System research and information technologies

Ranking of the technical condition of aircraft according to the diagnostic data of the glider design

Andrii Bolohin — 2025-06-28

Analysis of the data obtained through non-destructive testing of the power elements of the airframe structure enables the division of the studied aircraft into separate groups based on operational methods and, accordingly, predicts the probability of trouble-free operation of the airframe structure. Based on a bionic logical analysis of data on the technical condition of the aircraft’s airframe design, the article considers methodological approaches to building the author’s mathematical model of ranking the aircraft fleet. The ranking of the technical condition of aircraft serves as the basis for solving the problem of preparation, making a decision on extending the service life and taking into account the aging of the airframe design in operating conditions. The application of the proposed set of methods will create and establish a practical and effective system of intelligent support for decision-making on aircraft operations.

Time series forecasting using the normalization model

Viktor Bondarenko — 2025-06-28

Empirical constructions of time series models based on the reduction of initial data to normally distributed values have been proposed. The goal of a normalization method is to construct an optimal forecast that is linear for the updated data, and the forecasted original data is recovered through the inverse transformation. The different variants of such transformations have been considered, including the reduction of initial data to Gaussian fractional Brownian motion and a one-dimensional transformation using a strictly monotonic function. The computational experiment based on real data, which allows for a stationary model, confirms the higher quality of the forecast by the normalization method compared to traditional models.

Strategy for ensuring asymptotic convergence of the process of non-linear estimation of dynamic object parameters

Anton Silvestrov — 2025-06-28

The article considers a step-by-step strategy of sequential use and adjustment of a parallel model to an object of identical structure with orthogonal operators, a series-parallel model to an object with the connection of operators of a certain type for orthogonal approximation in order to obtain asymptotically unbiased estimates of coefficients of a structurally identical to a dynamic object of a mathematical model under conditions of noise of measurements of the initial variable of the identification object and non-convexity of the proximity functional of the initial variables of the object and the model in a space of coefficients of the object’s mathematical model. Structural diagrams of each stage of identification are given using refined parameters and the structure of the model of object. This algorithm was implemented to identify the parameters of the mathematical model of aircraft, provided that the sample of experiment data is limited and there is of the initial a significant range of deviations of state variables from the basic mode.

The concept of intelligent training system for Ukrainian school final STEM exam preparation

Anatoliy Kulik — 2025-06-28

The National Multi-subject Test has been prepared and conducted in Ukraine in online learning conditions for several years. Test results show a decline in schoolchildren’s performance in mathematics. The article presents a prototype of an intelligent training system for solving mathematical problems that should become an accessible test preparation tool. The system provides a solution to a wide range of mathematical problems in a step-by-step mode. The system is developed in accordance with the principle of rational management by diagnosis, which implies the presence of many diagnostic models. It allows for deep diagnostics of student errors. Artificial intelligence tools will make it possible to implement individual recommendations for each student, taking into account their level of preparation and learning goals.

Analysis of web accessibility of Ukrainian higher education institutions’ websites

Borys Kuzikov — 2025-06-28

In today’s digital world, website content accessibility for all users, including people with disabilities, is crucial. This paper examines the accessibility of web content on the websites of Ukrainian higher education institutions to assess their compliance with modern standards and requirements. The goal is to identify problematic aspects and develop strategies for improving the accessibility of educational web resources. The study covered data from the main pages of 372 higher education institution websites, whose addresses were obtained from the Unified State Electronic Database on Education (“USEDE”). The built-in accessibility enhancement tools used on these pages were analyzed. The paper also summarizes global experience in regulating web accessibility requirements. The analyzed regulatory documents include Web Content Accessibility Guidelines version 2.1 in their rules. Automated analysis tools WAVE and Axe were used to assess website compliance with the Guidelines. Results showed that the most common problems were insufficient highlighting of hyperlinks (characteristic of 84.8% of sites, Success criteria (SC) 2.4.4, 4.1.2), insufficient element contrast (84.6%, SC 1.4.3), lack of alternative text for images (42.9%; SC 1.1.1), and non-compliance with markup and semantics requirements. The conclusions present an analysis of the problems identified during the study, along with the authors’ recommendations for addressing them. The analysis results were systematized and published on a specially created web resource. The authors plan to conduct similar studies on an ongoing basis. It is also necessary to pay attention to problems identified when using automatic analysis tools. The Axe tool identified 11.875 cases of element contrast issues, accounting for 24% of the total number of detected problems. However, this figure is not final, as it does not account for the full range of possible color perception violations and overlooks the contrast of elements against backgrounds with non-uniform colors.

From CAD and BIM to digital twins

Anatolii Petrenko — 2025-06-28

A Digital Twin is a virtual model of a physical object or system that uses real-time data to simulate the behavior of its real counterpart. It can be a product, machine, building, or even an entire city. Digital modeling is a fundamental technology for creating Digital Twins, as it provides a methodology for representing physical objects in the virtual world. CAD (Computer-Aided Design) can be used to create the initial model of a Digital Twin. BIM (Building Information Modeling) is a specialized form of CAD that focuses on building projects incorporating more information than just geometry but also data on time, costs, operations, and maintenance. This paper examines how these technologies are increasingly integrated with each other, utilizing mathematical modeling that, through virtual computational experiments, provides an understanding of the complex functioning of objects and informed decision-making in various fields. The integration of Digital Twins and CAD is transforming the ways products are designed, modeled, and optimized in the industry. BIM models can serve as the basis for creating Digital Twins of buildings, which are then used to optimize energy consumption, maintenance, and repair. With the growth of the Internet of Things (IoT), Digital Twins are receiving more and more real data, making them even more accurate and useful for forecasting and optimization. The use of artificial intelligence to analyze data collected by digital twins allows predicting breakdowns, optimizing processes, and even automating the control of systems.

Streamlined management of physical and cloud infrastructure through a centralized web interface

Ivan Byzov — 2025-06-28

The article focuses on the development of a centralized management system for both physical and virtual servers via a web interface. This system enables server infrastructure administration through various tools. Key components of the system, integration with server management tools, the use of Paramiko for remote access via SSH, and the potential application of other technologies for managing cloud and physical servers through a web interface are discussed. The system enables centralized management of various server types through a web interface, supporting both basic and advanced administrative operations. Integration with Docker and support for cloud APIs provide convenient automation and simplify operations with both cloud and physical servers. As a result, the system serves as a versatile tool for DevOps engineers. The study highlights the relevance and importance of a centralized approach to server infrastructure management, thereby enhancing the efficiency and reliability of server operations in modern environments.

Navigating challenges in deep learning for skin cancer detection

Vladyslav Nikitin — 2025-06-28

Skin cancer is one of the most prevalent malignancies worldwide. A critical factor in reducing mortality rates is the early detection. It underscores the need for accessible Computer-Aided Diagnostic (CAD) systems. Recent advancements in Deep Learning (DL) have shown great promise in addressing this challenge. Despite this progress in the field of machine learning, researchers encounter numerous obstacles when it comes to skin cancer classification. This article examines the current state of DL-based skin cancer diagnostics. Critical aspects of system development, including data preprocessing, model training, and performance evaluation, are addressed. Moreover, the article highlights opportunities for innovation that could significantly advance the field. By providing a comprehensive overview, this article aims to guide researchers and practitioners in optimizing DL models, addressing existing limitations, and exploring emerging trends to enhance diagnostic accuracy and accessibility.

A conceptual model and a system for replacing text in an image while preserving the style

Pavlo Maslianko — 2025-06-28

Text replacement in images, particularly while preserving its style, is a complex task that requires solving a range of scientific challenges and developing new technical solutions. One of the main issues is maintaining the authenticity and harmony of the image after modifications. The Research Objective is the development of a conceptual model and a system for text replacement in images with style preservation based on systems engineering methodology and the Eriksson-Penker business profile, ensuring the natural integration of new text elements into the image’s context. Implementation Methodology – the systems engineering methodology and the Eriksson-Penker business profile are used to formalize the structured process of developing a system for text replacement in images with style preservation. Research Results – a method for developing the system based on systems engineering techniques was proposed, consisting of four main stages. In the first stage, the system structure is modeled as an Eriksson-Penker business profile. In the second stage, a set of processes is defined that are characteristic of the Data Science system class and the CRISP-DM international standard. Also, the structural and dynamic representations of the conceptual model, as well as the component interaction interfaces, are modeled. The third stage involves implementing a specific version of the system, while the fourth stage focuses on system verification and validation. A systems engineering method for the conceptual model and system for text replacement in images with style preservation has been proposed. It is based on a modified Eriksson-Penker business profile for metalevel system representation and international standards for Data Science and Data Mining processes.

Determining the level of propaganda in opera librettos using data mining and machine learning

Iryna Dats — 2025-06-28

The article presents an adapted multifactorial model that can be used to determine the level of propaganda in librettos to world operas. This model was created using the linear convolution method, for which eight indicators were selected that are most effective in identifying elements of propaganda in the text, taking into account the subject area's peculiarities. Each of the selected indicators was calculated using statistical analysis, data mining, and machine learning methods. As a result of applying the proposed method, the value function is calculated for each libretto, based on which a conclusion is made as to whether it contains elements of propaganda or not.