Yuliia Ulianovska
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yuliia Ulianovska has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Tatyana Rudyanova
Ph.D., Associate Professor, Department of Computer Science and Software Engineering, University of Customs and Finance
2 shared publications - Victoria Kostenko
University of Customs and Finance
2 shared publications - Alexander Firsov
University of Customs and Finance
1 shared publication - Alexandr Kuznetsov
Department of Theoretical and Applied Sciences, eCampus University, Via Isimbardi 10, 22060 Novedrate, CO, Italy
1 shared publication - Anastasiia Kiian
JSC “Institute of Information Technologies
1 shared publication Dmytro Bocharov
Department of International Economic Relations and Regional Studies University of Customs and Finance Dnipro Ukraine
1 shared publication
Latest Publications
- Open Access
- 5 April 2024
- Published by Private Company Technology Center in Technology audit and production reserves
- Vol. 2 (2(76)) , 32-37
Study of the process of identifying the authorship of texts written in natural language
The object of the research is the process of identifying the authorship of a text using computer technologies with the application of machine learning. The full process of solving the problem from text preparation to evaluation of the results was considered. Identification of the authorship of a text is a very complex and time-consuming task that requires maximum attention. This is because the identification process always requires taking into account a very large number of different factors and information related to each specific author. As a result, various problems and errors related to the human factor may arise in the identification process, which may ultimately lead to a deterioration in the results obtained. The subject of the work is the methods and means of analyzing the process of identifying the authorship of a text using existing computer technologies. As part of the work, the authors have developed a web application for identifying the authorship of a text. The software application was written using machine learning technologies, has a user-friendly interface and an advanced error tracking system, and can recognize both text written by one author and that written in collaboration. The effectiveness of different types of machine learning models and data fitting tools is analyzed. Computer technologies for identifying the authorship of a text are defined. The main advantages of using computer technology to identify text authorship are: – Speed: computer algorithms can analyze large amounts of text in an extremely short period of time. – Objectivity: computer algorithms use only proven algorithms to analyze text features and are not subject to emotional influence or preconceived opinions during the analysis process. The result of the work is a web application for identifying the authorship of a text developed on the basis of research on the process of identifying the authorship of a text using computer technology.
- 5 April 2024
- Published by Private Company Technology Center in Technology audit and production reserves
- Vol. 2 (2(76)) , 32-37
Open AccessStudy of the process of identifying the authorship of texts written in natural language
The object of the research is the process of identifying the authorship of a text using computer technologies with the application of machine learning. The full process of solving the problem from text preparation to evaluation of the results was considered. Identification of the authorship of a text is a very complex and time-consuming task that requires maximum attention. This is because the identification process always requires taking into account a very large number of different factors and information related to each specific author. As a result, various problems and errors related to the human factor may arise in the identification process, which may ultimately lead to a deterioration in the results obtained. The subject of the work is the methods and means of analyzing the process of identifying the authorship of a text using existing computer technologies. As part of the work, the authors have developed a web application for identifying the authorship of a text. The software application was written using machine learning technologies, has a user-friendly interface and an advanced error tracking system, and can recognize both text written by one author and that written in collaboration. The effectiveness of different types of machine learning models and data fitting tools is analyzed. Computer technologies for identifying the authorship of a text are defined. The main advantages of using computer technology to identify text authorship are: – Speed: computer algorithms can analyze large amounts of text in an extremely short period of time. – Objectivity: computer algorithms use only proven algorithms to analyze text features and are not subject to emotional influence or preconceived opinions during the analysis process. The result of the work is a web application for identifying the authorship of a text developed on the basis of research on the process of identifying the authorship of a text using computer technology.
- Open Access
- 28 February 2023
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 1 (4 (121)) , 6-25
Implementing the method of figurative transformations to minimize partially defined Boolean functions
This paper reports a research that established the possibility of increasing the effectiveness of the method of figurative transformations to minimize partially defined Boolean functions. The method makes it possible, without loss of functionality, to reduce the complexity of the minimization procedure, compared to sorting out binary definitions of partially defined Boolean functions. The interpretation of the result is that the 2-(n, b)-design, 2-(n, x/b)-design systems are a reflection of logical operations. Therefore, the identification of such combinatorial systems in the truth table of logical functions directly and unambiguously establishes the location of logical operations for equivalent transformations of Boolean expressions. This, in turn, implicates an algorithm for simplifying Boolean functions, including partially defined Boolean functions. Thus, the method of figurative transformations simplifies and speeds up the procedure for minimizing partially defined Boolean functions, compared to analogs. This indicates that the visual-matrix form of the analytical method still has the prospect of increasing its hardware capabilities, including in terms of minimizing partially defined Boolean functions. It has been experimentally confirmed that the method of figurative transformations increases the efficiency of minimizing partially defined Boolean functions, compared with analogs, by 100–200 %. There is reason to argue about the possibility of increasing the efficiency of minimizing partially defined Boolean functions in the main and polynomial bases by the specified method. The effectiveness of the method, in particular, is ensured by carrying out all operations of generalized gluing of variables for dead-end disjunctive normal forms (DNF), followed by the use of implicant tables; optimal combination of a sequence of logical operations for gluing variables
- 28 February 2023
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 1 (4 (121)) , 6-25
Open AccessImplementing the method of figurative transformations to minimize partially defined Boolean functions
This paper reports a research that established the possibility of increasing the effectiveness of the method of figurative transformations to minimize partially defined Boolean functions. The method makes it possible, without loss of functionality, to reduce the complexity of the minimization procedure, compared to sorting out binary definitions of partially defined Boolean functions. The interpretation of the result is that the 2-(n, b)-design, 2-(n, x/b)-design systems are a reflection of logical operations. Therefore, the identification of such combinatorial systems in the truth table of logical functions directly and unambiguously establishes the location of logical operations for equivalent transformations of Boolean expressions. This, in turn, implicates an algorithm for simplifying Boolean functions, including partially defined Boolean functions. Thus, the method of figurative transformations simplifies and speeds up the procedure for minimizing partially defined Boolean functions, compared to analogs. This indicates that the visual-matrix form of the analytical method still has the prospect of increasing its hardware capabilities, including in terms of minimizing partially defined Boolean functions. It has been experimentally confirmed that the method of figurative transformations increases the efficiency of minimizing partially defined Boolean functions, compared with analogs, by 100–200 %. There is reason to argue about the possibility of increasing the efficiency of minimizing partially defined Boolean functions in the main and polynomial bases by the specified method. The effectiveness of the method, in particular, is ensured by carrying out all operations of generalized gluing of variables for dead-end disjunctive normal forms (DNF), followed by the use of implicant tables; optimal combination of a sequence of logical operations for gluing variables
- Open Access
- 30 December 2022
- Published by FinTechAlliance in Financial and credit activity: problems of theory and practice
- Vol. 6 (47) , 266-278
GAME THEORY AND FINANCIAL COMPONENTS FOR DETERMINING THE BUDGET PLACES OPTIMAL DISTRIBUTION IN THE HIGHER EDUCATION SYSTEM OF UKRAINE
The complexity and interdependence of management and decision-making problems in the system of higher education require new ideas and approaches, which necessitates the search for new management solutions using modern approaches and methods of economic and mathematical modeling. The article is devoted to the problem of optimal allocation of budget places for higher education institutions by specialty. The conducted research shows that the priorities of the state, labor market and consumers do not coincide. In this situation, the university, as a provider of educational services, must balance the demand of the consumer (applicants, students and their parents) with the offers of the customer (the state, entrepreneurs, the labor market), taking into account the forecast of demand in the labor market. The purpose of the study is to determine the optimal allocation of budget places for higher education institutions considering financial constituents, system analysis and the game theory method. A solution to the problem is offered by building an economic-mathematical model using game theory techniques and methods of analyzing hierarchies, which have a powerful apparatus for considering many different models, approaches and concepts for solving the same problem. The presented mathematical model allows to obtain a balanced optimal distribution of budget places by university specialties, which harmonizes the demands of applicants and employers. The budgetary expenditures for higher education are an effective regulator of direct action on the training of specialists with higher education and an instrument of state regulation of the number of state-ordered students. Based on the results of the study, the model of distribution of the institution's budget expenditures for decision-making management is proposed, which allows redistributing funds to expenditure items that are included in the development expenditures of higher education institutions. Further development of the described model in the direction of researching the impact on existing restrictions on the market of educational services will allow offering powerful mechanisms and technologies for managing the process of forming optimal strategies for the development of higher education institutions.
- 30 December 2022
- Published by FinTechAlliance in Financial and credit activity: problems of theory and practice
- Vol. 6 (47) , 266-278
Open AccessGAME THEORY AND FINANCIAL COMPONENTS FOR DETERMINING THE BUDGET PLACES OPTIMAL DISTRIBUTION IN THE HIGHER EDUCATION SYSTEM OF UKRAINE
The complexity and interdependence of management and decision-making problems in the system of higher education require new ideas and approaches, which necessitates the search for new management solutions using modern approaches and methods of economic and mathematical modeling. The article is devoted to the problem of optimal allocation of budget places for higher education institutions by specialty. The conducted research shows that the priorities of the state, labor market and consumers do not coincide. In this situation, the university, as a provider of educational services, must balance the demand of the consumer (applicants, students and their parents) with the offers of the customer (the state, entrepreneurs, the labor market), taking into account the forecast of demand in the labor market. The purpose of the study is to determine the optimal allocation of budget places for higher education institutions considering financial constituents, system analysis and the game theory method. A solution to the problem is offered by building an economic-mathematical model using game theory techniques and methods of analyzing hierarchies, which have a powerful apparatus for considering many different models, approaches and concepts for solving the same problem. The presented mathematical model allows to obtain a balanced optimal distribution of budget places by university specialties, which harmonizes the demands of applicants and employers. The budgetary expenditures for higher education are an effective regulator of direct action on the training of specialists with higher education and an instrument of state regulation of the number of state-ordered students. Based on the results of the study, the model of distribution of the institution's budget expenditures for decision-making management is proposed, which allows redistributing funds to expenditure items that are included in the development expenditures of higher education institutions. Further development of the described model in the direction of researching the impact on existing restrictions on the market of educational services will allow offering powerful mechanisms and technologies for managing the process of forming optimal strategies for the development of higher education institutions.
- Open Access
- 11 August 2022
- Published by Private Company Technology Center in Technology audit and production reserves
- Vol. 4 (2(66)) , 14-18
Consideration of the possibilities of applying machine learning methods for data analysis when promoting services to bank's clients
The object of the research is modern online services and machine learning libraries for predicting the probability of the bank client's consent to the provision of the proposed services. One of the most problematic areas is the high unpredictability of the result in the field of banking marketing using the most common technique of introducing new services for clients – the so-called cold calling. Therefore, the question of assessing the probability and predicting the behavior of a potential client when promoting new banking services and services using cold calling is particularly relevant. In the course of the study, libraries of machine learning methods and data analysis of the Python programming language were used. A program was developed to build a model for predicting the behavior of bank customers using data processing methods using gradient boosting, regularization of gradient boosting, random forest algorithm and recurrent neural networks. Analogous models were built using cloud machine learning services Azure ML, BigML and the Auto-sklearn library. Data analysis and prediction models built using Python language libraries have a fairly high quality – an average of 94.5 %. Using the Azure ML cloud service, a predictive model with an accuracy of 88.6 % was built. The BigML machine learning service made it possible to build a model with an accuracy of 88.8 %. Machine learning methods from the Auto-sklearn library made it possible to obtain a model with a higher quality – 94.9 %. This is due to the fact that the proposed libraries of the Python programming language allow better customization of data processing methods and machine learning to obtain more accurate models than free cloud services that do not provide such capabilities. Thanks to this, it is possible to obtain a predictive model of the behavior of bank customers with a fairly high degree of accuracy. It is worth noting that in order to make a prediction (forecast), it is necessary to study the context of the task, process the data, build various machine learning algorithms, evaluate the quality of the models and choose the best of them.
- 11 August 2022
- Published by Private Company Technology Center in Technology audit and production reserves
- Vol. 4 (2(66)) , 14-18
Open AccessConsideration of the possibilities of applying machine learning methods for data analysis when promoting services to bank's clients
The object of the research is modern online services and machine learning libraries for predicting the probability of the bank client's consent to the provision of the proposed services. One of the most problematic areas is the high unpredictability of the result in the field of banking marketing using the most common technique of introducing new services for clients – the so-called cold calling. Therefore, the question of assessing the probability and predicting the behavior of a potential client when promoting new banking services and services using cold calling is particularly relevant. In the course of the study, libraries of machine learning methods and data analysis of the Python programming language were used. A program was developed to build a model for predicting the behavior of bank customers using data processing methods using gradient boosting, regularization of gradient boosting, random forest algorithm and recurrent neural networks. Analogous models were built using cloud machine learning services Azure ML, BigML and the Auto-sklearn library. Data analysis and prediction models built using Python language libraries have a fairly high quality – an average of 94.5 %. Using the Azure ML cloud service, a predictive model with an accuracy of 88.6 % was built. The BigML machine learning service made it possible to build a model with an accuracy of 88.8 %. Machine learning methods from the Auto-sklearn library made it possible to obtain a model with a higher quality – 94.9 %. This is due to the fact that the proposed libraries of the Python programming language allow better customization of data processing methods and machine learning to obtain more accurate models than free cloud services that do not provide such capabilities. Thanks to this, it is possible to obtain a predictive model of the behavior of bank customers with a fairly high degree of accuracy. It is worth noting that in order to make a prediction (forecast), it is necessary to study the context of the task, process the data, build various machine learning algorithms, evaluate the quality of the models and choose the best of them.
- Open Access
- 25 February 2022
- Published by Private Company Technology Center in Technology audit and production reserves
- Vol. 1 (4(63)) , 27-31
Analysing features of e-commerce systems architecture
The object of the research is the process of designing the architecture of high-load systems. The conducted research is based on the system approach to design the architecture of e-commerce systems, characterized by high workload due to the large number of users working simultaneously with the system, a large amount of data and a significant number of complex calculations. The main hypothesis of the research is that the efficiency of such systems depends on the efficiency of each individual step to scale up the system and the consistency of these steps. The maximum efficiency can be achieved only if the resource constraints and requirements, which are determined by the key stakeholders of the projects, consider the specifics of the business system. This paper examines the methodological support of the developing high-load systems architecture. Within this research let’s analyze such specific features of high-loaded systems as scalability, rigidity, and response time and demonstrate the importance of considering these features when designing the architecture of high-loaded systems. This paper analyzes approaches to developing high-load systems architecture, their advantages, and disadvantages. It is suggested to use hybrid scaling method, which is based on combining two approaches – microservices and monolithic. It is also suggested to use a microservices approach for high-loaded and requiring scaling parts and a monolithic approach for non-loaded parts of the system. The research indicates the parts of the system that are usually highly loaded in e-commerce systems and require a microservices approach to design their architecture. This paper analyzes approaches to database scaling and organization of data replication. The application of the proposed approach to design the architecture of high-load systems, including the e-commerce systems, allows designing a system that can be easily scaled when necessary. At the same time, the system can be improved and further developed.
- 25 February 2022
- Published by Private Company Technology Center in Technology audit and production reserves
- Vol. 1 (4(63)) , 27-31
Open AccessAnalysing features of e-commerce systems architecture
The object of the research is the process of designing the architecture of high-load systems. The conducted research is based on the system approach to design the architecture of e-commerce systems, characterized by high workload due to the large number of users working simultaneously with the system, a large amount of data and a significant number of complex calculations. The main hypothesis of the research is that the efficiency of such systems depends on the efficiency of each individual step to scale up the system and the consistency of these steps. The maximum efficiency can be achieved only if the resource constraints and requirements, which are determined by the key stakeholders of the projects, consider the specifics of the business system. This paper examines the methodological support of the developing high-load systems architecture. Within this research let’s analyze such specific features of high-loaded systems as scalability, rigidity, and response time and demonstrate the importance of considering these features when designing the architecture of high-loaded systems. This paper analyzes approaches to developing high-load systems architecture, their advantages, and disadvantages. It is suggested to use hybrid scaling method, which is based on combining two approaches – microservices and monolithic. It is also suggested to use a microservices approach for high-loaded and requiring scaling parts and a monolithic approach for non-loaded parts of the system. The research indicates the parts of the system that are usually highly loaded in e-commerce systems and require a microservices approach to design their architecture. This paper analyzes approaches to database scaling and organization of data replication. The application of the proposed approach to design the architecture of high-load systems, including the e-commerce systems, allows designing a system that can be easily scaled when necessary. At the same time, the system can be improved and further developed.
- 5 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 587-590
Formalized Designing Methodology of ISMS for Critical Infrastructure
Today, the functioning of the state is impossible without a developed information infrastructure. Such systems are already considered as critical infrastructure. The architecture of information systems is growing along with the number of services they provide. Designing flaws of such systems can critically affect the safety of their operation. As information and telecommunication systems become more complex, security is becoming an important issue, where a formal approach to the design of security features will help to avoid mistakes in integrating an information security management system. This paper proposes new requirements for the ISMS project for critical infrastructure, in particular a formal design approach.
- 5 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 587-590
Formalized Designing Methodology of ISMS for Critical Infrastructure
Today, the functioning of the state is impossible without a developed information infrastructure. Such systems are already considered as critical infrastructure. The architecture of information systems is growing along with the number of services they provide. Designing flaws of such systems can critically affect the safety of their operation. As information and telecommunication systems become more complex, security is becoming an important issue, where a formal approach to the design of security features will help to avoid mistakes in integrating an information security management system. This paper proposes new requirements for the ISMS project for critical infrastructure, in particular a formal design approach.
- 5 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 577-582
Information Technology for Contact Tracking in the COVID-19 Pandemic
The development and implementation of the latest information technologies for contact tracking in the context of the COVID-19 pandemic is an extremely important and urgent task, which is directly related to the possible adjustment and mitigation of quarantine restrictions without increasing the risks and threats of infection. In this article, we analyze, research, and substantiate various information technologies (such as Bluetooth, Wi-Fi, GPS, etc.) in contact tracking tools to prevent the spread of infectious diseases. We explore various aspects such as centralization; the need to use a central server (data warehouse); used cryptographic protection algorithms; acceptable actions when establishing contact, etc. The research results make it possible to formulate practical recommendations on the choice of information technologies for building global contact tracing systems.
- 5 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 577-582
Information Technology for Contact Tracking in the COVID-19 Pandemic
The development and implementation of the latest information technologies for contact tracking in the context of the COVID-19 pandemic is an extremely important and urgent task, which is directly related to the possible adjustment and mitigation of quarantine restrictions without increasing the risks and threats of infection. In this article, we analyze, research, and substantiate various information technologies (such as Bluetooth, Wi-Fi, GPS, etc.) in contact tracking tools to prevent the spread of infectious diseases. We explore various aspects such as centralization; the need to use a central server (data warehouse); used cryptographic protection algorithms; acceptable actions when establishing contact, etc. The research results make it possible to formulate practical recommendations on the choice of information technologies for building global contact tracing systems.