Переглянути
Нові надходження
Документ Adaptive multicriteria model for supporting decision-making in sports selection problems(Хмельницький національний університет, 2026) Hnatchuk, Alina; Hnatchuk, YaroslavIn the current environment of information technology development, intelligent data analysis, and decision support systems, there is a need to formalize and automate sports selection processes. Existing models of multi-criteria assessment of athletes are usually static in nature and focused only on analyzing the current level of preparedness, which limits their effectiveness in selecting young candidates for whom development potential is important. This paper proposes an adaptive multicriteria decision support model that integrates the assessment of the current level of candidates' characteristics with formalized consideration of their development dynamics over time. A mathematical apparatus for forming an integral assessment of prospects has been developed, based on the hierarchical aggregation of normalized indicators and the application of the hierarchy analysis method to determine weight coefficients. For the first time, a generalized characteristic indicator has been introduced, which combines normalized indicator values and the rate of their change, allowing not only current results but also development prospects to be assessed. An experimental study on a sample of 24 candidates showed a heterogeneous structure of the distribution of integral assessments, which confirms the feasibility of using adaptive thresholds to classify candidates according to their level of prospects. The sensitivity of the model to changes in the α parameter, which allows adjusting the balance between current indicators and development dynamics, was analyzed. The results confirmed the stability of the model and the consistency of the overall ranking structure of candidates when changing weight parameters. The proposed model ensures transparency, reproducibility, and interpretability of the assessment, which makes it suitable for use in intelligent decision support systems for the selection of young athletes. The practical benefit of the model is that it allows coaches and sports selection specialists to effectively and objectively identify candidates with high development potential, taking into account both their current level of preparedness and the dynamics of their characteristics. The model can be integrated into intelligent decision support systems for planning the training process and strategically forming teams of young athletes.Документ Analysis of information technologies and methods for automatic updating of threat detection models in computer systems(Хмельницький національний університет, 2026) Isaiev, Tymur; Atamaniuk, OlhaThe development of intelligent adaptive information technologies for automatic updating of threat detection models in computer systems is one of the most important directions in modern research on information technologies. Computer systems today operate in environments that are constantly changing, influenced by new software, evolving hardware, and diverse data processing methods. Traditional static approaches, which rely on fixed rules or predefined models, often become outdated quickly and fail to provide the necessary adaptability. Existing approaches to detection in computer systems have been studied extensively, and while they provide valuable insights, they also demonstrate clear limitations. Signature-based methods depend heavily on known patterns and therefore struggle to identify new or unexpected phenomena. Heuristic analysis allows for broader generalization but is frequently associated with high rates of false positives, which reduces its practical usefulness. Behavioral monitoring can capture dynamic changes in system activity, yet it requires significant computational resources and may slow down performance. Machine learning models offer adaptability and the ability to learn from data, but they demand large amounts of training information and careful tuning to avoid errors. Hybrid approaches attempt to combine the strengths of multiple techniques, but they often face difficulties in seamless integration and optimization within existing infrastructures. Because of these limitations, researchers are increasingly focused on developing frameworks that incorporate automatic updating mechanisms. Such frameworks are designed to be self-adaptive, meaning they can evolve continuously in response to new conditions without requiring manual intervention. Real-time adaptation is a central feature of these systems, enabling them to improve accuracy, reduce false positives, and optimize the use of computational resources. By integrating intelligent updating mechanisms, information infrastructures can achieve higher levels of stability and efficiency. This not only enhances the overall performance of computer systems but also ensures that they remain relevant and effective in environments where change is constant. The ability to evolve automatically, without relying on outdated static methods, positions these technologies as a cornerstone of future developments in information systems. The continuous evolution of computational environments demands solutions that are flexible, intelligent, and capable of real-time adaptation. By embracing adaptive frameworks, researchers and developers can create systems that are not only more accurate and efficient but also more resilient and scalable. This marks a decisive step toward the next generation of computer systems, where adaptability and automation are essential for long-term reliability and success.Документ Survey of tools and technologies for psychoemotional screening and determining the status of patients with depression(Хмельницький національний університет, 2026) Pytlyak, MaksymThe article is devoted to a comprehensive analysis of the current state and prospects for the development of information technologies for psychoemotional screening of patients with depressive disorders. The relevance of the study is due to the global increase in the prevalence of mental disorders, which in the conditions of modern challenges, in particular martial law, is becoming a critical threat to public health and economic stability. The work systematizes scientific sources, which made it possible to identify key trends in the field of digital psychiatry. The main attention is paid to a comparative analysis of existing methods according to eight fundamental criteria that determine the suitability of the technology for real clinical implementation. Among them, the availability of decision-making algorithms, patient routing mechanisms in the primary care setting, the use of validated psychometric tools, integration with electronic medical records, real-time notification systems, adaptation to the individual user norm, ethical transparency, and research on objective behavioral markers. The results of the analysis indicate a significant fragmentation of existing solutions - with a high interest of researchers in the use of biomarkers (voice, eye tracking, electroencephalography and locomotor activity) and artificial intelligence, there is an almost complete absence of systems integrated into the state medical infrastructure. It was found that most of the existing mobile applications and cyber-physical systems operate in isolation from the primary care level, which complicates timely diagnostics and continuity of treatment. The work places special emphasis on the importance of digital phenotyping, which allows objectifying the patient's condition through monitoring motor activity, but it is proven that such data must necessarily be combined with classical clinical protocols. It is substantiated that the lack of integration with electronic medical records and formalized routing algorithms are the main barriers to creating an effective national screening system. Based on the identified "blank spots" in world scientific practice, the author has proven the need to develop a unified information technology that would act as a full-fledged link in the medical process. The analytical basis of the article serves as a theoretical basis for designing a new information technology capable of providing a closed cycle of "monitoring - diagnostics - routing - treatment". The scientific novelty of the work lies in the systematic approach to evaluating screening technologies, which allows us to clearly identify the vectors of further research in the direction of creating information technology adapted to the needs of the modern healthcare system.Документ Hybrid method of adaptive control of variable mode of unmanned aerial vehicles with intelligent online compensation of disturbances(Хмельницький національний університет, 2026) Tanasiichuk, StepanThe article resolves the current scientific and technical contradiction between the need to increase the accuracy of navigation control of autonomous unmanned aerial vehicles (UAVs) and the strict resource constraints of on-board computing systems. An intelligent-robust control architecture is proposed, based on the synthesis of the adaptive alternating mode method (ASMC) and the recurrent neuro-fuzzy network RSEFNN. The scientific novelty of the work lies in the improvement of the hybrid approach, which, unlike classical robust methods, uses an intelligent observer for online identification and compensation of nonlinear components of dynamics and external disturbances. This made it possible to significantly reduce the gain coefficients of the discontinuous part of the controller, minimize the "rattling" effect, and increase the energy efficiency of actuators. Mathematical proof of the stability of the closed-loop system using the direct Lyapunov method confirmed the asymptotic convergence of trajectory tracking errors to zero and guaranteed the numerical stability of the neural network training processes. An important practical contribution is the implementation of methods for suppressing highfrequency oscillations by replacing the discontinuous control function with its smooth approximation based on the adaptive boundary layer and hyperbolic tangent. To ensure the determinism of the computational cycle in real time, optimization using the Padé method was applied, which allowed minimizing algorithmic latency and achieving a control frequency of up to 1000 Hz on embedded CPUs without specialized accelerators. The results of the comparative analysis confirmed the high robustness of the developed method under conditions of intense wind loads. In particular, the use of the ASMC+RSEFNN controller allowed to increase the positioning accuracy in steady state by 10.2–12.6 times compared to classical PID controllers. The integrated neuro-fuzzy identifier provided effective compensation for systematic wind shear, which is a critical factor for performing UAV precision guidance tasks in difficult meteorological conditionsДокумент Seamless tiling of quasi-periodic textures via an optimal cyclic shift on a discrete torus(Хмельницький національний університет, 2026) Bedratiuk, AnnaIn practical computer vision and computer graphics pipelines, it is often necessary to repeatedly replicate a single texture sample to construct a large canvas, background, or regular covering. When the mosaic is not strictly periodic, visible seams appear at the boundaries during repetition, disrupting the perceptual continuity of the texture and often manifesting as a regular grid of artifacts. Such seams not only degrade visual quality but can also alter local gradients and spectral components, which is critical for subsequent processing stages. Common seamless stitching methods increase computational complexity, introduce additional hyperparameters, and modify the local image statistics, which is undesirable in reproducible pipelines and in tasks where the invariance of pixel values is essential. The goal of this work is to propose a simple, reproducible, and computationally efficient method for seam reduction in quasiperiodic textures by selecting an optimal cyclic shift of the pattern that minimizes the energy of mismatch between opposite boundaries. The tile is modeled as a function on the discrete torus ℤ𝑀 × ℤ𝑁. A cyclic shift group 𝐺 = ℤ𝑀 × ℤ𝑁 is introduced, acting as a permutation of pixels. For each shift 𝜏𝑎,𝑏 , the boundary seam energy 𝐸(𝜏𝑎,𝑏 𝐼) is computed in a band of width 𝑤 for opposite boundary pairs, and the minimizing shift is selected. When needed, the evaluation is accelerated via cyclic correlations and FFT. Experiments on synthetic and real textures show that the optimal cyclic shift significantly reduces seam energy and the visual prominence of boundaries during tiling without modifying pixel values. For strictly periodic tiles, the method does not degrade the result. The proposed approach is a lightweight baseline tool for seamless tiling: it does not perform stitching but selects the best cut of the torus. The method is easy to integrate into production pipelines and can be used as a preprocessing step before further processingДокумент Modeling the process of recognition of pacemaker dysfunction(Хмельницький національний університет, 2026) Medzatyi, Dmytro; Hryshchuk, IlliaThe article presents a comprehensive study aimed at solving a pressing scientific and practical problem - modeling and designing information technology for recognizing pacemaker dysfunctions to increase the efficiency of diagnostics and reliability of life support systems. The relevance of the work is due to the rapid growth of the number of cardiovascular diseases in the world and in Ukraine in particular, which leads to an increase in the number of operations for implanting pacemakers, the functioning of which requires continuous and highprecision monitoring. The authors analyzed the world experience in using modern diagnostic tools, including neural networks for analyzing radiographs, mobile applications for remote monitoring, and machine learning algorithms for ECG analysis, which revealed the lack of integrated solutions that would combine different methods for detecting technical and clinical failures. The proposed approach is based on the use of multimodal input data, such as information about the patient's symptoms (dizziness, arrhythmia, weakness), device hardware reports (pacing rate, battery status, intracardiac signals), ECG and Holter monitoring results, as well as data from physical activity and intracardiac pressure sensors. The scientific novelty of the study lies in the development of a mathematical model of the process of recognizing pacemaker dysfunction, presented as a sequence of tuples and transformations that provide data preparation, selection of the most informative signs of cardiac activity and direct recognition of the system state. Special attention is paid to the stages of signal normalization and artifact filtering, which guarantees high accuracy of classification of disorders even under difficult operating conditions or during physical exertion of the patient. The practical significance of the work is confirmed by the creation of a structure of output results, which include not only automated fixation of anomalies, but also the formation of specific recommendations for changing pacemaker settings and instant notification of medical personnel, relatives and the patient himself. The proposed technology allows to ensure a continuous monitoring cycle, minimize the risk of human error when interpreting complex diagnostic data and significantly improve the prognosis for patients with high dependence on an artificial pacemaker. Thus, the results obtained create a reliable foundation for building modern information technologies for cardiac care.Документ Technology for selecting musical genres taking into account human mental health based on machine learning(Хмельницький національний університет, 2026) Alekseiko, Vitalii; Petiak, Olena; Bondarchuk, Bohdana; Petruk, TamaraThe research considers the technology of intelligent selection of musical genres taking into account human mental health based on machine learning methods. The relevance of using music therapy as an effective non-drug approach to improving emotional state, reducing stress, anxiety and preventing psychoemotional disorders is substantiated. Modern scientific research on the influence of music on mental health is analyzed, as well as existing approaches to recommender systems in the field of healthcare. A comparative analysis of the performance of various machine learning methods for the task of classifying and predicting the user’s psychoemotional state is conducted, based on the results of which the most relevant algorithm is selected. Hyperparameters are selected and optimized in order to increase the accuracy, stability and generalization ability of the model. A concept of a system that provides personalized selection of musical genres according to the individual psychological characteristics of the user is proposed. The compliance of the developed technology with the principles of explanatory and responsible artificial intelligence is outlined, in particular with regard to the transparency of decisions, the ethics of data use and the minimization of potential risks. The consistency of the research results with the UN Sustainable Development Goals is shown, in particular in the context of ensuring well-being, mental health and access to innovative digital technologies in the field of healthcare