YZYurii Zhuravskyi

Yurii Zhuravskyi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yurii Zhuravskyi has a total of 103 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Development of a comprehensive method of learning artificial neural networks for organizational and technical systems

    by Pavlo Zhuk, Andrii Shyshatskyi, Yurii Zhuravskyi, Nina Kuchuk, Serhii Shostak, Andrii Veretnov, Valentyn Olshanskyi, Roman Bahmut, Bohdan Karpishen, Ievgenii Kuzminov

    The object of the study is the learning process of artificial neural networks (ANNs). The problem addressed in the study is to increase the reliability of ANN learning while ensuring a given level of learning efficiency. The originality of the proposed complex method is: – verification of the architecture of organizational and technical systems (OTS) and the dynamics of its change, due to the use of an improved cheetah pack algorithm. This allows leveling the influence of the human factor and increasing the reliability of ANN learning; – taking into account the possible values of the state of the environment and the actions of agents, which allows taking into account in full the conditions and factors in which ANN learning is carried out. Due to this, the reliability of the ANN learning process increases under the influence of destabilizing factors; – formation of a generalized architecture of multi agent learning due to the use of the ensemble mutation procedure. Due to the use of this procedure, it becomes possible to achieve an increase in the reliability of ANN learning; – selected the type and parameters of the membership function due to the use of the appropriate procedure. Due to the use of this procedure, it becomes possible to achieve an increase in the accuracy of ANN learning; – reduction of sensitivity to a priori hyperparameters of models and tendency to excessive fragmentation of data in OTS, due to the use of improved procedures, which increases the reliability of ANN learning; – for ANN learning, a sample with an uneven distribution of the states of OTS functioning is used, which achieves the flexibility of ANN learning under the influence of destabilizing factors. The proposed complex method of ANN learning minimizes the geometric error of the division by an average of 25%, thereby increasing the reliability of ANN learning while maintaining a given level of efficiency, as confirmed by the results of a computational experiment

  • Open Access

    Creating a polymodel framework for the construction of intelligent decision support systems

    by Nina Kuchuk, Leonid Artushin, Yurii Zhuravskyi, Iraida Stanovska, Oleksii Kononov, Nadiia Protas, Serhii Shostak, Serhii Neronov, Anton Nikitenko, Andrii Veretnov

    Intelligent decision support systems (IDSS) are the object of the study. The research problem is to improve the accuracy of the mathematical description of the process of processing heterogeneous data in IDSS. The subject of the study is a mathematical description of the processes of processing heterogeneous data in IDSS. The proposed polymodel complex for the construction of IDSS solutions, which allows: – systemically represent the relationship between IDSS construction models in the course of their calculation and computing tasks; – simulate the process of functioning of the IDSS, due to the use of an algebraic (formal) approach to object-oriented modeling and design of the IDSS; – determine the rational tactical and technical indicators of the IDSS for solving specific calculation and computing tasks, due to the multi-level description of the order of construction of the IDSS; – make the transition from one type of data representation in IDSS to another due to the presence of appropriate mathematical transformations; – multidimensional to describe the process of processing heterogeneous data in IDSS, due to the use of a multidimensional matrix model of IDSS data; – approach the solution of computational-calculation tasks in IDSS by using an interconnected set of mathematical models of IDSS construction; – formalize the process of constructing IDSS, which allows combining IDSSs using different algorithmic and software. The disadvantages of the proposed polymodel complex include the need to adapt the mathematical apparatus to the specific operating conditions of the IDSS. The proposed polymodel complex should be used for the construction of IDSS to solve general and specialized calculation tasks, as well as to solve the task of integrating various types of IDSS

  • Open Access

    Development of a scientific and methodological apparatus for ensuring the functional reliability of special-purpose information systems

    by Andrii Shyshatskyi, Yurii Zhuravskyi, Ganna Plekhova, Igor Shostak, Elena Odarushchenko, Olena Feoktystova, Serhii Shostak, Nadiia Protas, Olena Shaposhnikova, Nataliia Hnatiuk

    The object of the study is special-purpose information systems (IS). The problem solved in the study is increasing the functional reliability of special-purpose IS. The development of a scientific and methodological apparatus for providing a functional special-purpose IS was carried out. The originality of the study consists in: – systematic assessment of the state of functional reliability of special-purpose IS using the proposed principles of its provision; – construction of multidimensional dependencies of the state of functional reliability of special-purpose IS, which achieves the assessment of functional reliability of IS based on an arbitrary number of indicators; – assessment of the functional reliability of special-purpose IS using the sharing of measurement data and fuzzy expert assessments, which solves the problem of dimensionality; – construction of the time dependence of changes in indicators that characterize the state of functional reliability of special-purpose IS, which allows determining the moments of deviation of their values from the nominal one; – assessment of the functional reliability of information services based on the concept of profiles, which achieves the possibility of decentralized influence on special-purpose IS to increase its functional reliability; – to reduce uncertainty about the state of functional reliability of special-purpose IS, due to the use of an appropriate approach in the method of assessing the functional reliability of information services based on the concept of profiles. The proposed scientific and methodological apparatus provides an increase in the efficiency of assessing the functional reliability of the IS by an average of 40%, while ensuring high reliability of the obtained results at the level of 92%, which is confirmed by the results of a numerical experiment.

  • Open Access

    Set of mathematical models for information systems resource management

    by Yurii Zhuravskyi, Serhii Neronov, Ganna Plekhova, Olena Feoktystova, Igor Shostak, Anastasiia Voznytsia, Dmytro Fedorchuk, Oleksandr Perehuda, Mykola Romanchuk, Roman Stavisiuk, et al.

    In this chapter of the research, management methods based on bio-inspired algorithms are proposed. The basis of the research is the theory of artificial intelligence. The method is aimed at solving optimization tasks, variable solutions are defined in such a way that complex dynamic objects work in their best point (mode) according to the optimization criteria determined. In the research, the authors proposed:– management method using a bio-inspired algorithm;– method of finding solutions using the improved flying squirrel algorithm;– method of assessing the state of dynamic objects using the population algorithm.Each of the methods was based on canonical optimization algorithms, but they were improved by the authors of the research.The essence of the improvement of these methods, which is the scientific novelty of each of them:– the initial position of the agents is determined taking into account the type of uncertainty due to the use of a correction factor for the degree of awareness of the state of the initial situation in relation to the object of analysis;– the initial speed of each agent is taken into account, which makes it possible to research complex functions;– the speed of movement is regulated according to the priority of finding a solution;– using the procedure of deep learning of knowledge bases of algorithm agents due to learning both architecture and parameters of artificial neural networks;– select the best individuals in the flock by using an improved genetic algorithm, which improves the reliability of the decisions made.A limitation of the research is the need to have an initial condition database complex dynamic object, the need to take into account the time delay for collecting and proving information from sources of information extraction. It is advisable to use the proposed approach to solve the tasks of evaluating complex and dynamic processes characterized by a high degree of complexity.

  • Open Access

    Scientific and methodological framework for processing heterogeneous data in decision support systems

    by Yurii Zhuravskyi, Dmytro Fedorchuk, Oleksandr Perehuda, Mykola Romanchuk, Roman Stavisiuk, Dmytro Stupak, Serhii Neronov, Ganna Plekhova, Olena Feoktystova, Igor Shostak, et al.

    This section of the study presents a scientific and methodological framework for processing heterogeneous data within decision support systems. The research is grounded in the theory of artificial intelligence, specifically focusing on evolving artificial neural networks, fundamental procedures of genetic algorithms, as well as advanced hybrid bio-inspired algorithms. In the course of the study, the authors propose the following:– a method for processing heterogeneous data in organizational and technical systems;– a method for evaluating the reliability of special-purpose radio communication systems using artificial intelligence theory. The implementation of the proposed scientific and methodological framework enables the following:– reduction of the probability of premature convergence of the metaheuristic algorithm within decision support systems;– maintenance of a balance between convergence speed and diversity of the metaheuristic algorithm during decision-making processes;– consideration of the type of uncertainty and data noise in the metaheuristic algorithm when operating within decision support systems;– accounting for available computational resources of the decision support system;– prioritization of search processes by agents within the swarms of the metaheuristic algorithm;– initialization of swarm individuals with consideration of the type of uncertainty present in the system;– precise training of individuals in metaheuristic algorithms;– execution of both local and global searches considering the level of noise in the data describing the analyzed object;– application as a universal tool for assessing the state of analysis objects through hierarchical object representation;– verification of the reliability of the obtained results;– enhancement of the reliability of object state assessments by constructing object-oriented and relational models of the object’s state with varying levels of hierarchy;– avoidance of the local optimum problem.

  • Open Access

    The method for detecting cyber attacks on information systems based on artificial intelligence technologies

    by Yurii Zhuravskyi, Hennadii Miahkykh, Andrii Shyshatskyi

    The object of this study is artificial immune systems. The problem addressed in the study is improving the responsiveness of cyberattack detection in information systems while ensuring a predetermined level of convergence, regardless of the number of destabilizing factors. The subject of the study is the cyberattack detection process. A cyberattack detection method for information systems based on artificial intelligence technologies is proposed. The originality of the method lies in the use of additional enhanced procedures that allow: – initializing the initial population of swarm agents and verifying information system parameters using an improved bat algorithm, which minimizes the error of entering incorrect data concerning the operational information system of military forces; – performing initial identification of attacks specific to the given information system using a decision tree; – conducting initial selection of antibodies for each swarm of the artificial immune system using an improved genetic algorithm; – replacing unfit individuals for search through antibody population renewal; – performing simultaneous solution search in multiple directions; – calculating the required amount of computational resources in cases where available resources are insufficient for the necessary calculations. An example application of the proposed method was conducted for cyberattack detection in an operational military force group. The results demonstrated an average increase in detection accuracy by 16%, an average improvement in responsiveness by 12%, and a high result convergence level of 95.23%

  • Open Access

    Development of a polymodel resource management complex for intelligent decision support systems

    by Andrii Shyshatskyi, Yurii Zhuravskyi, Ganna Plekhova, Igor Shostak, Olena Feoktystova, Oksana Dmytriieva, Ivan Starynskyi, Andrii Strepetov, Serhii Rudoi, Anton Zakharov

    The object of the study is intelligent decision support systems. The problem addressed in the research is to improve the accuracy of modeling the functioning process of intelligent decision support systems. A polymodel complex for resource management of intelligent decision support systems has been developed. The originality of the study lies in: – the comprehensive description of the functioning processes of intelligent decision support systems; – the capability to model both an individual process occurring in intelligent decision support systems and to perform comprehensive modeling of the processes taking place within them; – the establishment of conceptual dependencies in the functioning process of intelligent decision support systems. This makes it possible to describe the interaction of individual models at all stages of solving computational tasks; – the description of coordination processes in hybrid intelligent decision support systems, which ensures an increase in the reliability of managerial decision-making; – the modeling of processes for solving complex computational tasks in intelligent decision support systems through the conceptual description of the specified process; – the coordination of computational processes in intelligent decision support systems, which leads to a reduction in the number of computational resources of the systems; – the comprehensive resolution of conflicts through a set of corresponding mathematical models. The proposed polymodel complex is advisable for use in solving the problem of managing intelligent decision support systems characterized by a high degree of complexity


  • Open Access

    Development of a method of increasing the efficiency of decision-making in organizational and technical systems

    by Salman Rasheed Owaid, Yurii Zhuravskyi, Oleksandr Lytvynenko, Andrii Veretnov, Dmytro Sokolovskyi, Ganna Plekhova, Volodymyr Hrinkov, Tetiana Pluhina, Serhii Neronov, Oleksii Dovbenko

    The object of the study is organizational and technical systems. The subject of the study is the decision-making process in the problems of management of organizational and technical systems. A method of increasing the efficiency of decision-making in organizational and technical systems using artificial intelligence is proposed. The research is based on the giant armadillo swarm algorithm to find a solution regarding the state of organizational and technical systems. Giant armadillo agents (GAA) are trained using evolving artificial neural networks, and an advanced genetic algorithm is used to select the best GAA. The method has the following sequence of actions: – input of initial data; – setting GAA on the search plane; – numbering GAA in the swarm; – determining the initial velocity of GAA; – preliminary evaluation of the GAA search area; – classification of food sources for GAA; – sorting the best GAA individuals; – attack on termite mounds by GAA; – digging termite mounds by GAA; – updating GAA positions; – checking for the presence of a GAA predator; – escape and fight against GAA predators; – checking the stop criterion; – training GAA knowledge bases; – determining the amount of necessary computing resources of the intelligent decision support system. The originality of the proposed method lies in setting GAA taking into account the uncertainty of the initial data, advanced procedures of global and local search taking into account the noise degree of data on the state of organizational and technical systems. The method makes it possible to increase the efficiency of data processing at the level of 14–19 % using additional advanced procedures. The proposed method should be used to solve the problems of evaluating complex and dynamic processes


  • Open Access

    Development of a solution search method using an improved fish school algorithm

    by Aqeel Bahr Tarkhan, Yurii Zhuravskyi, Andrii Shyshatskyi, Tetiana Pluhina, Volodymyr Dudnyk, Ihor Kiris, Oleksii Nalapko, Nadiia Protas, Serhii Neronov, Vitaliy Nechyporuk

    The object of research is decision support systems. The subject of research is the decision-making process in management problems using the fish school (FSH) algorithm, an advanced genetic algorithm and evolving artificial neural networks. A solution search method using an improved FSH algorithm is proposed. The study is based on the FSH algorithm for finding a solution on the object state. For training FSH, evolving artificial neural networks are used. The method has the following sequence of actions: – input of initial data; – processing of initial data taking into account the degree of uncertainty; – checking the fitness function of the solution found; – procedure of feeding fish agents (FA); – instinctive-collective FA swimming; – calculation of the center of school gravity; – collective voluntary FA swimming; – changing the FA swimming parameters; – training of FA knowledge bases. The originality of the proposed method lies in the arrangement of FA taking into account the uncertainty of the initial data, improved global and local search procedures taking into account the degree of noise of data about the state of the analysis object. The peculiarity of the proposed method is the use of an improved FA training procedure. The training procedure consists in learning the synaptic weights of the artificial neural network, the type and parameters of the membership function, the architecture of individual elements and the architecture of the artificial neural network as a whole. The use of the method makes it possible to increase the efficiency of data processing at the level of 18–25 % due to the use of additional improved procedures. The proposed method should be used to solve the problems of evaluating complex and dynamic processes in the interest of solving national security problems


  • Open Access

    The development of a method for visualizing the states of the national security system

    by Nina Kuchuk, Andrii Shyshatskyi, Yurii Zhuravskyi, Tetiana Stasiuk, Oleksii Nalapko, Peter Sliusar, Nadiia Protas, Olena Shaposhnikova, Sergii Pronin, Oksana Havryliuk

    The scientific task, which is solved in the research, is the cognitive display of the state of the national security system with a complex hierarchical structure. As a rule, images are created individually taking into account a specific application field and interpreted by an expert (a group of experts) based on accumulated knowledge. Cognitive mapping is designed to support decision making by an expert (group of experts), monitoring and managing in real time. The object of research is the system of ensuring national security. The subject of the research is the functioning of the national security system. The research developed a method of visualization of the states of the national security system. An overview of the methods of visual graphic presentation of information about the state of multidimensional objects and systems was carried out. The novelties of the proposed method are: ‒ creation of a visual, multi-level and interconnected description of the national security system; ‒ increasing the efficiency of decision making while assessing the state of the national security system; ‒ solving the problem of falling into global and local extremes while assessing the state of the national security system; ‒ combination of graphic and numerical display of controlled state parameters of the national security system; ‒ avoiding the problem of loops while visualizing the state of the national security system in real time. The specified method should be implemented in specialized software, which is used to analyze the state of the national security system and make management decisions.