The article presents ways to improve the accuracy of the classification of normative and reference information using hierarchical clustering algorithms.

Keywords: machine learning, artificial neural network, convolutional neural network, normative reference information, hierarchical clustering, DIANA

Today, the problem of global climate change and the associated degradation of permafrost is a priority area of ​ ​ research. In the regions of the Far North, a change in temperature by half a degree contributes to the emergence of geocryological dangers: the appearance of ravines, thermokarst subsidence, heaving, the formation of residential ice and, as a result, the destruction of houses and infrastructure. In Russia, the permafrost zone occupies about 63-65% of its territory and extends for thousands of kilometers. Various engineering and geological impacts, including man-made ones, represent a serious geocryological hazard and can lead to degradation of frozen soils in various regions. Due to the rapid thawing of ice and climate change, collapses and voids form on frozen soils. Also, when thawing permafrost, a large amount of groundwater is formed and there is a risk of salinization of nearby water and coastal zones. This can lead to the loss of resources that are necessary for the life of the local population, as well as for the economy of the region. Despite the fact that there are numerous programs and studies on this topic, a huge amount of work has not yet been carried out in Russia to eliminate geocryological threats.

Keywords: Geocryology, permafrost, ground, frozen soil degradation, thawing, monitoring, Yakutia, cryolithozone, geocryological hazard

In the context of stable demand for consumer electronics, current methods of automated software testing in production often prove to be inefficient, leading to an increase in software errors. This paper examines an enhanced method of automated testing using Remote Procedure Call (RPC) and cloud technologies. The main objective of the research is to create a universal and effective system for automated software testing, capable of scaling and adapting to various platforms and libraries. The results of the experiment confirmed the possibility of integrating the described method with existing testing systems without significant modifications, ensuring a higher efficiency of the testing process and a reduction in its duration.

Keywords: automated testing, consumer electronics devices, consumer electronics, software, remote procedure call, software quality, software testing, cloud devices, software production, testing task manager

The possibility of detection of steganography in digital images based on the classification of stegocontainers is investigated. The obtained results demonstrate the effectiveness of using deep neural networks for solving this problem. The LSB method can be detected using EfficientNet b3 architecture. The achieved classification accuracy is above 97%. Using of steganography methods in frequency domain can be effectively detected by classifying their representation in the form of a digital YCrBr model, with augmentation (vertical and horizontal rotations). The classification accuracy is above 77%.

Keywords: Steganography, stegocontainer, machine learning, classification, digital image, deep learning, CNN, EfficientNet b3, confidentiality, information protection

This scientific article examines the application of artificial intelligence and machine learning in the textile industry with an emphasis on the automation of the design of weaving weaves. The article discusses research and approaches using neural networks, genetic algorithms, deep learning methods and computer vision to create, optimize and analyze weaves. The main attention is paid to the comparison of existing software solutions that allow automating the design process and significantly improving its productivity, accuracy and quality. The importance of integrating AI and machine learning into the textile industry is emphasized, as this opens up new opportunities for automating processes, improving product quality and increasing the competitiveness of the textile industry at the global level.

Keywords: automation, modern systems, design technologies, computer-aided design, information systems, software, fabric drawings, computer-aided design of weaving patterns, innovations in the textile industry, process optimization, digitalization

The article is devoted to the study of crowd behavior in public buildings during a fire. A method for evaluating the effectiveness of organizing the evacuation of people from a public building is proposed, which makes it possible to take into account the spread of panic among evacuees. The method is based on the development of an evacuation simulation model that takes into account the impact of certain factors on the degree of people's panic, which implements an agent-based approach. The proposed method allows, when describing the psycho-emotional behavior of each agent separately in the process of evacuation, to evaluate the effectiveness of organizing the evacuation of the crowd as a whole. The simulation results on the example of a shopping and entertainment center show that possible panic conditions of evacuees can affect the efficiency of evacuation.

Keywords: evacuation, panic, simulation model, efficiency assessment method, shopping and entertainment complex, agent-based approach

The paper considers the possibility of using waste from the forest industry, construction waste and ash and slag waste from boiler heating as a basis for the creation of biofertilizers and components that improve the structure of heavy soils. The analysis of experience on the impact of crushed bricks, coniferous and leaf litter with the inclusion of wood components, and ash and slag waste of boiler heating on the growth functions of red clover and watercress over various time intervals is presented. The possibility of using the presented waste in the process of self-infestation of territories is considered. A number of experiments have been conducted to identify the phytotoxic effect, as well as the reaction of general inhibition or stimulation of growth indicators of higher plants when used as a substrate in pure form, or a mixture with natural soil, wood components, samples of ash and slag waste of various shelf life, brick fighting.

Keywords: forest industry waste, construction waste, broken bricks, ash and slag waste, self-fouling, phytotoxicity, soil structure, morphological changes of plants

This article presents a research study dedicated to the application of the YOLOv8 neural network model for road sign detection. During the study, a model based on YOLOv8 was developed and trained, which successfully detects road signs in real-time. The article also presents the results of experiments in which the YOLOv8 model is compared to other widely used methods for sign detection. The obtained results have practical significance in the field of road traffic safety, offering an innovative approach to automatic road sign detection, which contributes to improving speed control, attentiveness, and reducing accidents on the roads.

Keywords: machine learning, road signs, convolutional neural networks, image recognition

Outlier detection is an important area of data research in various fields. The aim of the study is to provide a non-exhaustive overview of the features of using methods for detecting outliers in data based on various machine learning techniques: supervised, unsupervised, semi-supervised. The article outlines the features of the application of certain methods, their advantages and limitations. It has been established that there is no universal method for detecting outliers suitable for various data, therefore, the choice of a particular method for the implementation of research should be made based on an analysis of the advantages and limitations inherent in the chosen method, with the obligatory consideration of the capabilities of the available computing power and the characteristics of the available data, in including those including their classification into outliers and normal data, as well as their volume.

Keywords: outliers, machine learning, outlier detection, data analysis, data mining, big data, principal component analysis, regression, isolating forest, support vector machine

Models of open-loop and closed-loop systems for automatic control of air supply to a steam boiler are constructed. An open-loop system is modeled and, on its basis, a closed-loop system with a PI controller tuned to the optimum modulo is developed. The introduction of a frequency converter into the control system for more economical and gentle operation of the fan electric drive is considered. The developed system consists of models of a controller, a frequency converter, an asynchronous motor and a blower fan. The simulation results are presented, demonstrating the operability of the resulting system in compliance with the requirements for stability and speed. The modernized closed system has a number of advantages over the existing open one, and the described method of its construction can be applied when implemented at enterprises using air blowers.

Keywords: automatic pressure control system, automatic control system, closed system, open system, PI controller, modular optimum

One of the actual problems in the field of analysing loads and impacts on bearing structures is their identification. It means the point of application, the type of action and its intensity in cases where there is an impact result, but the parameters that caused this result are not determined. For example, it is an accident action, as a result of which the structure is deformed and collapsed. The solution of such problems arises when analysing accidents on load-bearing structures in construction, as well as when monitoring the deformed state of structures in time. The paper proposes to use the principles of neural network modelling to solve the problem of identifying the impact in the form of a concentrated force on the example of beam systems. The values of linear and angular nodal displacements at some action are considered as input data to neurons. As an example, the linearly deformable beam of constant stiffness is considered, the material of which is a continuous isotropic medium.

Keywords: neural network, deflections, load-bearing structure, displacement, deformation, identification

The article is devoted to the study of problematic issues of the formation of organizational and technical systems of the "cyberpolygons" class using the original methodological apparatus for the feasibility study of system engineering solutions for their construction. The features of existing approaches to the justification of system engineering solutions for the construction of organizational and technical systems, information technology and technical systems are considered. Directions for their development are proposed, taking into account the dynamics of the phased creation and modernization of organizational and technical systems with simultaneously developing infrastructure projects and solutions. Formal aspects in the methodological apparatus are reflected in the change in the composition of the functional components in the conceptual and analytical models, the corresponding formal descriptions of their relationships and characteristics, as well as in the modification of the procedures for the technical and economic assessment of options for building a cyberpolygon. The method of technical and economic evaluation of options for constructing a cyberpolygon proposed in this study makes it possible to rank alternative options for the infrastructures of the created cyberpolygon according to the value of their technical and economic efficiency and to select the rational one from them.

Keywords: information security, infrastructure, cyberpolygon, feasibility study, means of protection

This article discusses the practical implementation of the self sovereign system based on the technology of a distributed decentralized data registry, also known as blockchain. An implementation of the system based on the Proof of Stake (PoS) consensus-building mechanism is presented, which provides a number of advantages over alternative implementations described in the literature. The results of measuring system performance in comparison with known implementations based on Proof of Work (PoW) are presented, confirming the high efficiency of the proposed solution.

Keywords: decentralized, user-centric, identity-based encryption, blockchain, self Sovereign identity system

The article discusses the methods and approaches developed by the authors for the recommendation system, which are aimed at improving the quality of rehabilitation of the patient during respiratory training. To describe the training, we developed our own language for a specific subject area, as well as its grammar and syntax analyzer. Thanks to this language, it is possible to build a devereve describing a specific patient's training. Two main methods considered in the article are applied to the resulting tree: "A method for analyzing problem areas during training by patients" and "A method for fuzzy search of similar areas in training". With the help of these methods, it is proposed to analyze the problem areas of patients' training during rehabilitation and look for similar difficult areas of the patient to select similar exercises in order to maintain the level of diversity of tasks and involve the patient in the process.

Keywords: Recommendation system, learning management system, rehabilitation, medicine, respiratory training, marker system, domain-specific language, Levenshtein distance

This publication considers the architectural and compositional dominants of public spaces of two small historical settlements on the Don River - the Cossack villages of Veshenskaya and Razdorskaya. The author focuses on the study of the patterns of formation of the historical and cultural framework of a small historical settlement, as well as the process of development of its architectural and compositional core, which includes the public space of the center of the Cossack villages and the architectural and compositional dominants associated with it. The article provides a retrospective analysis of these dominants in the planning structure of the Cossack villages of Razdorskaya and Veshenskaya in a chronological framework from the beginning of the 19th century to the beginning of the 19th century until now.

Keywords: historical and architectural environment, architectural and compositional dominant, small historical settlement, public space, Cossack village,Cossack village of Veshenskaya, Cossack village of Razdorskaya (Razdorskaya-on-Don), project of protection zones