of using laser cutting in production and determine further directions in the development of laser technology. The work presents an analysis of Russian and foreign scientific research and highlights the indicators that affect the quality of manufacturing parts by laser cutting. The authors present the results of an experimental study of the influence of energy and optical factors and finding dependencies in order to determine the optimal technological modes for obtaining a high quality cut. The studies and experiments carried out made it possible to determine the optimal ratio between the focal spot diameter and the waist length when using lenses with focal lengths of 200, 250, and 300 mm. Based on the data obtained, the authors also formulated technical requirements for the development of a model of a laser optical head.

Keywords: laser cutting, radiation power, optical factor, parameters, laser head, experimental study

As practice has shown, enterprises that receive high profits achieve this by reducing costs, rather than increasing the price of products. The national project "Labor Productivity and Employment Support" defines one of the directions for achieving high labor productivity and product competitiveness as training in lean production tools. The article discusses the applied methods of lean production on the example of an architectural and artistic casting enterprise, and also shows the main indicators for evaluating the efficiency of using production capacities.

Keywords: efficiency of equipment operation, ITS index, lean manufacturing methods, Pareto analysis

The article highlights a number of problems that accompany the process of managing the property complex of the territory of the municipality. Issues related to the accounting and analysis of the state of objects of the property complex are considered. The need for systematic research is noted to justify decisions on the use of the city as a resource that provides a comfortable and safe space for life. Improving the process of managing the property complex is an urgent task for the development of cities around the world. An analysis of foreign experience indicates a common understanding of the criteria for the quality of the urban environment and the goals of the reorganization of urban space. When planning the development of urbanized territories, the peculiarities of the city, natural and climatic conditions are not always taken into account, which has a detrimental effect on the quality of the urban environment. It is shown that the effectiveness of the management of the property complex depends on the correct choice of the strategy for involving objects in the economic turnover, restoring their functional significance and ensuring environmental safety. To select effective solutions when solving issues of the use of the territory, it is proposed to use the method based on fuzzy sets, as the most optimal in conditions of high uncertainty and complexity of the processes under consideration.

Keywords: property complex management, decision-making methods, urban environment, urban space, natural and climatic conditions, urbanized territory, resources

The article considers the process of absorption with counterflow of phases with chaotic nozzles. Gas is supplied to the lower part of the column for separation, and liquid is supplied to the upper part of the column to irrigate the packing. In the packing layer, a film flow of the liquid phase occurs over the surface of the contact elements, and in the channels of complex geometry, the gas flow moves in countercurrent. Moreover, the film flow is usually laminar wave, and the movement of the gas phase is turbulent. Through the interfacial surface of the gas-liquid there is an exchange of momentum, mass and energy. Regular and irregular (chaotic) elements of various designs and sizes can be used as nozzles. The initial choice of packing design is carried out based on the ultimate loads that provide the film mode, and then refined based on the obtained efficiency of the process, which must meet the requirements of the technical specifications for the design or modernization of the apparatus. kind at the interface. However, such an approach is possible if the distribution of the interfacial surface area in space is fixed and known, for example, for film contacts of devices and some regular packings. Calculations of the process of air moistening with water were performed using the mass transfer equation (all resistance in the gas phase) in a column with a tubular packing with intensifiers. The efficiency of mass transfer obtained from the numerical solution is compared with experimental data, as well as calculations based on the ideal gas displacement model. It has been established that, taking into account the turbulence of the gas flow, the calculation of the efficiency is adequately consistent with the experiment, and the ideal displacement model slightly overestimates the values ​​of the separation efficiency.

Keywords: absorption, mathematical model, column, packing with intensifiers

The paper discusses methods for improving the efficiency of perimeter security systems through the use of neural network signal processing technologies that serve to increase the information content of data coming from security detectors. The proposed approach allows not only to establish in a timely manner the fact of illegal actions to overcome the perimeter of the object, but also to classify the violator with a minimum level of false positives. Special attention is paid to the issues of optimal control of the reliability of signal processing units with a logical neural network analyzer, considered as queuing systems.

Keywords: integrated security, security detector, detection zone, signal processing unit, artificial neural network, neural network signal processing, reliability, queuing system, optimal control, maximum principle

This article describes the implementation of an orientation software package for a mobile robot with the construction of a terrain map and its subsequent analysis. As part of the work, a software module was developed for a mobile robot using a laser rangefinder (lidar), a Raspberry Pi 3B+ microcomputer with a ROS robotic operating system installed on it is used to obtain data from a laser rangefinder. The algorithm of movement of a mobile robotic complex in space with the construction of a terrain map in real time is described. Such complexes are currently widely used, they can significantly reduce the need for human participation in heavy and dangerous work.

Keywords: mobile robot, robotic complex, laser rangefinder, lidar, ultrasonic sensor, vision system

Automation of procurement activities is considered one of the most well-known applications of IT solutions, since procurement is an integral element of the work of any organization and must be a holistic, systematic process that provides the opportunity to receive all those products, works, offers and services that are so important to the organization with the least expenditure of resources and resources in time. The article highlights the list of functional capabilities of various systems and describes the results of a formalized analysis of the functional completeness of these systems of the procurement session. The analysis also included a conditional system with the desired functionality, according to which it will be clear how this or that system is suitable for the customer.

Keywords: procurement session, procurement activity, comparative analysis of functional completeness, auction, reduction, lot, bid, analysis of compliance of user requirements to systems, similarity of systems

In this article discusses the problems of determining traffic signs for driving a motor vehicle using an artificial neural network apparatus. The relevance of research at this point in time is described, as well as the advantages of using neural networks in determining traffic signs. The input data for determining traffic signs for convolutional neural networks are presented. The architecture of the convolutional neural classification network is formed, in particular, the sequence of layers of the image classification network is considered. A mathematical description of the modeling of the error function and the stochastic gradient descent method is given. A mathematical model of the learning process of an artificial neural network, as well as activation functions: linear functions and sigmoids is presented. An algorithm for forming an artificial neural network model is proposed. The learning process of this function is visualized on the graph. The result of the training is presented.

Keywords: artificial neural networks, classification, convolutional neural networks, deep learning, big data, mathematical modeling, informatics

The article is devoted to the review of food production planning models, the analysis of their features. For this purpose, the classification of models was considered, which included models with deterministic and interval parameters, and also took into account the influence of natural and man-made events. The article considers a model for optimizing the functioning of an agro-industrial cluster, presents models for optimizing the production of food products in agro-industrial clusters of the Irkutsk region.

Keywords: optimization methods, agricultural production planning model, deterministic and interval parameters

The design of an information system for recording appeals received by the election commission is presented. The second stage of the life cycle for information system creation – the design stage is presented. The design was carried out through the use of modern CASE-technologies within the framework of a structural approach using the BPwin modeling tool. A model of the projected information system has been developed. It is constructed using two types of diagrams, tiedly connected each other. They are both the IDEF0 and DFD methodologies. IDEF0 diagrams contain a context diagram and decomposition ones of the first and second levels. The presented series of diagrams describe all the necessary processes sufficient for the activity modeling of the projected information system. A data flow diagrams (DFD) are constructed using the DFD methodology. It shows all data flows used during the execution of processes, including external entities outside the system and data stores inside it. If to supply the presented model with ERD diagrams, as a model of database, one can begin to program and realize an information system.

Keywords: information system, structural approach, methodology, CASE-tool, BPwin, IDEF0, the TO-BE model, decomposition, data flow diagram, data storage

The requirements for the creating information system automating the linguistic center activities are analyzed and optimized. The first and second stages of IP creation Life Cycle are presented. The analysis of the subject area and the design of the information system using the tools and methods of the object-oriented approach is carried out. Using such CASE tool, as the RationalRose, UML diagrams describing the activities of the Language Link linguistic center are constructed. By means of AnyLogic, simulation modeling was carried out and a student testing model was developed to determine the level of language proficiency in order to choose the exam category. The requirements for the projected information system of the linguistic center are formulated. Logical and physical ERD models of the database structure are constructed using the ERWin CASE tool. The design of the user interface of the information system for the linguistic center has been also carried out.

Keywords: domain analysis, design, information system, object-oriented approach, modeling, simulation model, UML language, CASE tool, UML diagram, ERD diagram

The problem of choosing the desired image segmentation algorithm and its real-time implementation arises in systems that work with a high-speed video data stream. Labeling related areas is an important step in preparing images for neural network training set. In this paper a modified one-pass image labeling algorithm for use in field-programmable gate arrays (FPGAs), as well as its implementation using the Xilinx System Generator for DSP and the Matlab/Simulink package was proposed. The results of the algorithm operation on test images, as well as images obtained experimentally, are presented. This algorithm was developed to analyze and evaluate the quality of wheat seeds by classifying their images using artificial intelligence.

Keywords: labeling of related areas, artificial intelligence, segmentation, stream processing

One of the most promising unmanned aerial vehicles (UAVs) designs is a single-rotor scheme, however, due to the complexity of the control principles for such aircraft, there are currently no effective methods for automating their takeoff and landing. The use of systems traditional for multicopter UAVs based on satellite positioning and calculation of control actions using strict mathematical formulas does not allow to fully realize the advantages of a single-rotor scheme. The article considers the existing model of the UAVs control process with a single-rotor scheme, proposes and justifies its changes, and also formulates a method for automatically controlling the take-off and landing of a single-rotor robot helicopter.

Keywords: single-rotor scheme, robotic helicopter, automatic takeoff, automatic landing, method, control

The object of the research is the method of cutting tool wear control that provides evaluation of the periodicity of cutting tool replacement on the basis of vibration signals. Noise and vibration meter VShV-003-M2 is used for registration of vibration level in the process of parts processing. A procedure of determining the index of catastrophic cutting tool wear according to the vibration index with the use of the autocorrelation function and the amplitude-frequency characteristics of the dynamic system is developed. Measurements of vibration readings of a batch of parts in wave-file format were made, by processing the readings an array of data - vibration indicators, allowing to estimate the process of the cutter wear development during the machining process was obtained. Providing control of catastrophic wear of cutting tools is necessary for timely replacement of cutting inserts.

Keywords: vibration index, catastrophic wear, tool, condition monitoring, vibration, turning machine, sensor

This article discusses the development of a universal mobile application "Signal "H"" for people with hearing and speech disabilities based on the analysis of existing mobile applications.

Keywords: fire, mobile application, communication, fire protection units, type of fire, people with disabilities

The paper considers the development of a system for executing machine learning models. The developed system is a set of micro-services that can be used in various areas of production. Technologists for the implementation and prospects of the product being developed are considered. The work uses modern technologies for segmentation and recognition of objects on frames, as well as technologies that allow you to build an infrastructure for this system, and software development technologies.

Keywords: machine learning, computer vision, microservice architecture, pattern recognition

As the number of low-orbit satellite constellations (LEOs) increases, the probability of destructive impact from alien spacecraft (SC) will increase. One of the most effective impacts on the NHS is the setting of relay interference, which is an intercepted and delayed signal. This problem can be eliminated by using the "friend or foe" identification system for the spacecraft. At the same time, in order to reduce the probability of selecting the correct transponder signal by a foreign spacecraft, it is proposed to reduce the time spent on calculating the status of the satellite through the use of parallel calculations using codes of the polynomial residue number system (PRNS). A characteristic feature of these codes is the independent and parallel execution of calculations based on the bases of the PRNS. However, this property of the PRNS code can also be used to correct errors that occur during the operation of the identification system. In this case, the algorithm must perform this procedure at a lower time cost. Therefore, the modification of the error correction algorithm, which makes it possible to provide a higher speed of searching and correcting errors, is an urgent task. The purpose of the work is to reduce the time spent on the execution of the procedure for detecting and correcting errors during the operation of the identification system, by modifying the correction algorithm based on the Chinese residual theorem

Keywords: satellite identification system, codes of the polynomial residue number system, positional characteristic, error detection and correction algorithms