System research and information technologies

Automated control of dynamic systems for ensuring Ukraine’s security using cognitive map impulse process models. Part 1. Demographic security

2025-11-07T23:26:23+02:00

The paper provides a cognitive map (CM) of demographic security and a dynamic model of CM impulse processes described as a difference equations system (Robert’s equations). The external control vector for the CM impulse process is implemented by means of varying the CM nodes’ coordinates. A closed-loop control system for the CM impulse process is proposed. It includes a multivariate discrete controller designed based on an automated control theory method, which generates the chosen control actions. We solve a discrete controller design problem for automated control of dynamic processes to ensure demographic security. The controller suppresses external and internal disturbances during CM impulse processes control based on the invariant ellipsoids method. The paper presents an algorithm for CM weights identification based on the recurrent least squares method. We present the results of a qualitative research study on dynamic processes related to demographic security in Ukraine under various disturbances during martial law.

Analysis and forecasting of the financial benefit for the tennis match outcomes by machine learning methods

2025-11-07T23:49:51+02:00

Tennis is one of the most popular sports in the world, attracting considerable attention from casual fans and professional analysts. The application of machine learning methods enables the accurate prediction of match results, opening up opportunities for profit through betting on likely winners. This study evaluates the financial benefits of predicting tennis match outcomes by identifying an effective sports betting strategy. The study examines various machine learning methods and auxiliary algorithms, comparing them to select the best betting strategy for maximizing the user’s potential profit. In the paper, the method and algorithm for determining effective sports betting strategies were developed. This algorithm and method were tested on tennis game datasets (for both women and men), and the best tennis betting strategy was identified. As part of the study, a software product has been developed to predict the outcomes of tennis matches.

Cognitive AI platform for autonomous navigation of distributed multi-agent systems

2025-11-06T19:11:11+02:00

This paper presents a concept for a cognitive AI platform that enables autonomous navigation of distributed multi-agent systems, exemplified by UAV swarms. The proposed architecture integrates a ground control center with cognitive services and a multi-layered onboard subsystem, supporting a continuous loop of learning, adaptation, execution, and behavioral model updates. Several core mission scenarios are introduced, such as reconnaissance, search and rescue, target neutralization, and deception, showcasing the swarm’s ability to operate autonomously and in a decentralized manner, even under adversarial conditions. An example of a search and rescue mission implementation plan using a cognitive platform that includes adaptive planning, SLAM navigation, swarm coordination, and deep object recognition is presented. The results were partially supported by the National Research Foundation of Ukraine, grant No. 2025.06/0022 “AI platform with cognitive services for coordinated autonomous navigation of distributed systems consisting of a large number of objects”.

Digital twins in AI-controlled navigation tasks for autonomous UAV swarm

2025-11-06T21:12:53+02:00

The article presents the concept and architecture of digital twins (DT) in the tasks of autonomous swarm navigation for unmanned aerial vehicles (UAVs) controlled by artificial intelligence. Study demonstrated that the effective operation of a drone swarm under conditions of disrupted or absent communication with the ground center is enabled by the functional distribution of DT components between the ground center and onboard levels of AI agents. Mathematical models of ground center’s DT provide strategic modeling, training, mission simulation, and post-mission analysis, while onboard AI agents focus on local adaptation, diagnostics, environmental reconstruction, and cognitive behavior control. Special attention is paid to the interface module of the DT, which provides asynchronous interaction with the ground infrastructure. A functional division on the swarm-level, environment, mission, telemetry, and agent-level DTs is proposed. The effectiveness of the “Learn–Simulate–Deploy–Adapt” cycle for continuous improvement of swarm systems in the context of electronic warfare (EW) and dynamic operational environments was justified. The results were partially supported by the National Research Foundation of Ukraine, grant No. 2025.06/0022 “AI platform with cognitive services for coordinated autonomous navigation of distributed systems consisting of a large number of objects”.

Multi-criteria mathematical model of credit scoring in data science problems

2024-07-19T12:07:38+03:00

A multi-criteria optimization mathematical model of credit scoring is proposed. The model is derived using a nonlinear trade-off scheme to solve multi-criteria optimization problems, allowing for the construction of a Pareto-optimal solution. The proposed approach forms an integrated assessment of a borrower’s creditworthiness based on a structured set of indicators that reflect the financial, credit, and social profile of clients. The model is designed for use in intelligent CRM and ERP systems operating on Big Data and does not rely on labeled training samples, making it applicable to unsupervised learning tasks. It can also serve as a foundational layer for further deep-learning analysis. Methodological steps for implementing the model, from indicator normalization to final decision-making, are described. A technological implementation demonstrates the model’s effectiveness in automated loan decisions and fraud detection.

Forecasting the quality of technological processes by methods of artificial neural networks

2025-11-08T15:53:08+02:00

A set of models of feed-forward neural networks has been created to obtain operational forecasts of the quality of mechanical engineering processes. It is established that the use of the Back Propagation of Error machine learning algorithm allows for obtaining forecasted estimates for the controlled parameter of the metalworking process with significantly smaller ranges of the mean absolute percentage error, mean square error, relative approximation error, and variance ratio criterion compared to the BFGS algorithm. It is shown that the proposed MLP neural network models can be recommended for practical applications in controlling the accuracy of the machining process of shaft-type parts.

Mathematical modeling of information diffusion process based on the principles of thermal conductivity

2024-02-19T14:15:50+02:00

Information diffusion, a fundamental process underlying societal evolution and decision-making, shares intriguing analogies with thermodynamics. This paper presents a mathematical model that bridges these domains by proposing an analogy between thermodynamics and information theory. The study introduces a solved heat equation as a foundational framework to model information diffusion within societal contexts. The specified societal conditions embedded within the solved heat equation are central to this model. These conditions encapsulate the susceptibility of a society to assimilate new information, the constraints dictating the number and nature of available information sources, and the dynamics of information distribution characterized by its aggressiveness. The relationship between information diffusion and thermodynamics lies in their inherent propensity to seek equilibrium or optimal states. Leveraging this analogy, the solved heat equation becomes a potent tool to simulate the dynamics of information spread, analogous to the flow of thermal energy within physical systems. This work aims to stimulate further inquiry into the parallels between thermodynamics and information theory, presenting a theoretical framework and software implementation that open new avenues for understanding and modeling information diffusion dynamics within complex societal systems.

Methods of swarm artificial intelligence in autonomous navigation tasks of UAVs

2025-11-08T17:51:00+02:00

This paper presents a comparative analysis of nine swarm intelligence (SI) methods in terms of their suitability for onboard AI platforms in autonomous unmanned aerial vehicle (UAV) swarms. A set of key criteria is defined, including computational complexity, scalability, latency, robustness to agent loss, and adaptability. Decentralized Behavior Trees (BTs) are identified as the most balanced approach for the reactive behavior layer, while the global swarm optimization method GBestPSO proves effective for high-level planning. A hybrid two-layer cognitive architecture is proposed that integrates BTs and GBestPSO, with functional separation between layers and communication based on DDS/RTPS protocols. The architecture exhibits high autonomy, fault tolerance, modularity, and suitability for real-time embedded systems operating in dynamic or adversarial environments. The results were partially supported by the National Research Foundation of Ukraine, grant No. 2025.06/0022 “AI platform with cognitive services for coordinated autonomous navigation of distributed systems consisting of a large number of objects”.

Research and development of methods to improve the quality of mobile communication and mobile internet in high-speed trains

2025-02-08T06:39:16+02:00

This paper proposes effective methods and means to enhance the quality of mobile communication and mobile Internet in high-speed trains. The current issues related to achieving enhanced mobile communication and Internet quality in high-speed trains are discussed within this thematic scope. The practical research examines the metrological features of the proposed new combined methodologies for improving mobile communication and Internet quality in high-speed trains at a model-complex level. It has been established that the methodology combining methods (LTE + Wi-Fi + 5G) shows the best results due to the combination of low-latency and jitter technologies. Metrological measurements confirm its effectiveness through lower latency and jitter values compared to other methodologies. Methodology 3 (5G + Micro-grids) offers high local indicators but is limited in bandwidth. Metrological data confirm the reduced latency and jitter.

Selection of target function in optical coatings synthesis problems

2024-03-31T00:13:25+02:00

The article presents general information on the use of optical coatings in various industries and analyzes the main approaches to optimizing optical filter structures. An approach to solving a class of optical coating synthesis problems is proposed, based on the formation of a new optimization model. The primary attention is paid to the formalization and analysis of the target function. To determine the quality of the optical coating, the deviation of the spectral characteristics from the required ones was estimated using the least squares, least absolute deviation, and minimum criteria. As a result, both smooth and two non-smooth target functions are proposed and analyzed. The peculiarities of their application in solving optimization problems related to optical coating synthesis are described, and corresponding numerical experiments are presented.

Use of methods and tools for ensuring software quality

2024-04-03T16:54:19+03:00

This paper proposes an examination of effective methods and tools for ensuring software quality. The scope of this topic includes current issues related to software quality assurance within the context of analyzing methods and tools used in practice to develop high-quality software. During the modeling process, a new comprehensive model for software quality assurance has been developed, combining modular testing, integration testing, and continuous integration methods. The advantage of this development is its enhanced adaptability to addressing key challenges in software quality assurance. Based on the developed model, strategies and approaches are proposed to improve configuration management processes and identify vulnerabilities in software systems.