Том 12, № 5 (2025)

The article proposes an enhancement of an information system for analyzing road traffic accident hotspots (RTAs), developed within the framework of a program-targeted approach and geoinformation technologies. The system’s architecture is described, including spatial analysis algorithms, methods for identifying and consolidating clusters, as well as mechanisms for formalized accident representation. Special attention is given to the implementation of accident hotspot prioritization based on risk factors, recommended measures, and the expected mitigation effect. Verification was conducted using real-world urban accident data. The proposed solution demonstrates the stability of the implemented algorithms and their applicability in digital transformation tasks related to transport infrastructure. Key directions for future development are outlined, including the integration of fuzzy logic, digital twins, and artificial intelligence modules.

Amid growing requirements for the quality and reliability of electronic equipment in high-tech products (including rocket and space technology), there is a noticeable gap between industry needs and the capabilities of domestic electronic component bases (ECB). This article examines existing approaches to the selection and application of ECB, including both Russian and imported components, with a focus on current limitations. Special attention is given to the necessity of transitioning from traditional ECB selection to automated component design using modern information technologies. A detailed design workflow for equipment components is presented, covering modeling, physical verification, integrated circuit design, unit and printed circuit board (PCB) design, enclosure development, and the use of modern CAD and process simulation tools. The paper emphasizes information support for various design stages, as well as methods and tools that ensure high precision, reliability, and compliance with technical-economic requirements.

The article examines a systematic approach to the development and implementation of innovative satellite services, based on accounting for consumer expectations and forecasting market needs. The authors analyze key factors influencing the successful promotion of such services, including technological trends, competitive environment, and quality management methods. Special attention is paid to technological forecasting methodologies, such as Foresight analysis and weak signal monitoring, as well as the development of roadmaps for creating radically new solutions. A conceptual model of consumer satisfaction integrating ISO 9000 principles is proposed, and mechanisms for adapting services to changing market conditions are discussed.

The purpose of this research is to develop and validate an integrated methodology for predicting the demand for university graduates in a regional labor market by applying data-mining tools and machine-learning techniques. Employment monitoring data from Turgenev Orel State University for 2022–2024 served as the empirical basis. The Random Forest algorithm was used to forecast graduate employment rates across aggregated fields of study, while the K-means clustering method grouped specialties according to their demand levels. The analysis identified three stable clusters – “high”, “medium”, and “low” employment prospects – provided actionable recommendations for adjusting curricula and enrollment quotas, and highlighted programs that need additional interdisciplinary digital competencies. The resulting models demonstrated high accuracy (MAE = 13.33%, R² = 0.78) and no multicollinearity issues, as confirmed by VIF values. The proposed methodology offers universities an effective tool for strategic enrollment planning, improving graduate employability, and real-time adaptation of educational offerings to the dynamic needs of the economy. It can also be embedded into digital education-management platforms and regional workforce-demand forecasting systems.

This study presents a comprehensive comparative analysis of the effectiveness of modern neural network architectures for countering targeted social engineering attacks on industrial systems. The paper characterizes the main social engineering methods, based on which a group of them is identified that have a critical impact on domestic production. The experimental part of the study is based on an open dataset containing 651 191 URLs categorized into four types: safe resources, defaced links, phishing resources, and malware distributors. The paper presents a systematic evaluation of both classical and innovative machine learning approaches, including Kolmogorov-Arnold networks (KAN), graph neural networks (GNN), capsule neural networks (CapsNets), and their hybrid combinations. The results demonstrate significant superiority of hybrid architectures, where the combination of CNN + LSTM achieved a maximum accuracy of 92.29%, and CNN + KAN demonstrated a result of 92.00%. A detailed analysis revealed the specific effectiveness of various architectures for specific threat categories: CapsNets demonstrated the best results in identifying safe resources (98.60%), while CNN + LSTM were most effective in detecting phishing attacks (72.76%). The scientific novelty of this work lies in establishing a correlation between the type of neural network architecture and the nature of a potential cyberthreat, which creates a methodological basis for developing next-generation adaptive security systems for industrial infrastructure.

The article presents an advanced technique for categorizing objects of critical information infrastructure (CII), taking into account industry criticality. The aim of the study is to improve the objectivity and accuracy of the categorization process, minimize subjective distortions, and optimize the allocation of resources for ensuring information security. The authors propose a methodology based on calculating an industry criticality coefficient, which integrates expert assessments across five key criteria: national security, economic significance, social importance, industry interdependence, and potential damage. The methodology was tested on 14 industries, enabling their classification into three criticality categories. The results demonstrated high consistency among expert evaluations and confirmed the effectiveness of the proposed approach. Implementing this technique facilitates differentiated planning of CII protection measures and optimizes regulatory requirements.

The article discusses the application of mathematical modeling and cluster analysis methods for processing monitoring data on the activities of educational institutions of higher education. The relevance of the research is determined by the need for an objective assessment of the effectiveness of universities, the identification of problem areas and the development of targeted management solutions. The paper analyzes key indicators, including educational, research, international, financial and economic activities, as well as the salary level of teachers. The main focus is on clustering methods that allow universities to be grouped according to similar characteristics. Hierarchical, centroid, and density algorithms are considered, as well as the specifics of their application in the context of multidimensional educational data. Special importance is attached to the preprocessing of indicators, including normalization and standardization, to ensure the correctness of the results. The clustering quality is assessed using the silhouette index and other metrics, which makes it possible to determine the stability of the selected groups. The results of the study demonstrate that automated clustering of monitoring data helps identify typical university development trajectories, optimize resource management, and develop differentiated support measures. The proposed approach can be integrated into a regular monitoring system, providing operational analytics for management decision-making. The prospects for further research are related to the development of adaptive algorithms, forecasting the dynamics of indicators and the creation of interactive analytical platforms.

This article describes an algorithm for applying an intelligent analysis model to detect anomalies in statistical observation data for educational organizations. The definition of an anomaly is given, typical anomalies that may be contained in statistical reporting data are analyzed. The classification of anomaly detection techniques is given depending on the level of markup of the training sample, and possible ways of marking up data to present the results of the anomaly search are analyzed. The analysis and description of the process of collecting and processing statistical data of educational organizations in the Scientific and Technical Center of RTU MIREA is carried out. The weaknesses of the data collection process are analyzed, which can be strengthened by applying intelligent analysis to search for anomalies in the data. The analysis and mathematical description of the format and features of the received and stored statistical data is carried out. An algorithm has been developed for preparing data for training an intelligent analysis model, taking into account their specifics, as well as the subsequent application of the trained model to detect anomalies in the data under consideration. The algorithm was tested on real data using the autoencoder neural network model.

This article discusses the application of the video-computer-psychodiagnostics and psychocorrection (VCP) method to determine the reliability of Tinkoff Bank clients in addition to credit scoring, as well as an example of diagnosing clients of the microfinance organization Bank 911 in on-line mode. The problem of reducing the risks of consumer lending in Russia and the importance of solving it are identified, existing methods for determining reliable borrowers in the banking sector, such as Personal Credit Rating, scoring system, psychoscoring, their shortcomings in the context of a large flow of borrowers are studied, the essence of the video-computer psychodiagnostics and psychocorrection method is described and the result of the study of its application for diagnosing Tinkoff Bank clients is given. The advantage of the VKP method is indicated, which consists in the fact that, using this method, it is possible to quickly identify a fraudster who deliberately came with forged documents, or simply a borrower who initially does not intend or cannot repay the loan, and also to give a forecast of the behavior of clients for a long period, since with the help of the program it is possible to identify a potential predisposition to fraud, such properties as “falsehood” and “carelessness”. A comparison of the VKP method with other systems for recognizing emotions in an image, its advantage and the possibility of application in organizations associated with a danger to life and extreme situations are given.