Viktor Vyshnivskyi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Viktor Vyshnivskyi has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Olha Zinchenko
State University of Information and Communication Technologies
3 shared publications - Anton Shantyr
Державний університет інформаційно-комунікаційних технологій, Київ
2 shared publications - Iryna Zamrii
State University of Information and Communication Technologies
2 shared publications - Anna Soroka
State University of Information and Communication Technologies
1 shared publication - E. N. Shikula
National Academy of Sciences of Ukraine
1 shared publication - Kamila Storchak
State University of Information and Communication Technologies
1 shared publication
Latest Publications
- Open Access
- 5 June 2026
- Published by Taras Shevchenko National University of Kyiv in Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics
- Vol. 82 (1) , 165-169
Model of deformation of in-plane reinforced fiberous materials with physically nonlinear matrix
With increasing load, many homogeneous and composite materials exhibit nonlinear relationships between macrostresses and macrostrains. This may be due to the physical nonlinearity of component deformation. Fibrous materials are used in structures and parts operating under high force and temperature loads. Therefore, predicting their nonlinear properties is relevant. The aim of the work is to build a model and study the nonlinear deformation of in-plane reinforced fibrous composite materials with a physically nonlinear matrix. In-plane reinforced fibrous materials are considered as multicomponent materials with a random arrangement of fibers, considering the matrix and fibers of each direction as separate components. We will assume that the fiber material is transversely isotropic with an axis of symmetry along the fibers, the matrix material is isotropic physically nonlinear. The determination of the effective deformation properties and the stress-strain state of the material is carried out in two stages. At the first stage, the properties of the subsystem, which is a unidirectional fibrous material formed by fibers of a certain direction and part of the matrix, are determined. The solution of the first stage problem is carried out on the basis of a model of a unidirectional fibrous material of a stochastic structure. The solution is built using the method of conditional moments of L.P. Khoroshun. At the second stage, the effective properties of the entire system are determined based on the calculated properties of the subsystems. The solution is built on the basis of the Voichta scheme. Nonlinear equations that take into account the physical nonlinearity of the matrix are solved by the iterative method. An algorithm for determining the effective properties and stress-strain state of a material with a physically nonlinear matrix has been developed. The laws of the relationship between macrostresses and macrostrains in the material and the dependence of the average strains and stresses in the material matrix on macrostrains have been established. The deformation curves of the material have been studied. It has been established that the nonlinearity of the components significantly affects the effective deformation properties and the stress-strain state of the material.
- 5 June 2026
- Published by Taras Shevchenko National University of Kyiv in Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics
- Vol. 82 (1) , 165-169
Open AccessModel of deformation of in-plane reinforced fiberous materials with physically nonlinear matrix
With increasing load, many homogeneous and composite materials exhibit nonlinear relationships between macrostresses and macrostrains. This may be due to the physical nonlinearity of component deformation. Fibrous materials are used in structures and parts operating under high force and temperature loads. Therefore, predicting their nonlinear properties is relevant. The aim of the work is to build a model and study the nonlinear deformation of in-plane reinforced fibrous composite materials with a physically nonlinear matrix. In-plane reinforced fibrous materials are considered as multicomponent materials with a random arrangement of fibers, considering the matrix and fibers of each direction as separate components. We will assume that the fiber material is transversely isotropic with an axis of symmetry along the fibers, the matrix material is isotropic physically nonlinear. The determination of the effective deformation properties and the stress-strain state of the material is carried out in two stages. At the first stage, the properties of the subsystem, which is a unidirectional fibrous material formed by fibers of a certain direction and part of the matrix, are determined. The solution of the first stage problem is carried out on the basis of a model of a unidirectional fibrous material of a stochastic structure. The solution is built using the method of conditional moments of L.P. Khoroshun. At the second stage, the effective properties of the entire system are determined based on the calculated properties of the subsystems. The solution is built on the basis of the Voichta scheme. Nonlinear equations that take into account the physical nonlinearity of the matrix are solved by the iterative method. An algorithm for determining the effective properties and stress-strain state of a material with a physically nonlinear matrix has been developed. The laws of the relationship between macrostresses and macrostrains in the material and the dependence of the average strains and stresses in the material matrix on macrostrains have been established. The deformation curves of the material have been studied. It has been established that the nonlinearity of the components significantly affects the effective deformation properties and the stress-strain state of the material.
- 29 May 2026
- Published by Rauf Ablyazov East European University in Bulletin of East European University of Economics and Management
- p. 453
ALGORITHMIC CHOICE MANAGEMENT IN B2M MARKETING: FROM COSINE SIMILARITY TO API-CALL RATE
The article is devoted to the conceptualization of a new marketing paradigm – Business-to-Machine (B2M), which emerges as a result of delegating consumer decision-making to autonomous AI agents. This new paradigm replaces the classical B2C (Business-to-Consumer) and B2B (Business-to-Business) models in the context of total digitalization and the transformation of enterprise marketing management systems. The study focuses on identifying the mechanisms of transformation of marketing strategies and customer interaction management – from emotional influence on humans to algorithmic interaction with digital intermediaries. The research applies methods of system analysis to verify the transition from SEO (Search Engine Optimization) to AEO (Answer Engine Optimization). A mathematical model of deterministic AI-agent choice based on minimizing the cosine distance between the brand characteristic vector and the consumer needs vector has been developed and substantiated. Special attention is paid to the issues of managing the effectiveness of B2M marketing under conditions of algorithmization of digital communications. For the first time, the API-Call Rate (ACR) indicator is introduced and mathematically described as a key metric for evaluating and managing the effectiveness of B2M marketing, replacing the traditional Click-Through Rate (CTR). The research results enable enterprises to adapt their data architecture, improve the management of digital marketing processes, and ensure high brand relevance within the agentic commerce environment. The proposed model minimizes transaction costs and eliminates cognitive biases in the purchasing process, ensuring the transition to a state of market “hyper-efficiency.” Keywords: management system, decision, B2M marketing, autonomous AI agents, deterministic selection model, ecosystem, cosine similarity, API-Call Rate, Answer Engine Optimization (AEO).
- 29 May 2026
- Published by Rauf Ablyazov East European University in Bulletin of East European University of Economics and Management
- p. 453
ALGORITHMIC CHOICE MANAGEMENT IN B2M MARKETING: FROM COSINE SIMILARITY TO API-CALL RATE
The article is devoted to the conceptualization of a new marketing paradigm – Business-to-Machine (B2M), which emerges as a result of delegating consumer decision-making to autonomous AI agents. This new paradigm replaces the classical B2C (Business-to-Consumer) and B2B (Business-to-Business) models in the context of total digitalization and the transformation of enterprise marketing management systems. The study focuses on identifying the mechanisms of transformation of marketing strategies and customer interaction management – from emotional influence on humans to algorithmic interaction with digital intermediaries. The research applies methods of system analysis to verify the transition from SEO (Search Engine Optimization) to AEO (Answer Engine Optimization). A mathematical model of deterministic AI-agent choice based on minimizing the cosine distance between the brand characteristic vector and the consumer needs vector has been developed and substantiated. Special attention is paid to the issues of managing the effectiveness of B2M marketing under conditions of algorithmization of digital communications. For the first time, the API-Call Rate (ACR) indicator is introduced and mathematically described as a key metric for evaluating and managing the effectiveness of B2M marketing, replacing the traditional Click-Through Rate (CTR). The research results enable enterprises to adapt their data architecture, improve the management of digital marketing processes, and ensure high brand relevance within the agentic commerce environment. The proposed model minimizes transaction costs and eliminates cognitive biases in the purchasing process, ensuring the transition to a state of market “hyper-efficiency.” Keywords: management system, decision, B2M marketing, autonomous AI agents, deterministic selection model, ecosystem, cosine similarity, API-Call Rate, Answer Engine Optimization (AEO).
- 8 April 2026
- Published by MECS Publisher in International Journal of Computer Network and Information Security
- Vol. 18 (2) , 1-18
Cloud-native AI Pipelines for Continuous Infrastructure Optimization and Anomaly Detection
The article describes a model of cloud-native AI pipelines designed for continuous optimization of computing infrastructure and real-time anomaly detection. The developed model combines modern approaches to observability, machine learning (ML), and auto-scaling based on load forecasting. The methodology is based on the use of LSTM models, autoencoders, and convolutional neural networks (CNN) integrated into Kubernetes environment with support for Prometheus, Kafka, and Grafana. Load changes are simulated, and the system's response to critical events is evaluated. The results demonstrate a significant improvement in anomaly detection accuracy (up to 93%) and resource efficiency (up to 26% cost reduction compared to traditional approaches). The proposed model can be used in AIOps systems that require a high level of automation and reliability.
- 8 April 2026
- Published by MECS Publisher in International Journal of Computer Network and Information Security
- Vol. 18 (2) , 1-18
Cloud-native AI Pipelines for Continuous Infrastructure Optimization and Anomaly Detection
The article describes a model of cloud-native AI pipelines designed for continuous optimization of computing infrastructure and real-time anomaly detection. The developed model combines modern approaches to observability, machine learning (ML), and auto-scaling based on load forecasting. The methodology is based on the use of LSTM models, autoencoders, and convolutional neural networks (CNN) integrated into Kubernetes environment with support for Prometheus, Kafka, and Grafana. Load changes are simulated, and the system's response to critical events is evaluated. The results demonstrate a significant improvement in anomaly detection accuracy (up to 93%) and resource efficiency (up to 26% cost reduction compared to traditional approaches). The proposed model can be used in AIOps systems that require a high level of automation and reliability.
- 10 September 2025
- Published by National Aerospace University - Kharkiv Aviation Institute in RADIOELECTRONIC AND COMPUTER SYSTEMS
- Vol. 2025 (3) , 88-100
An integrated approach to forecasting software system quality using bayesian correction, multi-criteria optimization, and meta-learning
The aim of this study is to improve modern methods for forecasting the quantitative characteristics of software system quality to enhance reliability, efficiency, and adaptability in dynamic IT environments. To achieve this, an integrated forecasting approach was developed that combines adaptive Bayesian noise correction, probabilistic ensembles with weighted risk adjustment, hybrid multi-criteria optimization, graph models of metric interdependencies, and meta-learning for forecast adaptation. The scientific novelty lies in the proposed ensemble integration and adaptive mechanisms that increase forecasting robustness while accounting for uncertainty and metric dependencies. The methods were validated on the GitLab CE system. The experimental results confirmed measurable improvements: forecasting error was reduced from 18.7% to 4.2%, execution time decreased by 36.8%, CPU and memory consumption dropped by up to 20%, and system reliability indicators (downtime, fault tolerance) improved by more than 60%. These metrics confirm that the proposed approach strengthens reliability, efficiency, and adaptability of software quality forecasting compared to traditional methods.
- 10 September 2025
- Published by National Aerospace University - Kharkiv Aviation Institute in RADIOELECTRONIC AND COMPUTER SYSTEMS
- Vol. 2025 (3) , 88-100
An integrated approach to forecasting software system quality using bayesian correction, multi-criteria optimization, and meta-learning
The aim of this study is to improve modern methods for forecasting the quantitative characteristics of software system quality to enhance reliability, efficiency, and adaptability in dynamic IT environments. To achieve this, an integrated forecasting approach was developed that combines adaptive Bayesian noise correction, probabilistic ensembles with weighted risk adjustment, hybrid multi-criteria optimization, graph models of metric interdependencies, and meta-learning for forecast adaptation. The scientific novelty lies in the proposed ensemble integration and adaptive mechanisms that increase forecasting robustness while accounting for uncertainty and metric dependencies. The methods were validated on the GitLab CE system. The experimental results confirmed measurable improvements: forecasting error was reduced from 18.7% to 4.2%, execution time decreased by 36.8%, CPU and memory consumption dropped by up to 20%, and system reliability indicators (downtime, fault tolerance) improved by more than 60%. These metrics confirm that the proposed approach strengthens reliability, efficiency, and adaptability of software quality forecasting compared to traditional methods.
- Open Access
- 26 June 2024
- Published by State University "Kyiv Aviation Institute" in Ukrainian Information Security Research Journal
- Vol. 26 (1) , 89-101
МУЛЬТИАСПЕКТНІСТЬ ТА CТРАТЕГІЧНЕ ПЛАНУВАННЯ ПРИ СТВОРЕНІ БАГАТОЦІЛЬОВИХ МОДЕЛЕЙ ОЦІНКИ ЯКОСТІ ПРОГРАМНИХ СИСТЕМ
У сучасному інформаційному суспільстві проблема оцінювання якості програмних систем (ПС) є однією з ключових. Мета даної статті полягає в ретельному розгляді особливостей процесу оцінювання якості ПС з використанням принципів мультиаспектності та стратегічного планування. Для досягнення поставленої мети визначені чотири основні цілі. По-перше, стаття пропонує докладно розглянути основні етапи принципу мультиаспектності в підході до оцінювання якості ПС при створенні багатоцільових моделей якості. По-друге, здійснюється спроба надати математичні пояснення щодо того, як може бути представлена мультиаспектність в моделюванні якості ПС. По-третє, стаття розглядає основні аспектні етапи стратегічного планування багатоцільових моделей із оцінки якості ПС. Нарешті, вона пропонує аналізувати фундаментальні формули, які можна використовувати для математичного вираження різних аспектів якості ПС в межах стратегічного планування та реалізації механізму оцінки якості ПС. Отримані результати статті сприятимуть подальшому розвитку області оцінки якості програмного забезпечення та підвищенню ефективності розробки та управління програмними проектами. Дослідження показало, що використання принципів мультиаспектності та стратегічного планування в оцінюванні якості програмних систем є дієвим підходом, що дозволяє створювати комплексні та адаптивні моделі оцінки. Ретельний аналіз основних етапів принципу мультиаспектності в підході до оцінювання якості ПС, а також розгляд аспектів стратегічного планування багатоцільових моделей, підкреслив важливість розуміння різноманітних потреб користувачів та інших зацікавлених сторін. Математичні пояснення стосовно представлення мультиаспектності в моделюванні якості ПС виявилися корисними для розробки формул та механізмів оцінки. Аналіз фундаментальних формул дав змогу розробити інструменти для математичного вираження різних аспектів якості ПС та їх використання у стратегічному плануванні. На підставі отриманих результатів можна зробити висновок, що застосування розглянутих підходів до оцінювання якості ПС сприятиме підвищенню ефективності управління проектами та розробки програмного забезпечення. Такі моделі дозволять враховувати різноманітні потреби та очікування різних зацікавлених сторін, що є ключовим для досягнення успіху в сучасному програмному індустрії.
- 26 June 2024
- Published by State University "Kyiv Aviation Institute" in Ukrainian Information Security Research Journal
- Vol. 26 (1) , 89-101
Open AccessМУЛЬТИАСПЕКТНІСТЬ ТА CТРАТЕГІЧНЕ ПЛАНУВАННЯ ПРИ СТВОРЕНІ БАГАТОЦІЛЬОВИХ МОДЕЛЕЙ ОЦІНКИ ЯКОСТІ ПРОГРАМНИХ СИСТЕМ
У сучасному інформаційному суспільстві проблема оцінювання якості програмних систем (ПС) є однією з ключових. Мета даної статті полягає в ретельному розгляді особливостей процесу оцінювання якості ПС з використанням принципів мультиаспектності та стратегічного планування. Для досягнення поставленої мети визначені чотири основні цілі. По-перше, стаття пропонує докладно розглянути основні етапи принципу мультиаспектності в підході до оцінювання якості ПС при створенні багатоцільових моделей якості. По-друге, здійснюється спроба надати математичні пояснення щодо того, як може бути представлена мультиаспектність в моделюванні якості ПС. По-третє, стаття розглядає основні аспектні етапи стратегічного планування багатоцільових моделей із оцінки якості ПС. Нарешті, вона пропонує аналізувати фундаментальні формули, які можна використовувати для математичного вираження різних аспектів якості ПС в межах стратегічного планування та реалізації механізму оцінки якості ПС. Отримані результати статті сприятимуть подальшому розвитку області оцінки якості програмного забезпечення та підвищенню ефективності розробки та управління програмними проектами. Дослідження показало, що використання принципів мультиаспектності та стратегічного планування в оцінюванні якості програмних систем є дієвим підходом, що дозволяє створювати комплексні та адаптивні моделі оцінки. Ретельний аналіз основних етапів принципу мультиаспектності в підході до оцінювання якості ПС, а також розгляд аспектів стратегічного планування багатоцільових моделей, підкреслив важливість розуміння різноманітних потреб користувачів та інших зацікавлених сторін. Математичні пояснення стосовно представлення мультиаспектності в моделюванні якості ПС виявилися корисними для розробки формул та механізмів оцінки. Аналіз фундаментальних формул дав змогу розробити інструменти для математичного вираження різних аспектів якості ПС та їх використання у стратегічному плануванні. На підставі отриманих результатів можна зробити висновок, що застосування розглянутих підходів до оцінювання якості ПС сприятиме підвищенню ефективності управління проектами та розробки програмного забезпечення. Такі моделі дозволять враховувати різноманітні потреби та очікування різних зацікавлених сторін, що є ключовим для досягнення успіху в сучасному програмному індустрії.
- Open Access
- 7 June 2024
- Published by European Scientific Platform (Publications) in Grail of Science
- No. 40,p. 355-359
USE OF MODERN TECHNOLOGIES IN THE DEVELOPMENT PROCESS OF MOBILE APPLICATIONS IN THE E-COMMERCE
The article provides a detailed analysis of the application of information technologies and the possibilities of their effective use in the e-commerce market. The main technologies for the development of mobile applications based on the Android operating system, relevant software environments and programming languages are considered. Possible scenarios for the use of programs are formed, taking into account their functionality. The analysis of native and cross-platform approaches to mobile application development was carried out.
- 7 June 2024
- Published by European Scientific Platform (Publications) in Grail of Science
- No. 40,p. 355-359
Open AccessUSE OF MODERN TECHNOLOGIES IN THE DEVELOPMENT PROCESS OF MOBILE APPLICATIONS IN THE E-COMMERCE
The article provides a detailed analysis of the application of information technologies and the possibilities of their effective use in the e-commerce market. The main technologies for the development of mobile applications based on the Android operating system, relevant software environments and programming languages are considered. Possible scenarios for the use of programs are formed, taking into account their functionality. The analysis of native and cross-platform approaches to mobile application development was carried out.
- 20 March 2024
- Published by Academy of Cognitive and Natural Sciences
Method of Ensuring the Functional Stability of the Information System based on Detection of Intrusions and Reconfiguration of Virtual Networks
The functioning of the information system takes place in conditions of constant interaction with the external environment under the influence of various destabilizing factors. Informational conflicts that provide information about bilateral interaction and have a destructive effect on the elements of the opposite party deserve special attention, which allows for obtaining, storing, and processing information necessary to achieve the goals of the entire system and even counteract the processes that have arisen under the influence of an informational conflict. Destabilizing factors and conflicts in the system lead to failures in the functional processes of the information system. Prevention of these effects occurs by ensuring the functional stability of the information system, that is, the ability of the system to preserve or restore certain system functions during the action of destabilizing factors. The article develops a method for ensuring the functional stability of the information system using software-defined wide area networks, which is aimed at solving the problem of increasing the stability and security of the information system against violations based on the detection of intrusions and the reconfiguration of virtual networks in virtual cloud environments.
- 20 March 2024
- Published by Academy of Cognitive and Natural Sciences
Method of Ensuring the Functional Stability of the Information System based on Detection of Intrusions and Reconfiguration of Virtual Networks
The functioning of the information system takes place in conditions of constant interaction with the external environment under the influence of various destabilizing factors. Informational conflicts that provide information about bilateral interaction and have a destructive effect on the elements of the opposite party deserve special attention, which allows for obtaining, storing, and processing information necessary to achieve the goals of the entire system and even counteract the processes that have arisen under the influence of an informational conflict. Destabilizing factors and conflicts in the system lead to failures in the functional processes of the information system. Prevention of these effects occurs by ensuring the functional stability of the information system, that is, the ability of the system to preserve or restore certain system functions during the action of destabilizing factors. The article develops a method for ensuring the functional stability of the information system using software-defined wide area networks, which is aimed at solving the problem of increasing the stability and security of the information system against violations based on the detection of intrusions and the reconfiguration of virtual networks in virtual cloud environments.
- Open Access
- 1 January 2022
- Published by Taras Shevchenko National University of Kyiv in Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics
- No. 3,p. 47-54
Method of identification of atomic elements of information space with the help of a unified information space
The article considers a method that allows to identify the input atomic element of the information space by combining information spaces into a unified information space (this is an information model of a complex subject area, which includes information objects, relationships between them, space environment and processes). This method allows you to refine the missing features for the input element to enable it to be added to a unified information space. Pages of the article in the issue: 47 - 54 Language of the article: Ukrainian
- 1 January 2022
- Published by Taras Shevchenko National University of Kyiv in Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics
- No. 3,p. 47-54
Open AccessMethod of identification of atomic elements of information space with the help of a unified information space
The article considers a method that allows to identify the input atomic element of the information space by combining information spaces into a unified information space (this is an information model of a complex subject area, which includes information objects, relationships between them, space environment and processes). This method allows you to refine the missing features for the input element to enable it to be added to a unified information space. Pages of the article in the issue: 47 - 54 Language of the article: Ukrainian