Kostiantyn Buravchenko
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kostiantyn Buravchenko has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Oleksii Smirnov
Central Ukrainian National Technical University
11 shared publications - Nataliia Yakymenko
Central Ukrainian National Technical University
7 shared publications - Serhii Smirnov
Central Ukrainian National Technical University
7 shared publications - Tetiana Smirnova
Central Ukrainian National Technical University
6 shared publications Олексій Смірнов
Центральноукраїнський національний технічний університет
5 shared publications- Oksana Konoplitska-Slobodeniuk
Central Ukrainian National Technical University
4 shared publications
Latest Publications
- Open Access
- 24 September 2026
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 2 (34) , 677-686
LIMITATIONS OF RESOURCES OF MOBILE AND EDGE PLATFORMS WHEN DEVELOPING SOFTWARE FOR IMPLEMENTATION AND OPTIMIZATION OF MACHINE LEARNING MODELS
This paper analyzes modern approaches to the implementation and optimization of machine learning models for mobile and edge platforms. The relevance of this issue is due to the rapid development of mobile computing, Internet of Things systems, peripheral computing, and the need to perform intelligent data processing directly on devices with limited resources. It is shown that modern mobile and edge devices are gradually transforming into full-fledged computing systems that are capable of performing complex machine learning and artificial intelligence tasks without the use of remote servers. At the same time, the use of models directly on mobile devices is accompanied by a number of significant limitations associated with limited computing power, a small amount of RAM, energy constraints, and the peculiarities of the thermal mode of operation. It is separately established that the mobile environment is characterized by high dynamics of available resources. Available computing power, battery charge level, device temperature, activity of background processes, and available memory can change during system operation. This creates additional difficulties for the execution of machine learning models and significantly complicates the use of static optimization methods.
- 24 September 2026
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 2 (34) , 677-686
Open AccessLIMITATIONS OF RESOURCES OF MOBILE AND EDGE PLATFORMS WHEN DEVELOPING SOFTWARE FOR IMPLEMENTATION AND OPTIMIZATION OF MACHINE LEARNING MODELS
This paper analyzes modern approaches to the implementation and optimization of machine learning models for mobile and edge platforms. The relevance of this issue is due to the rapid development of mobile computing, Internet of Things systems, peripheral computing, and the need to perform intelligent data processing directly on devices with limited resources. It is shown that modern mobile and edge devices are gradually transforming into full-fledged computing systems that are capable of performing complex machine learning and artificial intelligence tasks without the use of remote servers. At the same time, the use of models directly on mobile devices is accompanied by a number of significant limitations associated with limited computing power, a small amount of RAM, energy constraints, and the peculiarities of the thermal mode of operation. It is separately established that the mobile environment is characterized by high dynamics of available resources. Available computing power, battery charge level, device temperature, activity of background processes, and available memory can change during system operation. This creates additional difficulties for the execution of machine learning models and significantly complicates the use of static optimization methods.
- Open Access
- 26 March 2026
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- p. 573
OPTIMIZING FACIAL RECOGNITION WITH THE CUDA ACCELERATED DLIB LIBRARY
This work presents a comprehensive study of the effectiveness of computer vision methods for the task of detecting faces in images and in video streams. The main attention is paid to the comparative analysis of two algorithms of the dlib library: the classical method based on histograms of oriented gradients (HOG) and the modern method based on convolutional neural networks (CNN). The problem of high computational complexity of neural network methods is considered and a solution is proposed through the use of NVIDIA CUDA parallel computing technology. A software algorithm for benchmarking is developed, which allows for automatic evaluation of frame processing speed (FPS), inference time and detection stability on different hardware. The experiment proved that the use of a graphics processor (GPU) allows achieving multiple acceleration (speedup) of image processing when using CNN, providing the ability to work in real time with high accuracy. The results of the study allow us to determine the optimal hardware and software configurations for building video surveillance, access control, and biometric identification systems. The conclusions obtained can be used in the design of high-load video analytics systems.
- 26 March 2026
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- p. 573
Open AccessOPTIMIZING FACIAL RECOGNITION WITH THE CUDA ACCELERATED DLIB LIBRARY
This work presents a comprehensive study of the effectiveness of computer vision methods for the task of detecting faces in images and in video streams. The main attention is paid to the comparative analysis of two algorithms of the dlib library: the classical method based on histograms of oriented gradients (HOG) and the modern method based on convolutional neural networks (CNN). The problem of high computational complexity of neural network methods is considered and a solution is proposed through the use of NVIDIA CUDA parallel computing technology. A software algorithm for benchmarking is developed, which allows for automatic evaluation of frame processing speed (FPS), inference time and detection stability on different hardware. The experiment proved that the use of a graphics processor (GPU) allows achieving multiple acceleration (speedup) of image processing when using CNN, providing the ability to work in real time with high accuracy. The results of the study allow us to determine the optimal hardware and software configurations for building video surveillance, access control, and biometric identification systems. The conclusions obtained can be used in the design of high-load video analytics systems.
- 4 December 2025
- Published by Central Ukrainian National Technical University in Central Ukrainian Scientific Bulletin. Technical Sciences
- Vol. 2 (12(43))
STRIDE-based threat Modeling of Cybersecurity Risks in Local Computer Networks
Orest Polotai, Associate Professor, PhD (Candidate of Technical Sciences), Associate Professor of the Department of Information Security Management, Lviv State University of Life Safety, Lviv, Ukraine, ORCID: https://orcid.org/0000-0003-4593-8601, e-mail: orest.polotaj@gmail.com Oleksandr Dorenskyi, Associate Professor, PhD in Information Technology (Candidate of Technical Sciences), Associate Professor of Cybersecurity and Software Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0000-0002-7625-9022, e-mail: dorenskyiop@kntu.kr.ua. Anastasiia Kovalenko, Assistant Lecturer of Cybersecurity and Software Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0009-0000-9042-8358, e-mail: stasja.artem09@gmail.com Kostiantyn Buravchenko, Associate Professor, PhD (candidate of technical sciences), Associate Professor of Cybersecurity & Software Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0000-0001-6195-7533, e-mail: buravchenkok@gmail.com The article examines the problem of ensuring LAN cybersecurity under conditions of increasing threat volume and complexity. Accordingly, the study focuses on developing a generalised adaptive method for threat modelling in LANs based on the STRIDE framework. To this end, the paper analyses current scientific sources on the application of STRIDE in the field of information security and identifies a gap between theoretical threat models and their practical implementation in the context of local networks. Based on a constructed DFD model, a structured representation of typical LAN components, external entities, network processes and data flows is formed. The STRIDE threat classification is applied to each model element, enabling the systematisation of potential risks and the development of a threat matrix for further analysis. An adaptive threat-modelling method is formulated, comprising network architecture analysis, automated generation of a threat list, selection of relevant countermeasures, modelling of a secure network architecture, and verification in a simulation environment. The effectiveness of the method is evaluated according to criteria such as completeness of threat coverage, adaptability, practical feasibility, and the degree of automation. The research findings demonstrate that the use of STRIDE in combination with DFD modelling enhances the structural consistency of cybersecurity analysis and provides a systematic approach to designing a LAN protection model.
- 4 December 2025
- Published by Central Ukrainian National Technical University in Central Ukrainian Scientific Bulletin. Technical Sciences
- Vol. 2 (12(43))
STRIDE-based threat Modeling of Cybersecurity Risks in Local Computer Networks
Orest Polotai, Associate Professor, PhD (Candidate of Technical Sciences), Associate Professor of the Department of Information Security Management, Lviv State University of Life Safety, Lviv, Ukraine, ORCID: https://orcid.org/0000-0003-4593-8601, e-mail: orest.polotaj@gmail.com Oleksandr Dorenskyi, Associate Professor, PhD in Information Technology (Candidate of Technical Sciences), Associate Professor of Cybersecurity and Software Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0000-0002-7625-9022, e-mail: dorenskyiop@kntu.kr.ua. Anastasiia Kovalenko, Assistant Lecturer of Cybersecurity and Software Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0009-0000-9042-8358, e-mail: stasja.artem09@gmail.com Kostiantyn Buravchenko, Associate Professor, PhD (candidate of technical sciences), Associate Professor of Cybersecurity & Software Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0000-0001-6195-7533, e-mail: buravchenkok@gmail.com The article examines the problem of ensuring LAN cybersecurity under conditions of increasing threat volume and complexity. Accordingly, the study focuses on developing a generalised adaptive method for threat modelling in LANs based on the STRIDE framework. To this end, the paper analyses current scientific sources on the application of STRIDE in the field of information security and identifies a gap between theoretical threat models and their practical implementation in the context of local networks. Based on a constructed DFD model, a structured representation of typical LAN components, external entities, network processes and data flows is formed. The STRIDE threat classification is applied to each model element, enabling the systematisation of potential risks and the development of a threat matrix for further analysis. An adaptive threat-modelling method is formulated, comprising network architecture analysis, automated generation of a threat list, selection of relevant countermeasures, modelling of a secure network architecture, and verification in a simulation environment. The effectiveness of the method is evaluated according to criteria such as completeness of threat coverage, adaptability, practical feasibility, and the degree of automation. The research findings demonstrate that the use of STRIDE in combination with DFD modelling enhances the structural consistency of cybersecurity analysis and provides a systematic approach to designing a LAN protection model.
- 4 December 2025
- Published by Central Ukrainian National Technical University in Central Ukrainian Scientific Bulletin. Technical Sciences
- Vol. 2 (12(43))
Cloud-based Technology for Monitoring Key Performance Indicators of Technological Processes in Critical Infrastructure
Tetiana Smirnova, Candidate of Science (Engineering), Senior Lecturer, Department of Automation of Production Processes, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine ORCID: https://orcid.org/0000-0001-6896-0612, e-mail: sm.tetyana@gmail.com Kostiantyn Buravchenko, Associate Professor, PhD (candidate of technical sciences), Associate Professor of Cybersecurity & Software Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0000-0001-6195-7533, e-mail: buravchenkok@gmail.com. Oleksandr Dobrynchuk, Junior Researcher, State University "Kyiv Aviation Institute", Kyiv, Ukraine, ORCID: https://orcid.org/0009-0002-2877-844X, e-mail: Dobrynchuk85@icloud.com. Serhii Smirnov, Associate Professor, PhD, Associate Professor of Cybersecurity & Software Academic Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0000-0002-7649-7442, e-mail: smirnov.ser.81@gmail.com. Nataliia Yakymenko, Associate Professor, PhD (Candidate of Physical and Mathematical Sciences), Associate Professor of Cybersecurity & Software Academic Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0000-0002-4498-0093, e-mail: yakimenko_n_m@ukr.net Oleksii Smirnov, Professor, Doctor of technical sciences, head of Cybersecurity & Software Academic Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0000-0001-9543-874X, e-mail: dr.smirnovoa@gmail.com. In this work, a cloud technology was developed for monitoring key performance indicators of critical infrastructure technological processes in real time in order to detect deviations in technological processes, as well as to prevent attacks (failures) by analyzing anomalous equipment behavior, changes in load modes, resource consumption, etc. The tuple model of key performance indicators was further developed, which allows systematizing monitoring parameters in information and communication systems of critical infrastructure objects, formalizing automatic data processing, supporting integration with analytical cloud platforms, as well as identifying deviations (anomalies), cyber incidents, degradation, excessive load or sabotage and, as a result, preparing aggregated key performance indicators for daily monitoring by operators and IT services. A model of the technological process of electric arc processing in UAV engineering is proposed, which in the conditions of the current stage of the Russian-Ukrainian war is part of the critical infrastructure in the economy and defense- industrial production sector. This is due to the fact that UAVs now play a crucial role on the battlefield. A scheme for monitoring key performance indicators for the electric arc processing technological process has been developed. For this, the use of cloud technologies is proposed, a general scheme of the electric arc processing technological process in UAV engineering is given, with their use. An example of a model infrastructure based on the Azure cloud platform has been implemented. The data model is presented in JSON format (which is effective for API, MQTT broker or Kafka). Verification of the model on empirical data confirmed its compliance with the requirements, resistance to changing conditions and great significance for monitoring technological processes in critical infrastructure. In the context of digitalization and countering cyber risks, the model is the basis for creating a digital twin of the production system. Thus, reliability, predictability and security are ensured. The paper proposes integration with artificial intelligence/machine learning (AI/ML) algorithms, such as LSTM, which allows for real-time advanced analytics, adaptive process control, and automated decision- making. In the future, the LSTM algorithm can be used to build a model for predicting the parameters of key performance indicators in an electric arc processing system, and other AI/ML and data mining algorithms that can process large volumes of time series and take into account complex nonlinear dependencies between technological parameters can also be used.
- 4 December 2025
- Published by Central Ukrainian National Technical University in Central Ukrainian Scientific Bulletin. Technical Sciences
- Vol. 2 (12(43))
Cloud-based Technology for Monitoring Key Performance Indicators of Technological Processes in Critical Infrastructure
Tetiana Smirnova, Candidate of Science (Engineering), Senior Lecturer, Department of Automation of Production Processes, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine ORCID: https://orcid.org/0000-0001-6896-0612, e-mail: sm.tetyana@gmail.com Kostiantyn Buravchenko, Associate Professor, PhD (candidate of technical sciences), Associate Professor of Cybersecurity & Software Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0000-0001-6195-7533, e-mail: buravchenkok@gmail.com. Oleksandr Dobrynchuk, Junior Researcher, State University "Kyiv Aviation Institute", Kyiv, Ukraine, ORCID: https://orcid.org/0009-0002-2877-844X, e-mail: Dobrynchuk85@icloud.com. Serhii Smirnov, Associate Professor, PhD, Associate Professor of Cybersecurity & Software Academic Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0000-0002-7649-7442, e-mail: smirnov.ser.81@gmail.com. Nataliia Yakymenko, Associate Professor, PhD (Candidate of Physical and Mathematical Sciences), Associate Professor of Cybersecurity & Software Academic Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0000-0002-4498-0093, e-mail: yakimenko_n_m@ukr.net Oleksii Smirnov, Professor, Doctor of technical sciences, head of Cybersecurity & Software Academic Department, Central Ukrainian National Technical University, Kropyvnytskyi, Ukraine, ORCID: https://orcid.org/0000-0001-9543-874X, e-mail: dr.smirnovoa@gmail.com. In this work, a cloud technology was developed for monitoring key performance indicators of critical infrastructure technological processes in real time in order to detect deviations in technological processes, as well as to prevent attacks (failures) by analyzing anomalous equipment behavior, changes in load modes, resource consumption, etc. The tuple model of key performance indicators was further developed, which allows systematizing monitoring parameters in information and communication systems of critical infrastructure objects, formalizing automatic data processing, supporting integration with analytical cloud platforms, as well as identifying deviations (anomalies), cyber incidents, degradation, excessive load or sabotage and, as a result, preparing aggregated key performance indicators for daily monitoring by operators and IT services. A model of the technological process of electric arc processing in UAV engineering is proposed, which in the conditions of the current stage of the Russian-Ukrainian war is part of the critical infrastructure in the economy and defense- industrial production sector. This is due to the fact that UAVs now play a crucial role on the battlefield. A scheme for monitoring key performance indicators for the electric arc processing technological process has been developed. For this, the use of cloud technologies is proposed, a general scheme of the electric arc processing technological process in UAV engineering is given, with their use. An example of a model infrastructure based on the Azure cloud platform has been implemented. The data model is presented in JSON format (which is effective for API, MQTT broker or Kafka). Verification of the model on empirical data confirmed its compliance with the requirements, resistance to changing conditions and great significance for monitoring technological processes in critical infrastructure. In the context of digitalization and countering cyber risks, the model is the basis for creating a digital twin of the production system. Thus, reliability, predictability and security are ensured. The paper proposes integration with artificial intelligence/machine learning (AI/ML) algorithms, such as LSTM, which allows for real-time advanced analytics, adaptive process control, and automated decision- making. In the future, the LSTM algorithm can be used to build a model for predicting the parameters of key performance indicators in an electric arc processing system, and other AI/ML and data mining algorithms that can process large volumes of time series and take into account complex nonlinear dependencies between technological parameters can also be used.
- Open Access
- 26 September 2025
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 1 (29) , 704-716
RESEARCH ON CYBERSECURITY TECHNOLOGIES FOR BANKING SYSTEMS USING ARTIFICIAL INTELLIGENCE
The article explores the application of modern artificial intelligence (AI) technologies as a tool for ensuring cybersecurity in banking systems. Amid the growing number of sophisticated cyberattacks, traditional protection methods are no longer sufficient to provide an adequate level of security, making the implementation of intelligent systems capable of automatically analyzing large volumes of data and promptly responding to threats highly relevant. The study examines key approaches to integrating AI into the processes of detecting anomalies and cybercrimes in the banking sector. It analyzes core AI technologies used for real-time fraud detection, behavioral biometrics, countering phishing attacks, and automating compliance and audit processes. Based on practical case studies, the high efficiency of AI in enhancing threat detection accuracy, reducing response times, and minimizing false positives is demonstrated. Particular attention is given to the adaptability and self-learning capabilities of intelligent security systems in a dynamic threat environment. The advantages of integrating AI into the banking security infrastructure are highlighted, alongside the main challenges associated with implementing such solutions. The research results confirm the promising potential of AI as an effective cybersecurity tool in banking systems.
- 26 September 2025
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 1 (29) , 704-716
Open AccessRESEARCH ON CYBERSECURITY TECHNOLOGIES FOR BANKING SYSTEMS USING ARTIFICIAL INTELLIGENCE
The article explores the application of modern artificial intelligence (AI) technologies as a tool for ensuring cybersecurity in banking systems. Amid the growing number of sophisticated cyberattacks, traditional protection methods are no longer sufficient to provide an adequate level of security, making the implementation of intelligent systems capable of automatically analyzing large volumes of data and promptly responding to threats highly relevant. The study examines key approaches to integrating AI into the processes of detecting anomalies and cybercrimes in the banking sector. It analyzes core AI technologies used for real-time fraud detection, behavioral biometrics, countering phishing attacks, and automating compliance and audit processes. Based on practical case studies, the high efficiency of AI in enhancing threat detection accuracy, reducing response times, and minimizing false positives is demonstrated. Particular attention is given to the adaptability and self-learning capabilities of intelligent security systems in a dynamic threat environment. The advantages of integrating AI into the banking security infrastructure are highlighted, alongside the main challenges associated with implementing such solutions. The research results confirm the promising potential of AI as an effective cybersecurity tool in banking systems.
- 22 April 2025
- Published by State University "Kyiv Aviation Institute" in Ukrainian Scientific Journal of Information Security
- Vol. 31 (1) , 49-60
Методологія підтримки технологічних процесів у критичній інфраструктурі з забезпеченням безпеки інформації на основі хмарних технологій
This article proposes a methodology for supporting technological processes in critical infrastructure based on cloud technologies. The critical infrastructure of the state requires new approaches to ensure reliability, adaptability and information security of technological processes. At the same time, cloud technologies open up new opportunities for scalable monitoring, analysis and management of critical infrastructure in conditions of hybrid threats. Thus, the proposed methodology is aimed at forming an integrated digital platform based on the use of cloud technologies for monitoring, analysis and automated management of technological processes in conditions of high risks. The purpose of the developed methodology is to ensure continuous, safe and stable operation of technological processes of critical infrastructure facilities of the state through the implementation of cloud technologies for monitoring, analysis and automated management in conditions of high risks. The main task of this methodology is to develop a comprehensive architecture for supporting technological processes of critical infrastructure based on cloud solutions, increasing the level of technological readiness of critical infrastructure facilities for functioning in an unstable environment by implementing adaptive, scalable and secure solutions. The methodology proposed in this work is focused on functioning in conditions of increased threats, both man-made and cyber, taking into account the requirements for information security, communication reliability, redundancy of critical components and flexibility of the system architecture. This approach contributes to increasing the level of technological readiness of critical infrastructure objects to operate in an unstable environment, reduces the likelihood of failures and ensures resistance to external influences.
- 22 April 2025
- Published by State University "Kyiv Aviation Institute" in Ukrainian Scientific Journal of Information Security
- Vol. 31 (1) , 49-60
Методологія підтримки технологічних процесів у критичній інфраструктурі з забезпеченням безпеки інформації на основі хмарних технологій
This article proposes a methodology for supporting technological processes in critical infrastructure based on cloud technologies. The critical infrastructure of the state requires new approaches to ensure reliability, adaptability and information security of technological processes. At the same time, cloud technologies open up new opportunities for scalable monitoring, analysis and management of critical infrastructure in conditions of hybrid threats. Thus, the proposed methodology is aimed at forming an integrated digital platform based on the use of cloud technologies for monitoring, analysis and automated management of technological processes in conditions of high risks. The purpose of the developed methodology is to ensure continuous, safe and stable operation of technological processes of critical infrastructure facilities of the state through the implementation of cloud technologies for monitoring, analysis and automated management in conditions of high risks. The main task of this methodology is to develop a comprehensive architecture for supporting technological processes of critical infrastructure based on cloud solutions, increasing the level of technological readiness of critical infrastructure facilities for functioning in an unstable environment by implementing adaptive, scalable and secure solutions. The methodology proposed in this work is focused on functioning in conditions of increased threats, both man-made and cyber, taking into account the requirements for information security, communication reliability, redundancy of critical components and flexibility of the system architecture. This approach contributes to increasing the level of technological readiness of critical infrastructure objects to operate in an unstable environment, reduces the likelihood of failures and ensures resistance to external influences.
- Open Access
- 1 January 2025
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 3 (31) , 227-241
RESEARCH OF ARTIFICIAL INTELLIGENCE TOOLS FOR INTELLIGENT DATA ANALYSIS
The article presents a comprehensive study of modern artificial intelligence (AI) tools designed for intelligent data analysis (Data Mining), their computational capabilities, and areas of practical application. The key data analysis algorithms are examined, including machine learning methods, deep learning, clustering, classification, regression modeling, and neural networks. Special attention is given to tools such as Scikit-learn, TensorFlow, RapidMiner, Google AutoML, Power BI, and other platforms and frameworks that provide automation of data processing, analysis, and visualization of large-scale datasets. The study includes a comparative analysis of the advantages and limitations of the most widely used AI tools in terms of model accuracy, computational efficiency, ease of integration, scalability, AutoML support, and the ability to work with unstructured data. Examples of applying AI tools in industry, economics, medicine, the financial sector, and other fields of human activity are provided. The research considers current trends in the development of intelligent data analysis, taking into account the growing role of cloud platforms, automated model-building systems, multimodal AI models, and integration with corporate analytical systems. The results of the study make it possible to determine the most effective approaches and tools for solving applied Data Mining tasks, ensuring the selection of technologies according to requirements for accuracy, performance, and openness. The findings may be used in scientific research, business analytics, digital transformation of enterprises, and the design of intelligent decision-support systems.
- 1 January 2025
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 3 (31) , 227-241
Open AccessRESEARCH OF ARTIFICIAL INTELLIGENCE TOOLS FOR INTELLIGENT DATA ANALYSIS
The article presents a comprehensive study of modern artificial intelligence (AI) tools designed for intelligent data analysis (Data Mining), their computational capabilities, and areas of practical application. The key data analysis algorithms are examined, including machine learning methods, deep learning, clustering, classification, regression modeling, and neural networks. Special attention is given to tools such as Scikit-learn, TensorFlow, RapidMiner, Google AutoML, Power BI, and other platforms and frameworks that provide automation of data processing, analysis, and visualization of large-scale datasets. The study includes a comparative analysis of the advantages and limitations of the most widely used AI tools in terms of model accuracy, computational efficiency, ease of integration, scalability, AutoML support, and the ability to work with unstructured data. Examples of applying AI tools in industry, economics, medicine, the financial sector, and other fields of human activity are provided. The research considers current trends in the development of intelligent data analysis, taking into account the growing role of cloud platforms, automated model-building systems, multimodal AI models, and integration with corporate analytical systems. The results of the study make it possible to determine the most effective approaches and tools for solving applied Data Mining tasks, ensuring the selection of technologies according to requirements for accuracy, performance, and openness. The findings may be used in scientific research, business analytics, digital transformation of enterprises, and the design of intelligent decision-support systems.
- Open Access
- 1 January 2025
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 2 (30) , 413-427
LOGICAL-STRUCTURAL MODEL OF A COMPUTER-BASED PROCEDURE FOR THE SUPPORT SYSTEM FOR NPP OPERATIONAL PERSONNEL
This article develops a logical-structural model of a computer-oriented procedure for normal operation and elimination of violations for the support system for NPP operational personnel. The purpose of this study is to create a model of a computer-oriented procedure, the data structures of which will comply with technological regulations and instructions for NPP operational personnel and contain information about the relationship between states and steps of procedures. The object of the study is the process of forming computer-oriented procedures for controlling a NPP power unit. The subject of the study is logical-structural models of computer-oriented procedures and methods for identifying states and steps of procedure execution based on production rules. The following tasks were solved in this study: the data structure of the computer-oriented procedure model was developed, which complies with current regulations and instructions; a logical-structural model of a computer-oriented procedure was created, which will be used to create support systems for NPP operational personnel; A method for identifying the conditions for entering the procedure and performing its steps has been developed. The model is designed to solve the problem of maintaining relevance, early identification of the states of the power unit and its equipment, ensuring the possibility of obtaining information about the state of technological parameters with the required level of reliability and accuracy. The proposed model can be used to create support systems for operational personnel managing complex technological facilities using specific procedures and instructions.
- 1 January 2025
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 2 (30) , 413-427
Open AccessLOGICAL-STRUCTURAL MODEL OF A COMPUTER-BASED PROCEDURE FOR THE SUPPORT SYSTEM FOR NPP OPERATIONAL PERSONNEL
This article develops a logical-structural model of a computer-oriented procedure for normal operation and elimination of violations for the support system for NPP operational personnel. The purpose of this study is to create a model of a computer-oriented procedure, the data structures of which will comply with technological regulations and instructions for NPP operational personnel and contain information about the relationship between states and steps of procedures. The object of the study is the process of forming computer-oriented procedures for controlling a NPP power unit. The subject of the study is logical-structural models of computer-oriented procedures and methods for identifying states and steps of procedure execution based on production rules. The following tasks were solved in this study: the data structure of the computer-oriented procedure model was developed, which complies with current regulations and instructions; a logical-structural model of a computer-oriented procedure was created, which will be used to create support systems for NPP operational personnel; A method for identifying the conditions for entering the procedure and performing its steps has been developed. The model is designed to solve the problem of maintaining relevance, early identification of the states of the power unit and its equipment, ensuring the possibility of obtaining information about the state of technological parameters with the required level of reliability and accuracy. The proposed model can be used to create support systems for operational personnel managing complex technological facilities using specific procedures and instructions.
- 1 January 2025
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 3 (27) , 429-448
RESEARCH OF ARTIFICIAL INTELLIGENCE TOOLS FOR WORKING WITH DATABASES AND DATA ANALYSIS
This paper examines artificial intelligence tools for working with databases and data analysis. The purpose of this paper is to investigate the means and possibilities of using artificial intelligence in solving problems that arise when working with databases. The object of the study is the process of applying artificial intelligence. The subject of the study is the definition of artificial intelligence tools for working with databases and data analysis. The following tasks were solved in this study: the integration of artificial intelligence into databases was investigated; artificial intelligence tools for database design were analyzed; artificial intelligence tools for data analysis were analyzed; ways of using Generative AI for databases were considered. Each of the tools considered represents solutions based on artificial intelligence, has unique functions and strengths, and is capable of solving a variety of tasks. As artificial intelligence continues to develop, these tools will undoubtedly become an even more integral part of the success of organizations managing data.
- 1 January 2025
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 3 (27) , 429-448
RESEARCH OF ARTIFICIAL INTELLIGENCE TOOLS FOR WORKING WITH DATABASES AND DATA ANALYSIS
This paper examines artificial intelligence tools for working with databases and data analysis. The purpose of this paper is to investigate the means and possibilities of using artificial intelligence in solving problems that arise when working with databases. The object of the study is the process of applying artificial intelligence. The subject of the study is the definition of artificial intelligence tools for working with databases and data analysis. The following tasks were solved in this study: the integration of artificial intelligence into databases was investigated; artificial intelligence tools for database design were analyzed; artificial intelligence tools for data analysis were analyzed; ways of using Generative AI for databases were considered. Each of the tools considered represents solutions based on artificial intelligence, has unique functions and strengths, and is capable of solving a variety of tasks. As artificial intelligence continues to develop, these tools will undoubtedly become an even more integral part of the success of organizations managing data.
- Open Access
- 1 January 2024
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 1 (25) , 253-278
RESEARCH OF INFORMATION SECURITY AND TECHNOLOGICAL REGULATIONS OF THE MANAGEMENT PROCESSES OF THE CRITICAL INFRASTRUCTURE OF A NPP POWER UNIT WITH A VVER-1000 REACTOR
A brief overview of the technological processes of the critical infrastructure of the NPP power unit with the VVER-1000 type reactor is given using the example of power units 1 and 2 of the South Ukrainian NPP. The purpose of this article is to study the organization of power unit management in different modes, to analyze the structure and volume of information provided to operational personnel from the information and control system, digital software and technical complexes, and other systems, as well as to analyze the complexity of the technological regulations by which management takes place NPP power unit. The object of the research is the process of information support and technological regulations, according to which the power unit of the NPP is managed. The subject of the study is the intensity and complexity of the decision-making processes by the operational staff of the NPP when managing the power unit. The following tasks were solved in this work: The organization of the power unit management process was studied; The main information and control systems and software and technical complexes of the power unit were considered, as well as means of their interaction with operational personnel; The information model, which is used by operational personnel in managing the power unit, is considered. For this purpose, the indicators of the information model, which is used by operational staff to make decisions when managing the power unit, were determined and the volume of control bodies with which the operational staff interacts to manage the power unit was determined. The structure of technological regulations and instructions for power unit management was analyzed and the volume and complexity of these documents were determined; The expediency of research on improving NPP power unit management processes has been determined, namely: in the direction of further research, support systems for operational personnel, their classification, functions and experience of application at NPPs of Ukraine will be considered, with the aim of determining the actual design directions of such systems. It is necessary to determine which support systems have been implemented or are being developed at the present time, which difficulties arise for the operational staff during the management of the power unit, and which of them can be solved with the help of support systems.
- 1 January 2024
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 1 (25) , 253-278
Open AccessRESEARCH OF INFORMATION SECURITY AND TECHNOLOGICAL REGULATIONS OF THE MANAGEMENT PROCESSES OF THE CRITICAL INFRASTRUCTURE OF A NPP POWER UNIT WITH A VVER-1000 REACTOR
A brief overview of the technological processes of the critical infrastructure of the NPP power unit with the VVER-1000 type reactor is given using the example of power units 1 and 2 of the South Ukrainian NPP. The purpose of this article is to study the organization of power unit management in different modes, to analyze the structure and volume of information provided to operational personnel from the information and control system, digital software and technical complexes, and other systems, as well as to analyze the complexity of the technological regulations by which management takes place NPP power unit. The object of the research is the process of information support and technological regulations, according to which the power unit of the NPP is managed. The subject of the study is the intensity and complexity of the decision-making processes by the operational staff of the NPP when managing the power unit. The following tasks were solved in this work: The organization of the power unit management process was studied; The main information and control systems and software and technical complexes of the power unit were considered, as well as means of their interaction with operational personnel; The information model, which is used by operational personnel in managing the power unit, is considered. For this purpose, the indicators of the information model, which is used by operational staff to make decisions when managing the power unit, were determined and the volume of control bodies with which the operational staff interacts to manage the power unit was determined. The structure of technological regulations and instructions for power unit management was analyzed and the volume and complexity of these documents were determined; The expediency of research on improving NPP power unit management processes has been determined, namely: in the direction of further research, support systems for operational personnel, their classification, functions and experience of application at NPPs of Ukraine will be considered, with the aim of determining the actual design directions of such systems. It is necessary to determine which support systems have been implemented or are being developed at the present time, which difficulties arise for the operational staff during the management of the power unit, and which of them can be solved with the help of support systems.