Svitlana Kashkevich
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Svitlana Kashkevich has a total of 145 co-authors. Here are the top co-authors by number of shared publications:
- Andrii Shyshatskyi
Kharkiv National Automobile and Highway University
10 shared publications Andrii Veretnov
8 shared publicationsOleksandr Lytvynenko
8 shared publicationsSerhii Neronov
7 shared publicationsGanna Plekhova
Kharkiv National Automobile and Highway University
6 shared publicationsAnna Lyashenko
5 shared publications
Latest Publications
- Open Access
- 25 June 2025
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 3 (9 (135)) , 33-39
Development of a method for detecting cyber attacks on information systems based on artificial intelligence technologies
The object of this research 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 research 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; – adapting to the type and duration of cyberattacks through multi-level adaptation of the artificial immune system; – conducting initial selection of antibodies for each swarm of the artificial immune system using an improved genetic algorithm; – training general-swarm antibodies using elite-swarm antibodies, thereby enabling deep learning; – 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 %
- 25 June 2025
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 3 (9 (135)) , 33-39
Open AccessDevelopment of a method for detecting cyber attacks on information systems based on artificial intelligence technologies
The object of this research 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 research 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; – adapting to the type and duration of cyberattacks through multi-level adaptation of the artificial immune system; – conducting initial selection of antibodies for each swarm of the artificial immune system using an improved genetic algorithm; – training general-swarm antibodies using elite-swarm antibodies, thereby enabling deep learning; – 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
- 30 April 2025
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 2 (4 (134)) , 47-53
Development of a methodological approach for assessing the condition of complex organizational and technical systems
In this study, the object of research is organizational and technical systems. The primary issue addressed is the enhancement of operational efficiency in assessing the state of such systems under constraints related to data reliability, regardless of the volume of incoming data acquired from information sources. The subject of the research is the process of evaluating the condition of organizational and technical systems. The study presents the development of a methodological approach for assessing the condition of complex organizational and technical systems. The originality of the proposed approach lies in the implementation of advanced auxiliary procedures that enable the following: – deployment of a search population of hippopotamus agents across the search plane, accounting for uncertainty in the information acquired through technical means about the organizational and technical system, by employing appropriate corrective coefficients. This enables a reduction in the time required for initial configuration of the subsystem responsible for processing heterogeneous data from extraction sources; – additional consideration of the velocity of each agent within the hippopotamus swarm, allowing the prioritization of search tasks by each individual agent within the corresponding search space (across elements and components of the organizational and technical system); – verification of the algorithm’s convergence to local and global optima; – replacement of ineffective search agents by refreshing the population of hippopotamus agents; – implementation of deep learning mechanisms for the knowledge bases of the hippopotamus agent swarm; – estimation of the required computational resources in cases where the available computational capacity is insufficient for performing the necessary calculations. An illustrative example demonstrated a 13–16 % increase in decision-making efficiency due to the integration of additional procedures, while ensuring a decision reliability level of 0.9
- 30 April 2025
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 2 (4 (134)) , 47-53
Open AccessDevelopment of a methodological approach for assessing the condition of complex organizational and technical systems
In this study, the object of research is organizational and technical systems. The primary issue addressed is the enhancement of operational efficiency in assessing the state of such systems under constraints related to data reliability, regardless of the volume of incoming data acquired from information sources. The subject of the research is the process of evaluating the condition of organizational and technical systems. The study presents the development of a methodological approach for assessing the condition of complex organizational and technical systems. The originality of the proposed approach lies in the implementation of advanced auxiliary procedures that enable the following: – deployment of a search population of hippopotamus agents across the search plane, accounting for uncertainty in the information acquired through technical means about the organizational and technical system, by employing appropriate corrective coefficients. This enables a reduction in the time required for initial configuration of the subsystem responsible for processing heterogeneous data from extraction sources; – additional consideration of the velocity of each agent within the hippopotamus swarm, allowing the prioritization of search tasks by each individual agent within the corresponding search space (across elements and components of the organizational and technical system); – verification of the algorithm’s convergence to local and global optima; – replacement of ineffective search agents by refreshing the population of hippopotamus agents; – implementation of deep learning mechanisms for the knowledge bases of the hippopotamus agent swarm; – estimation of the required computational resources in cases where the available computational capacity is insufficient for performing the necessary calculations. An illustrative example demonstrated a 13–16 % increase in decision-making efficiency due to the integration of additional procedures, while ensuring a decision reliability level of 0.9
- Open Access
- 31 March 2025
- Published by Private Company Technology Center
- p. 60-66
Modeling of transport logistics during the period of special legal regime
The problems of relocation of high-tech enterprises, cargo and people under martial law, as well as optimization of supply of components after changing the location of production, are studied. Logistics planning models are proposed that take into account the risks caused by military actions, disruptions of transport chains and resource shortages. The key stages of relocation are identified: selection of a safe location, adaptation of logistics infrastructure, establishment of new supply channels. Factors affecting the supply of components are analyzed, in particular the availability of transport corridors, ensuring the stability of supplies and minimizing transportation costs. It is determined that effective modeling of relocation processes and supply logistics is an important factor for maintaining the competitiveness and stability of high-tech enterprises during crisis situations.
- 31 March 2025
- Published by Private Company Technology Center
- p. 60-66
Open AccessModeling of transport logistics during the period of special legal regime
The problems of relocation of high-tech enterprises, cargo and people under martial law, as well as optimization of supply of components after changing the location of production, are studied. Logistics planning models are proposed that take into account the risks caused by military actions, disruptions of transport chains and resource shortages. The key stages of relocation are identified: selection of a safe location, adaptation of logistics infrastructure, establishment of new supply channels. Factors affecting the supply of components are analyzed, in particular the availability of transport corridors, ensuring the stability of supplies and minimizing transportation costs. It is determined that effective modeling of relocation processes and supply logistics is an important factor for maintaining the competitiveness and stability of high-tech enterprises during crisis situations.
- Open Access
- 24 February 2025
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 1 (4 (133)) , 64-71
Development of heterogeneous data processing method in organizational and technical systems
The object of the study is heterogeneous data in organizational-technical systems. The subject of the study is the process of heterogeneous data processing. The problem of this study is enhancing the efficiency of heterogeneous data processing in organizational-technical systems while ensuring a predefined level of reliability, regardless of the volume of incoming data. A method for heterogeneous data processing in organizational-technical systems has been developed. The originality of the method lies in the use of additional improved procedures, which allow: – achieving the placement of the initial population of agents in the combined algorithm swarm and their initial position in the search space, considering the uncertainty level of input data circulating in the organizational-technical system. This is achieved using correction coefficients; – accounting for the initial velocity of each agent in the combined algorithm swarm, enabling search prioritization in the corresponding search space (across elements and components of the organizational-technical system); – determining the feasibility of decisions in heterogeneous data processing, considering external factors, which reduces the solution search time; – ability to calculate the required computational resources, determining the additional resources needed in case existing computational capacity is insufficient. A practical implementation of the proposed method was tested on heterogeneous data processing in an operational military task force, demonstrating: a 14–20 % increase in decision-making efficiency due to the integration of additional procedures; a decision reliability level maintained at 0.9
- 24 February 2025
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 1 (4 (133)) , 64-71
Open AccessDevelopment of heterogeneous data processing method in organizational and technical systems
The object of the study is heterogeneous data in organizational-technical systems. The subject of the study is the process of heterogeneous data processing. The problem of this study is enhancing the efficiency of heterogeneous data processing in organizational-technical systems while ensuring a predefined level of reliability, regardless of the volume of incoming data. A method for heterogeneous data processing in organizational-technical systems has been developed. The originality of the method lies in the use of additional improved procedures, which allow: – achieving the placement of the initial population of agents in the combined algorithm swarm and their initial position in the search space, considering the uncertainty level of input data circulating in the organizational-technical system. This is achieved using correction coefficients; – accounting for the initial velocity of each agent in the combined algorithm swarm, enabling search prioritization in the corresponding search space (across elements and components of the organizational-technical system); – determining the feasibility of decisions in heterogeneous data processing, considering external factors, which reduces the solution search time; – ability to calculate the required computational resources, determining the additional resources needed in case existing computational capacity is insufficient. A practical implementation of the proposed method was tested on heterogeneous data processing in an operational military task force, demonstrating: a 14–20 % increase in decision-making efficiency due to the integration of additional procedures; a decision reliability level maintained at 0.9
- Open Access
- 6 February 2025
- Published by Private Company Technology Center
- p. 124-159
Intellectual methods for evaluating the state of UAV channels
In this section of the research, intellectual methods for assessing the state of unmanned aerial vehicle (UAV) channels are proposed. During the study, the authors: 1. Developed an intellectual method for assessing the state of UAV channels based on the application of fuzzy set theory and artificial neural networks, which, while being sufficiently simple, allows for obtaining highly accurate solutions. The distinctive features of the proposed method include:– simultaneous assessment of the UAV channel state based on multiple evaluation indicators (impulse response, frequency response, and bit error rate);– real-time continuous assessment of several channel state characteristics;– continuous assessment of multiple channel state characteristics in both the downlink and uplink channels;– obtaining channel state assessments for each indicator on separate layers of the neural network through the construction of membership functions;– following the assessment of individual channel characteristics by separate neural network layers, a generalized channel state assessment is formed at their output. 2. Proposed a methodology for identifying the state of UAV control and data transmission channels.The novelty of the proposed methodology lies in:– considering a corrective coefficient during calculations to account for the degree of uncertainty regarding the state of UAV channels;– adding a corrective coefficient to address data noise resulting from distortions in information about UAV channel states;– reducing computational costs when assessing the state of UAV channels;– enabling calculations with input data of various natures and units of measurement.
- 6 February 2025
- Published by Private Company Technology Center
- p. 124-159
Open AccessIntellectual methods for evaluating the state of UAV channels
In this section of the research, intellectual methods for assessing the state of unmanned aerial vehicle (UAV) channels are proposed. During the study, the authors: 1. Developed an intellectual method for assessing the state of UAV channels based on the application of fuzzy set theory and artificial neural networks, which, while being sufficiently simple, allows for obtaining highly accurate solutions. The distinctive features of the proposed method include:– simultaneous assessment of the UAV channel state based on multiple evaluation indicators (impulse response, frequency response, and bit error rate);– real-time continuous assessment of several channel state characteristics;– continuous assessment of multiple channel state characteristics in both the downlink and uplink channels;– obtaining channel state assessments for each indicator on separate layers of the neural network through the construction of membership functions;– following the assessment of individual channel characteristics by separate neural network layers, a generalized channel state assessment is formed at their output. 2. Proposed a methodology for identifying the state of UAV control and data transmission channels.The novelty of the proposed methodology lies in:– considering a corrective coefficient during calculations to account for the degree of uncertainty regarding the state of UAV channels;– adding a corrective coefficient to address data noise resulting from distortions in information about UAV channel states;– reducing computational costs when assessing the state of UAV channels;– enabling calculations with input data of various natures and units of measurement.
- Open Access
- 6 February 2025
- Published by Private Company Technology Center
- p. 33-61
Methods of processing various data in intelligent systems for management of the network and server architecture of the internet of combat things
In this chapter of the research, a method of processing various types of data in intelligent management systems of the network and server architecture of the internet of military equipment is proposed. The basis of this research is the theory of artificial intelligence, namely evolving artificial neural networks, basic genetic algorithm procedures, neuro-fuzzy expert systems, as well as bio-inspired algorithms. In the course of the research, the authors proposed:– a complex model of processing various types of data in intelligent decision-making support systems;– a method of processing various types of data in intelligent management systems of network and server architecture;– a method of increasing the efficiency of processing various types of data in intelligent management systems of network and server architecture. The use of methods of processing various types of data in intelligent management systems of the network and server architecture of the internet of military equipment:– to reduce the probability of premature convergence of the metaheuristic algorithm while processing various types of data in intelligent management systems of the network and server architecture of the internet of military equipment;– to maintain a balance between the speed of convergence of the metaheuristic algorithm and diversification while processing various types of data in the intelligent control systems of the network and server architecture of the internet of military equipment;– to take into account the type of uncertainty and noise of the data of the metaheuristic algorithm while processing various types of data in the intelligent control systems of the network and server architecture of the internet of military equipment;– to take into account the available computing resources of the system while processing various types of data in the intelligent management systems of the network and server architecture of the internet of military equipment;– to take into account the priority of search by swarm agents of the meta-heuristic algorithm while processing various types of data in intelligent management systems of the network and server architecture of the internet of military equipment;– to conduct an initial display of flock individuals taking into account the type of uncertainty;– to conduct accurate training of metaheuristic algorithms;– to conduct a local and global search taking into account the degree of data noise while processing various types of data in intelligent management systems of the network and server architecture of the internet of military equipment.
- 6 February 2025
- Published by Private Company Technology Center
- p. 33-61
Open AccessMethods of processing various data in intelligent systems for management of the network and server architecture of the internet of combat things
In this chapter of the research, a method of processing various types of data in intelligent management systems of the network and server architecture of the internet of military equipment is proposed. The basis of this research is the theory of artificial intelligence, namely evolving artificial neural networks, basic genetic algorithm procedures, neuro-fuzzy expert systems, as well as bio-inspired algorithms. In the course of the research, the authors proposed:– a complex model of processing various types of data in intelligent decision-making support systems;– a method of processing various types of data in intelligent management systems of network and server architecture;– a method of increasing the efficiency of processing various types of data in intelligent management systems of network and server architecture. The use of methods of processing various types of data in intelligent management systems of the network and server architecture of the internet of military equipment:– to reduce the probability of premature convergence of the metaheuristic algorithm while processing various types of data in intelligent management systems of the network and server architecture of the internet of military equipment;– to maintain a balance between the speed of convergence of the metaheuristic algorithm and diversification while processing various types of data in the intelligent control systems of the network and server architecture of the internet of military equipment;– to take into account the type of uncertainty and noise of the data of the metaheuristic algorithm while processing various types of data in the intelligent control systems of the network and server architecture of the internet of military equipment;– to take into account the available computing resources of the system while processing various types of data in the intelligent management systems of the network and server architecture of the internet of military equipment;– to take into account the priority of search by swarm agents of the meta-heuristic algorithm while processing various types of data in intelligent management systems of the network and server architecture of the internet of military equipment;– to conduct an initial display of flock individuals taking into account the type of uncertainty;– to conduct accurate training of metaheuristic algorithms;– to conduct a local and global search taking into account the degree of data noise while processing various types of data in intelligent management systems of the network and server architecture of the internet of military equipment.
- Open Access
- 6 February 2025
- Published by Private Company Technology Center
- p. 3-32
Scientific method apparatus for intellectual assessment of the state of complex systems
In this section of the research, a scientific and method apparatus for intelligent assessment of the state of complex systems is proposed. The basis of this research is the theory of artificial intelligence, namely evolving artificial neural networks, basic genetic algorithm procedures, neuro-fuzzy expert systems and bio-inspired algorithms. In the course of the research, the authors proposed:– the method approach to assessing the state of hierarchical systems using a metaheuristic algorithm;– the method of analysis and forecasting of the state of multidimensional objects using a metaheuristic algorithm;– the method of increasing the reliability of the assessment of the object state. The use of the proposed scientific and method apparatus will allow:– to reduce the probability of premature convergence of the metaheuristic algorithm;– to maintain a balance between the speed of convergence of the metaheuristic algorithm and diversification;– to take into account the type of uncertainty and noisy data of the metaheuristic algorithm;– to take into account the available computing resources of the state analysis system of the analysis object;– to take into account the priority of search by swarm agents of the metaheuristic algorithm;– to carry out the initial display of flock individuals taking into account the uncertainty type;– to conduct accurate training of individuals of metaheuristic algorithms;– to conduct a local and global search taking into account the degree of noise of the data on the state of the analysis object;– to apply as a universal tool for solving the task of analyzing the state of analysis objects due to the hierarchical description of analysis objects;– to check the reliability of the obtained results;– to increase the reliability of the assessment of the objects state of analysis due to the construction of object and relational models of their state with different degrees of hierarchy;– to avoid the local extremum problem.
- 6 February 2025
- Published by Private Company Technology Center
- p. 3-32
Open AccessScientific method apparatus for intellectual assessment of the state of complex systems
In this section of the research, a scientific and method apparatus for intelligent assessment of the state of complex systems is proposed. The basis of this research is the theory of artificial intelligence, namely evolving artificial neural networks, basic genetic algorithm procedures, neuro-fuzzy expert systems and bio-inspired algorithms. In the course of the research, the authors proposed:– the method approach to assessing the state of hierarchical systems using a metaheuristic algorithm;– the method of analysis and forecasting of the state of multidimensional objects using a metaheuristic algorithm;– the method of increasing the reliability of the assessment of the object state. The use of the proposed scientific and method apparatus will allow:– to reduce the probability of premature convergence of the metaheuristic algorithm;– to maintain a balance between the speed of convergence of the metaheuristic algorithm and diversification;– to take into account the type of uncertainty and noisy data of the metaheuristic algorithm;– to take into account the available computing resources of the state analysis system of the analysis object;– to take into account the priority of search by swarm agents of the metaheuristic algorithm;– to carry out the initial display of flock individuals taking into account the uncertainty type;– to conduct accurate training of individuals of metaheuristic algorithms;– to conduct a local and global search taking into account the degree of noise of the data on the state of the analysis object;– to apply as a universal tool for solving the task of analyzing the state of analysis objects due to the hierarchical description of analysis objects;– to check the reliability of the obtained results;– to increase the reliability of the assessment of the objects state of analysis due to the construction of object and relational models of their state with different degrees of hierarchy;– to avoid the local extremum problem.
- Open Access
- 6 February 2025
- Published by Private Company Technology Center
- p. 95-123
Scientific and methodological apparatus for processing diverse data in automated control systems
This section of the study proposes the conceptual foundations for the use of artificial intelligence in intelligent decision support systems. In the course of the research, the authors:– justified the feasibility of using artificial intelligence theory for processing heterogeneous data in automated control systems;– developed a methodology for data distribution in automated control systems;– designed a model for evaluating the process of heterogeneous data processing in automated troop control systems using expert information;– improved the methodology for configuring an information system to evaluate the process of heterogeneous data processing in automated control systems under conditions of uncertainty. The analysis conducted in the study established that the application of fuzzy graphs and the mathematical apparatus of fuzzy logic in decision support tasks for data distribution and the evaluation of heterogeneous data processing under various conditions, including uncertainty, enables the distribution of data among elements of automated control systems based on the importance of the elements and the number of features in real-time. The methodology for rational data distribution based on the importance of automated control system elements and the number of features in such systems under conditions of uncertainty has been improved. This methodology differs from existing ones by combining the mathematical apparatus of information theory, fuzzy logic, and expert evaluation, enabling the formalization of features in a unified parameter space and the intellectualization of information processing processes. A quantitative assessment of the proposed methodology’s efficiency was conducted. The results of this assessment demonstrated that data distribution among the elements of automated control systems based on importance and the number of features using the proposed methodology improves the timeliness of data processing and decision-making regarding the state of the heterogeneous data processing process by 15–17 %. An enhanced methodology for configuring the information system for evaluating the heterogeneous data processing process in automated control systems under conditions of uncertainty, utilizing a genetic algorithm, was developed. This methodology addresses limitations of other methods in varying specific features while holding other indicators constant, thus improving the efficiency of the developed information system for evaluating heterogeneous data processing in automated control systems. The scientific outcome is the improvement of the genetic algorithm for differentiated tuning of the fuzzy knowledge base of the information system for evaluating heterogeneous data processing in automated control systems based on posterior data. A quantitative assessment of the improved methodology’s effectiveness was performed. The results indicated that the proposed methodology enhances the timeliness of configuring the information system for processing heterogeneous data in automated control systems under conditions of uncertainty.
- 6 February 2025
- Published by Private Company Technology Center
- p. 95-123
Open AccessScientific and methodological apparatus for processing diverse data in automated control systems
This section of the study proposes the conceptual foundations for the use of artificial intelligence in intelligent decision support systems. In the course of the research, the authors:– justified the feasibility of using artificial intelligence theory for processing heterogeneous data in automated control systems;– developed a methodology for data distribution in automated control systems;– designed a model for evaluating the process of heterogeneous data processing in automated troop control systems using expert information;– improved the methodology for configuring an information system to evaluate the process of heterogeneous data processing in automated control systems under conditions of uncertainty. The analysis conducted in the study established that the application of fuzzy graphs and the mathematical apparatus of fuzzy logic in decision support tasks for data distribution and the evaluation of heterogeneous data processing under various conditions, including uncertainty, enables the distribution of data among elements of automated control systems based on the importance of the elements and the number of features in real-time. The methodology for rational data distribution based on the importance of automated control system elements and the number of features in such systems under conditions of uncertainty has been improved. This methodology differs from existing ones by combining the mathematical apparatus of information theory, fuzzy logic, and expert evaluation, enabling the formalization of features in a unified parameter space and the intellectualization of information processing processes. A quantitative assessment of the proposed methodology’s efficiency was conducted. The results of this assessment demonstrated that data distribution among the elements of automated control systems based on importance and the number of features using the proposed methodology improves the timeliness of data processing and decision-making regarding the state of the heterogeneous data processing process by 15–17 %. An enhanced methodology for configuring the information system for evaluating the heterogeneous data processing process in automated control systems under conditions of uncertainty, utilizing a genetic algorithm, was developed. This methodology addresses limitations of other methods in varying specific features while holding other indicators constant, thus improving the efficiency of the developed information system for evaluating heterogeneous data processing in automated control systems. The scientific outcome is the improvement of the genetic algorithm for differentiated tuning of the fuzzy knowledge base of the information system for evaluating heterogeneous data processing in automated control systems based on posterior data. A quantitative assessment of the improved methodology’s effectiveness was performed. The results indicated that the proposed methodology enhances the timeliness of configuring the information system for processing heterogeneous data in automated control systems under conditions of uncertainty.
- Open Access
- 6 February 2025
- Published by Private Company Technology Center
- p. 160-189
Intelligent methods for evaluating the state of hierarchical systems
This section of the study proposes intelligent methods for assessing the state of hierarchical systems. During the research, the authors:– conducted an analysis of knowledge representation models, substantiating the advantages of using production knowledge representation in expert systems. The study outlines key concepts of fuzzy expert systems and formulates a formal task for accelerating decision-making in the rule base of a fuzzy expert system;– developed a methodology for assessment and prediction using fuzzy cognitive maps. The novelty of the proposed methodology lies in:– considering a corrective coefficient for the degree of uncertainty regarding the state of the object;– adding a corrective coefficient for data noise resulting from distortions in object state information;– reducing computational costs when evaluating object states;– creating a multilevel and interconnected description of hierarchical objects;– adjusting the object description due to changes in its current state using a genetic algorithm;– enabling calculations with input data of different natures and measurement units. The research includes the development of a visualization method for hierarchical system states. The novelty of this method lies in:– creating a visual, multilevel, and interconnected description of the hierarchical system;– enhancing decision-making efficiency in assessing the hierarchical system’s state;– addressing the issue of global and local extrema when evaluating the state of hierarchical systems;– combining graphical and numerical representations of the monitored parameters of the hierarchical system’s state;– avoiding loop formation during real-time visualization of hierarchical system states. The study also develops a method for evaluating complex hierarchical systems based on an improved particle swarm optimization (PSO). This evaluation method combines PSO with coordinate averaging and its modification by employing multiple particle swarms and integrating the Hooke-Jeeves procedure and appropriate corrective coefficients. The novelty of this method lies in:– creating a multilevel and interconnected description of real-time complex hierarchical systems;– enhancing decision-making efficiency for real-time hierarchical systems assessment;– resolving global and local extrema issues during real-time hierarchical system state evaluation;– enabling directed searches by multiple swarm particles in a specific direction;– considering the degree of uncertainty;– allowing for repeated analysis of complex real-time hierarchical systems.
- 6 February 2025
- Published by Private Company Technology Center
- p. 160-189
Open AccessIntelligent methods for evaluating the state of hierarchical systems
This section of the study proposes intelligent methods for assessing the state of hierarchical systems. During the research, the authors:– conducted an analysis of knowledge representation models, substantiating the advantages of using production knowledge representation in expert systems. The study outlines key concepts of fuzzy expert systems and formulates a formal task for accelerating decision-making in the rule base of a fuzzy expert system;– developed a methodology for assessment and prediction using fuzzy cognitive maps. The novelty of the proposed methodology lies in:– considering a corrective coefficient for the degree of uncertainty regarding the state of the object;– adding a corrective coefficient for data noise resulting from distortions in object state information;– reducing computational costs when evaluating object states;– creating a multilevel and interconnected description of hierarchical objects;– adjusting the object description due to changes in its current state using a genetic algorithm;– enabling calculations with input data of different natures and measurement units. The research includes the development of a visualization method for hierarchical system states. The novelty of this method lies in:– creating a visual, multilevel, and interconnected description of the hierarchical system;– enhancing decision-making efficiency in assessing the hierarchical system’s state;– addressing the issue of global and local extrema when evaluating the state of hierarchical systems;– combining graphical and numerical representations of the monitored parameters of the hierarchical system’s state;– avoiding loop formation during real-time visualization of hierarchical system states. The study also develops a method for evaluating complex hierarchical systems based on an improved particle swarm optimization (PSO). This evaluation method combines PSO with coordinate averaging and its modification by employing multiple particle swarms and integrating the Hooke-Jeeves procedure and appropriate corrective coefficients. The novelty of this method lies in:– creating a multilevel and interconnected description of real-time complex hierarchical systems;– enhancing decision-making efficiency for real-time hierarchical systems assessment;– resolving global and local extrema issues during real-time hierarchical system state evaluation;– enabling directed searches by multiple swarm particles in a specific direction;– considering the degree of uncertainty;– allowing for repeated analysis of complex real-time hierarchical systems.
- Open Access
- 30 December 2024
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 6 (9 (132)) , 108-116
Development of a method for managing a group of unmanned aerial vehicles using a population algorithm
The object of the study is a group of unmanned aerial vehicles (UAVs). The subject of the study is the decision-making process in management tasks using: – an improved brown bear algorithm (BBA), which achieves the determination of the optimal UAV movement route based on the given optimization criterion (the probability of completing the flight task), described by complex multimodal functions; – evolving artificial neural networks for deep learning of the multi-agent system knowledge base, by training both the parameters and the architecture of artificial neural networks. The originality of the method lies in using additional improved procedures that allow: – the initial BBA population and their initial position on the search plane are determined considering the degree of uncertainty in the data on the UAV group movement route; – the initial speed of each BBA is considered, enabling the prioritization of searches in the respective search plane (height, latitude, and longitude); – the suitability of the UAV group's flight route for performing the flight task is determined, considering a set of external factors, thereby reducing the decision search time; – the universality of BBA food search strategies allows classifying a set of conditions and factors affecting the completion of the flight task. This aids in identifying the most feasible movement options for the UAV group based on the defined optimization criterion for movement route. Modeling the operation of the proposed method has shown that the increase in decision-making efficiency reaches 15–18 %. The enhancement in the method's efficiency is achieved through additional procedures and ensuring the reliability of the decisions at a level of 0.9
- 30 December 2024
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 6 (9 (132)) , 108-116
Open AccessDevelopment of a method for managing a group of unmanned aerial vehicles using a population algorithm
The object of the study is a group of unmanned aerial vehicles (UAVs). The subject of the study is the decision-making process in management tasks using: – an improved brown bear algorithm (BBA), which achieves the determination of the optimal UAV movement route based on the given optimization criterion (the probability of completing the flight task), described by complex multimodal functions; – evolving artificial neural networks for deep learning of the multi-agent system knowledge base, by training both the parameters and the architecture of artificial neural networks. The originality of the method lies in using additional improved procedures that allow: – the initial BBA population and their initial position on the search plane are determined considering the degree of uncertainty in the data on the UAV group movement route; – the initial speed of each BBA is considered, enabling the prioritization of searches in the respective search plane (height, latitude, and longitude); – the suitability of the UAV group's flight route for performing the flight task is determined, considering a set of external factors, thereby reducing the decision search time; – the universality of BBA food search strategies allows classifying a set of conditions and factors affecting the completion of the flight task. This aids in identifying the most feasible movement options for the UAV group based on the defined optimization criterion for movement route. Modeling the operation of the proposed method has shown that the increase in decision-making efficiency reaches 15–18 %. The enhancement in the method's efficiency is achieved through additional procedures and ensuring the reliability of the decisions at a level of 0.9