INNOVATIVE TECHNOLOGIES AND SCIENTIFIC SOLUTIONS FOR INDUSTRIES

Models of medical center business processes to improve decision-making efficiency

Marina Grinchenko, Dmytro Kutsenko — Sun, 28 Dec 2025 00:00:00 +0200

The subject of the article is the process of digitizing laboratory test results and formalizing the business processes of a medical center in order to develop an information system focused on intelligent data analysis. The goal of this work is to design models that formalize the business processes of a medical center in interaction with patients, enabling the identification of areas that require automation to improve the efficiency of medical services. The following tasks were solved: analyzing the current state of medical data digitalization and the issues related to the unification of laboratory test results; examining the organization of business processes in a medical center and the interaction of its key participants; developing a conceptual and functional model of service delivery; and constructing a business process model that reflects the structured organization of the institution’s activities in interaction with patients. The following methods include SWOT and PEST analyses of the medical center, examination of internal and external documentation, analysis of the existing database and algorithms for providing medical services, the IDEF0 functional modeling methodology, and the BPMN business process modeling approach. The obtained results: an analysis of existing solutions and studies was conducted; the results of SWOT and PEST analyses of the medical center were presented; a conceptual model of medical service organization was created; a functional model was built considering regulatory, organizational, and clinical aspects; and a BPMN-based model of key business processes was developed. Business processes requiring automation using intelligent data analysis methods were identified, forming the framework of the future information system. Conclusions: the proposed models provide a scientific and methodological foundation for automating the collection and processing of laboratory test results, their standardization, and integration into a unified information framework of the medical center. This will enhance the efficiency of the medical center’s business processes in interaction with patients, reduce the time required for processing diagnostic results, minimize the risk of errors, and ensure high-quality support for the provision of medical services.

Content-based image retrieval method in a multidimensional data model at big data scale

Stanislav Danylenko, Kyrylo Smelyakov — Sun, 28 Dec 2025 00:00:00 +0200

The subject of the study is the method and algorithms for content-based image retrieval within the Multidimensional Cube (MDC) model. The goal is to develop a search method based on image descriptor vectors and an algorithm that implements this method in both sequential and parallel versions for MDC. The research tasks include: defining requirements for the search method; analyzing the MDC model structure and defining the approach to the search method; developing search methods and algorithms for scenarios where the model is stored in RAM or in a relational database; integrating parallel computing into the algorithm; analyzing alternative models based on multidimensional trees, graphs, hashing, inverted indexing, quantization and inverted multi-index structures; developing evaluation metrics and conducting experiments to compare the efficiency of the MDC-based method with alternative search models. Methodology: analytical and comparative methods for search algorithm evaluation, modeling, and experimental verification were applied. Thread-level parallelism and hardware optimization methods were used, along with comparative analysis of model efficiency (KD-tree, Locality-Sensitive Hashing, Hierarchical Navigable Small World, Inverted File with Flat Compression, Inverted Multi-Index). Statistical methods were employed to assess results using recall, search time, and model construction time metrics. Experiments were conducted with both web-sourced and synthetic image descriptors, as well as load testing to evaluate the model’s throughput. Results: a new search method and the Wave-Search Algorithm were developed. Its parallel version achieves up to a 3x speedup. For top-10 and top-100 queries in a dataset of 1 million descriptors, MDC shows the best overall performance among the compared models based on the metrics and strong stability under load. Conclusions: the proposed search method and its implementation (Wave-Search Algorithm) efficiently utilize the MDC model’s structure for search tasks, outperforms alternative search models in terms of effectiveness, demonstrates robustness under load, and has significant potential for further development, including the use of hardware acceleration.

Integrated simulation model of swarm control and adaptive routeing of UAVS in a changing air environment

Maksym Yena, Olha Pohudina — Sun, 28 Dec 2025 00:00:00 +0200

Subject matter: the processes of swarm control and adaptive routing of unmanned aerial vehicles (UAVs) in complex and dynamically changing air conditions using adaptive algorithms. Goal: to develop an integrated simulation model that combines swarm control methods, adaptive PID control and adaptive routing algorithms to ensure the safety, optimality and efficiency of UAV fleet movement in conditions of a changing air environment. Tasks: to analyze existing approaches to swarm control and adaptive routing of UAVs; to develop a mathematical model of an integrated system that takes into account the specifics of interaction between UAVs, collision avoidance and dynamic changes in the air environment; to create a swarm control algorithm based on adaptive PID regulation of UAV movement parameters; to develop and implement an adaptive routing algorithm that responds to changes in traffic, weather conditions and other airspace factors; to implement the integrated model in a simulation environment and test its effectiveness; to conduct a comparative analysis of the efficiency of UAV operation with and without the developed algorithms. Methods: use of adaptive PID control methods for dynamic regulation of UAV movement trajectories and ensuring flight accuracy and stability; application of swarm control algorithms (boids-type methods) for synchronization of movement and collision avoidance in UAV groups; nonlinear optimization of routes taking into account dynamically changing conditions, which allows minimizing collision risks, energy consumption and flight time; construction of a graph-theoretic model of airspace for effective route planning and situation forecasting; creation of digital twins of the air environment for conducting simulation experiments. Results: an integrated simulation model of swarm control and adaptive routing of UAVs was developed, which takes into account air environment variables; adaptive PID control and swarm control algorithms ensured a reduction in the average positioning error and collision avoidance of UAVs; According to the results of simulation experiments, an increase in the reward of agents by ≈50%, an increase in the successful completion of episodes by ≈50%, and a reduction in agent errors on the way to the goal by ≈10%. Conclusions: created integrated model allows for effective management of UAV flotillas in conditions of a changing air environment, significantly increasing the safety and optimality of routes; the use of adaptive algorithms and graph-theoretic models provides high forecasting accuracy and risk minimization; the results of the study confirm the prospects for implementing the developed algorithms for UAV control in urban and regional conditions.

Application of machine learning methods for analysis of UX/UI data from mass user surveys"

Yevhenii Ihnatiuk, Andrii Popov — Sun, 28 Dec 2025 00:00:00 +0200

The subject of this article is the application of machine learning methods to the interpretation of UX/UI data collected through mass user surveys on digital platforms. The paper explores the hypothesis that coordinated use of various classification models allows for the identification of behavioral patterns that hold predictive value for assessing users’ interactions with product features. The goal is to perform a comparative analysis of classification accuracy using real-world UX/UI survey data. The methodology includes data preprocessing, feature encoding, normalization, clustering, and training of six model types: decision trees, random forest, gradient boosting, multilayer perceptron (MLP), logistic regression, and k-nearest neighbors. Particular attention is paid to how these models perform on small-scale, mixed-type UX/UI datasets. The modeling results demonstrate that even with limited data, it is possible to uncover significant relationships between socio-demographic variables, user types, and feature usage. These findings suggest that machine learning can be a promising approach for analyzing user behavior, with the potential for further integration into decision support systems. This approach can be adapted to various domains where structured user data is available, including online education, healthcare, public administration, urban services, and internal organizational platforms.

Optimization of mobile flow routing in a wireless sensor network using heuristic algorithms

Liubov Melnikova, Olena Linnyk, Svitlana Shtangei, Artem Marchuk — Sun, 28 Dec 2025 00:00:00 +0200

The subject of the study is a wireless sensor network (WSN) with a mobile sink. The purpose of the work is to improve the performance of the WSN, increase its lifetime and functionality by reducing the data transmission delay time in the process of polling routers by optimizing the mobile sink route using the most efficient algorithm. To achieve this goal, the following tasks must be performed: optimize the route of the WSN mobile stock by solving the traveling salesman problem using the branch and bound method and comparing the conditional average route length of a set of solutions without optimization and with optimization using the Robbins–Monroe procedure; conduct a comparative analysis of the exact solution of the traveling salesman problem obtained by the branch and bound method and the approximate solution obtained by heuristic methods; formulate practical recommendations for the selection of algorithms for optimizing the mobile flow route depending on the size of the sensor network. The following methods were used: simulation modeling, optimization methods, mathematical data processing. Results achieved. The solution of the mobile flow route optimization problem in BSM using heuristic algorithms was investigated in order to formulate practical recommendations for selecting mobile flow route optimization algorithms depending on the size of the sensor network. A comparative analysis was performed of the exact solution of the traveling salesman problem, performed using the branch and bound method, and the approximate solution, performed using heuristic methods. To obtain an approximate solution, two heuristic algorithms were implemented: the ant colony optimization (ACO) algorithm and the simulated annealing (SA) algorithm. These algorithms were implemented for the traveling salesman problem with specific coordinates for each problem. The effectiveness of the algorithms is evaluated on networks of various sizes, from 10 to 500 nodes. The simulation results show that ACO is highly effective on small and medium-sized networks (up to 50 nodes), providing shorter routes and faster computation times. SA is determined to be the best scalable on large networks (100 nodes and more), offering stable performance under high computational load. Conclusions. It has been demonstrated that introducing optimization in the selection of the mobile flow route in BSM leads to a reduction in the length of the mobile flow bypass contour in the range of 30–40% depending on the network size and the distances between routers. Reducing the polling time of routers in a sensor network leads to an increase in the residual power of power supplies, and thus extends the life of the network. It has been proven that the use of heuristic algorithms is only appropriate when a high speed of calculating a new mobile flow route is required. If the speed of calculating a new route is not critical, then it is better to use accurate calculation algorithms. For each algorithm, parameters must be selected depending on the task at hand, since these parameters affect the speed of the algorithm and can reduce the range of possible routes that can be obtained during calculations. The study proves the importance of individual parameter tuning of algorithms to improve the accuracy and adaptability of solutions in mobile flow routing tasks.

Models of distribution logistics of technical defense products under wartime risk conditions

Yuriy Polupan, Olga Malyeyeva — Sun, 28 Dec 2025 00:00:00 +0200

The subject of this article is the processes of organization and optimization of the distribution logistics of technical defense products under wartime conditions, in particular, the development of a network logistics structure considering reverse flows, risks, and limited resources. The purpose of the study is to improve the efficiency of distribution logistics of technical defense products in wartime by constructing an adaptive structure of logistics flows and developing a mathematical optimization model that accounts for risks and resource constraints. The article addresses the following tasks: analysis of the specific features of distribution logistics for technical defense products in combat conditions; development of a structural model of logistics flows that considers direct and reverse links as well as the reuse of components; construction of a mathematical model for optimizing logistics processes with consideration of time costs, delay risks, and resource constraints; justification of the application of scenario analysis and adaptive planning to enhance the resilience and continuity of supply under uncertainty. The following methods are applied: a systems approach, structural decomposition of logistics processes, risk-based approach, constrained mathematical modeling, scenario analysis, and adaptive planning. The results obtained include the construction of a structural model of logistics flows for supplying the Armed Forces of Ukraine, which takes into account direct and reverse flows as well as component reuse; the development of a mathematical model for optimization of distribution logistics with an objective function of minimizing time and constraints on supply volume, total risk, and the number of routes. It is demonstrated that risk consideration significantly affects the choice of optimal routes and strategies. The feasibility of using scenario analysis and adaptive planning to ensure continuity of supply in combat conditions is substantiated. Conclusions. The proposed structural and mathematical models make it possible to reduce the logistics cycle time, increase the resilience of the logistics system to risks, and ensure rapid response to changing circumstances. The use of reverse logistics and component reuse helps reduce costs and mitigate resource shortages. Scenario analysis and adaptive planning are effective tools for managing the distribution logistics of technical products under uncertainty and wartime risks.

Integral survivability metric of an information system on a mobile platform under functional cascading and secondary failures

Vitalii Tkachov, Ihor Ruban — Sun, 28 Dec 2025 00:00:00 +0200

The subject of the study is an integral metric of the survivability of an information system on a mobile platform under intermittent connectivity, partial observability, and cascading and secondary failures. The system is presented as a multilevel "data–processes–resources" structure. The goal of the work is to develop an integrated survivability metric that takes into account time deviations from requirements, their propagation through a dependency graph, and hidden violations; to propose a single-pass algorithm and prove its properties on scenarios. The article solves the following tasks: to formalize service requirements and structure projection; to build a metric with risk-oriented aggregation of deficits, cascading correction, and systematic consideration of secondary failures; to develop single-pass calculations in "availability windows"; to prove monotonicity, scale invariance, and resistance to omissions; to define rules for parameter tuning and configuration comparison; to perform experimental verification and comparison with baseline indicators. The following methods are used: projection of services at the level of data, processes, and resources; use of conditional average excess as risk-oriented aggregation; cascading correction by depth and width; organization of secondary failures and desynchronization fixation; normalization in "availability windows"; single-pass updates close to linear complexity. The following results were obtained: an integrated metric of survivability was proposed and formally defined; its monotonicity in terms of parameters, boundedness, invariance to scaling, and resistance to omissions were proven; the difference from the average deficit was shown – the proposed metric amplifies the contribution of rare deep failures and responds to cascading, while the average values are almost constant; in the absence of service deficits, a positive level is maintained due to the detection of latent secondary failures; scenarios yield consistent families of curves and a three-dimensional surface that demonstrate controllable sensitivity tuning and stable ranking of configurations for industrial mobile platform operating conditions. Conclusions: The proposed metric provides a service-consistent assessment of the state of the information system, while taking into account time deficits, cascading propagation, and secondary failures. It is suitable for sequential computing in resource-constrained environments, enhances early risk detection, and supports monitoring, localization, and survivability.

Intellectual data analysis in relational information and analytical systems

Valentin Filatov, Oleh Zolotukhin, Maryna Kudryavtseva — Sun, 28 Dec 2025 00:00:00 +0200

The subject of the study is the methods of intellectual analysis, namely the construction of a decision tree, associative analysis, the identification of patterns between related events based on data presented by a relational model. The purpose of the study is to analyze the features of information units and data structures, using the example of relational systems that affect the technology of knowledge extraction. Tasks: the article solves the following tasks: to consider the relational data model as the most popular and effective data structure used in intelligent information systems for data processing and storage; to analyze the operations of relational algebra, the operational component of the relational data model regarding the application of aggregate functions; to develop a general formal statement of the problem of knowledge extraction from a relational database; to consider the concept of functional associative rules; the ID3 decision tree generation algorithm focused on data processing in relational systems is analyzed. The following methods are implemented: modern view and trends in the field of data mining; features of building information systems based on relational databases, relational algebra, theory of normalization of relations; analysis of literature on the topic of research; comparative analysis. Results achieved: the relational data model is considered as the most effective data structure used in intelligent information systems for data processing and storage. A group of aggregate functions of relational databases is identified and analyzed with respect to key attributes of the relation, which makes it possible to build logical dependencies between information units of the subject area being analyzed. The task of extracting knowledge from the database is formally formulated. The concept of functional associative rules is introduced. The ID3 decision tree generation algorithm focused on data processing in relational systems is carefully analyzed. The semantic network (SN), built on the basis of the proposed approach, allows to increase the efficiency of decision support systems. Conclusions: the universal approach proposed in the article to build a relational data model of an information system for searching for associative patterns in data allows to solve a whole class of typical tasks in which objects are connected by a "many-to-many" relationship or M →N. The relational database model is proposed as a universal information structure for solving associative analysis tasks and presenting knowledge in the form of a semantic network. The examples given in the article confirm the effectiveness of the developed and considered approaches to solving the problem of data mining in the environment of relational systems. Solving the problem of identifying knowledge in data will allow to improve the quality of management decisions made.

A two-layer model to detecting falsified information using neural networks in socially oriented systems

Artem Khovrat, Volodymyr Kobziev — Sun, 28 Dec 2025 00:00:00 +0200

The subject matter of the article is the problem of detecting fabricated information in socially oriented systems characterized by significant user load. The goal of the work is to develop of a two-layer fake information classification model based on a combination of a naive Bayesian classifier and a hybrid recurrent-convolutional neural network. The following tasks were solved in the article: conducting expert evaluation and domain analysis to determine basic classes of fake information; analyzing linguistic markers of disinformation and developing feature vectors for classification; developing models for data segregation using a naive Bayesian classifier; conducting experimental verification of the proposed two-layer model in comparison with the RCNN approach. The following methods used are – analytical method for forming a set of disinformation markers; inductive method for determining the target set of indicators for implementing the second layer of the model; expert evaluation for determining the most influential efficiency factors and feature weight coefficients; experimental and multi-criteria evaluation methods for determining the most effective model. The following results were obtained – a classification structure for types of fake information was formed, including five categories from jokes to globally harmful news. A set of discriminative features characteristic of fabricated information was developed, including primary linguistic markers and secondary stylometric indicators. It was determined that the approach using a two-layer model demonstrated, on average, a 15% improvement in efficiency compared to direct application of a hybrid recurrent-convolutional neural network. Conclusions: the application of a two-layer data classification model successfully expands the capabilities of basic detection of data falsification, including scale assessment and analysis of fabrication intentionality. Empirical analysis shows that implementation of a two-layer model with a naive Bayesian classifier achieves an average 15% performance improvement compared to simple neural network application. This performance difference becomes particularly significant in high-throughput systems where rapid identification and response to fabricated information are critical operational parameters. The obtained result allows us to assert the feasibility of implementing the proposed approach, and accordingly, provides the opportunity to reduce the impact of such information in socially oriented systems, especially during crisis situations.

Application of computational intelligence technologies in clusterization problems of wireless sensor networks

Olena Semenova, Andrii Dzhus, Volodymyr Martyniuk — Sun, 28 Dec 2025 00:00:00 +0200

The subject matter of the study is the process of selecting the head node of a cluster in wireless sensor networks (WSNs) using intelligent approaches that can adapt to changing environmental conditions. WSNs consist of a large number of sensor nodes with that collect, process and transmit data. Effective clustering is one of the main mechanisms for optimizing the operation of WSNs, as it allows reducing energy consumption, increasing network reliability and scalability. The goal of the study is to analyze the features of using modern computational intelligence tools and methods to increase the efficiency of the sensor node clustering process, which allow taking into account a variety of factors when making decisions about cluster formation and selecting head nodes. Traditional clustering algorithms are not always able to adapt to changes in network parameters, especially in the presence of heterogeneous nodes or changes in topology. In this regard, methods based on computational intelligence, in particular genetic algorithms, neural networks, fuzzy logic, as well as hybrid approaches, are becoming increasingly relevant. These methods allow taking into account a number of parameters when forming clusters and selecting cluster heads. Tasks of the study are analysis of existing approaches to clustering in BSM; development of a clustering fuzzy inference system; construction of a rule base for making optimal decisions; experimental verification of the proposed system. Methods of the study are tools of computational intelligence, in particular neural network learning, genetic optimization and fuzzy control, as well as computer modeling. The article analyzes the advantages of using each of the existing approaches. Results are: a structure of the fuzzy inference system was developed, input and output variables were determined, a database of fuzzy rules and membership functions was formed. The operation of the fuzzy system was simulated in the MATLAB environment. The developed system was also optimized and its operation validated. Conclusions: the use of hybrid intelligent approaches has significant advantages for solving clustering problems in BSM, which may indicate the prospects for further development of systems capable of functioning effectively in conditions of limited resources and high environmental complexity.

Development of an intelligent system for early detection of vision pathologies based on analysis of eye micromovement

Oleksiy Mormitko, Serhiy Tymchyk — Sun, 28 Dec 2025 00:00:00 +0200

The subject of the research is the development and implementation of an eye health monitoring system using modern technologies, in particular wireless sensor networks, biometric sensors and software for automatic detection of vision diseases. Special attention is paid to methods of processing and analyzing data from sensors for accurate diagnosis of pathologies such as cataracts, glaucoma, diabetic retinopathy and other eye diseases. The aim of the work is to create a system that allows detecting visual impairments in real time, performing automatic diagnostics and providing treatment recommendations. The system integrates with a mobile application and can work together with other medical devices to facilitate patient-doctor interaction. The tasks solved in the article: 1) develop a system for collecting and monitoring eye health data; 2) create algorithms for processing and analyzing the obtained data; 3) develop a mobile application; 4) test the developed system. Methods used in the study: data analysis from biometric sensors, algorithms for automatic comparison of indicators with a database of normal and pathological values, and wireless data transmission technologies (Bluetooth, Wi-Fi). The developed database and software provide secure storage and analysis of medical data. Results. The results of the study showed that the system allows monitoring the state of vision in real time with high accuracy (85–90%), detecting pathologies in the early stages and automatically notifying the patient and doctor about detected deviations. The system demonstrates effectiveness in early detection of diseases and allows for timely prescribing of treatment or additional examinations. Conclusions. The developed system is an important step towards integrating medical technologies into everyday life. It provides timely detection of vision disorders and convenient access to monitoring results. In the future, it is possible to expand the functions to detect other eye diseases and integrate with additional medical devices for comprehensive monitoring of the patient's health.

The method development for controlling the mobile platform with four steering wheels

Igor Nevlyudov, Sergiy Novoselov, Oksana Sychova, Sergii Zygin — Sun, 28 Dec 2025 00:00:00 +0200

The subject matter is a method for determining the robot trajectory with four steering wheels to reach a given point on a terrain map. The research goal is to develop a method for determining the orientation of the wheels depending on the trajectory of the mobile platform to increase the maneuverability of an autonomous robotic vehicle in a limited production space. Tasks to be solved: to analyze similar solutions, describe the proposed design of the steering unit mechanism for a mobile robotic cart, describe the kinematics of a mobile robot with four steerable wheels, develop an algorithm for the steering unit control module, propose a method for controlling a mobile platform with four steerable wheels, and perform experimental studies on the application of the proposed method. Scientific novelty: a method for determining the orientation of the wheels to reach a given point on the terrain plan has been proposed. An algorithm for performing calculations using a software tool has been developed. A mathematical justification for the method of controlling individual wheel blocks of a mobile platform has been provided. Methods of the study: modeling methods and automatic control theory, methods for describing linear dynamic systems, analytical modeling methods, computer modeling in the Matlab/Simulink environment. Results and conclusions: The mobile platform movement principle using four independent steering wheels is considered. A method for determining the orientation of the steering wheels depending on the trajectory of movement is proposed, which is based on the geometric analysis of the position of the platform and the target point, which allows calculating the angle of rotation of each wheel in such a way as to ensure movement to a given point without lateral slippage. A mathematical model of the control system is built, a structural and functional diagram is developed, an algorithm for processing commands, calculating the angles of rotation is described, and a three-level control system is implemented: linear speed, wheel orientation angle and angular speed of the entire platform. The developed mock-up sample of the mechatronic steering wheel assembly is described. The simulation conducted in the Simulink environment confirmed the operability of the proposed system.