Oleksandr Mitsa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Oleksandr Mitsa has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Vasyl Sharkan
ДВНЗ «Ужгородський національний університет
4 shared publications - Petro I. Stetsyuk
V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine, Kyiv
3 shared publications - Vasyl Petsko
Uzhhorod National University
3 shared publications - Yurii Horoshko
T. H. Shevchenko National University «Chernihiv Colehium
3 shared publications - Yurii Voloshchuk
Uzhhorod National University
3 shared publications - Maksym Lupei
School of Electrical Engineering and Computer Science, Pennsylvania State University, United States of America
2 shared publications
Latest Publications
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 135-140
Web-Based Modeling of Multilayer Optical Filters with Refractive Index Dispersion Reconstruction
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 135-140
Web-Based Modeling of Multilayer Optical Filters with Refractive Index Dispersion Reconstruction
- Open Access
- 27 February 2026
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 1 (9 (139)) , 68-77
Design of autonomous gaze-tracking system for inclusive education
Eye-tracking technology as a means of ensuring the accessibility of education for people with severe musculoskeletal disorders has been investigated in this study. A number of assistive technologies have been devised up to now that possess significant educational potential, but their autonomous use is mainly associated with such difficulties as dependence on the instability of wireless networks or external computing resources. The need to overcome the technological gap between the capabilities of assistive technologies and their real autonomy is a task addressed in this work. The study's result is the designed fully autonomous architecture based on virtual reality headsets (Meta Quest), which enables the execution of all eye image processing activities and provides direct interface control using the device's processor. The hardware was improved (frame miniaturization, transition to a wired USB interface were carried out); software was developed in the Rust language in the OpenXR API (Application Programming Interface) layer format. That has made it possible to get rid of network delays and ensure the system's operation, resistant to any conditions. Direct interaction with the headset hardware is provided by effective optimization of convolutional neural networks and the use of low-level system calls. An immersive graphical user interface (GUI) was designed, successfully tested for system configuration and calibration. The GUI became available directly in the virtual space of the headset. The results could be used for individual learning at home, as well as at inclusive educational institutions or rehabilitation centers that organize training for people with severe musculoskeletal disorders
- 27 February 2026
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 1 (9 (139)) , 68-77
Open AccessDesign of autonomous gaze-tracking system for inclusive education
Eye-tracking technology as a means of ensuring the accessibility of education for people with severe musculoskeletal disorders has been investigated in this study. A number of assistive technologies have been devised up to now that possess significant educational potential, but their autonomous use is mainly associated with such difficulties as dependence on the instability of wireless networks or external computing resources. The need to overcome the technological gap between the capabilities of assistive technologies and their real autonomy is a task addressed in this work. The study's result is the designed fully autonomous architecture based on virtual reality headsets (Meta Quest), which enables the execution of all eye image processing activities and provides direct interface control using the device's processor. The hardware was improved (frame miniaturization, transition to a wired USB interface were carried out); software was developed in the Rust language in the OpenXR API (Application Programming Interface) layer format. That has made it possible to get rid of network delays and ensure the system's operation, resistant to any conditions. Direct interaction with the headset hardware is provided by effective optimization of convolutional neural networks and the use of low-level system calls. An immersive graphical user interface (GUI) was designed, successfully tested for system configuration and calibration. The GUI became available directly in the virtual space of the headset. The results could be used for individual learning at home, as well as at inclusive educational institutions or rehabilitation centers that organize training for people with severe musculoskeletal disorders
- Open Access
- 31 October 2025
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 5 (2 (137)) , 98-106
Determining the effectiveness of GPT-4.1-mini for multiclass text categorization
The object of this study is the process of multiclass automatic categorization of user queries using large language models under the conditions of a language transition from English to Ukrainian. The scientific task relates to the fact that most modern large language models (LLMs) are optimized for English while their effectiveness for morphologically complex and low-resource languages, particularly Ukrainian, remains insufficiently studied. In this work, an experimental approach was devised and implemented to evaluate the transferability of the GPT-4.1-mini model from English to Ukrainian in the task to categorize 11,047 user queries spanning nine applied domains. The analysis employed conventional metrics (Recall, Precision, Weighted-F1, Macro-F1) alongside a novel indicator, the Uncertainty/Error Rate (U/E), which captures the proportion of model refusals and “hallucinations.” The findings demonstrate that the highest quality was achieved on the English dataset (Macro-F1 = 69.78%, U/E = 0.05%). When Ukrainian prompts were applied, Macro-F1 decreased to 63.73%; however, the U/E equaled 0%, indicating higher reliability of responses. Using English prompts with Ukrainian-language data preserved nearly the same level of accuracy (Macro-F1 = 69.66%), thereby revealing strong internal translation and generalization mechanisms. The novelty of this study is attributed to the use of a large multidomain parallel corpus, the systematic comparison of prompts in two languages, the application of the state-of-the-art model GPT-4.1-mini, and the introduction of the U/E metric as a reliability criterion. The proposed approach demonstrates the feasibility of applying GPT-4.1-mini to Ukrainian-language information services without additional training, particularly for automatic query routing in financial, medical, legal, and other domains.
- 31 October 2025
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 5 (2 (137)) , 98-106
Open AccessDetermining the effectiveness of GPT-4.1-mini for multiclass text categorization
The object of this study is the process of multiclass automatic categorization of user queries using large language models under the conditions of a language transition from English to Ukrainian. The scientific task relates to the fact that most modern large language models (LLMs) are optimized for English while their effectiveness for morphologically complex and low-resource languages, particularly Ukrainian, remains insufficiently studied. In this work, an experimental approach was devised and implemented to evaluate the transferability of the GPT-4.1-mini model from English to Ukrainian in the task to categorize 11,047 user queries spanning nine applied domains. The analysis employed conventional metrics (Recall, Precision, Weighted-F1, Macro-F1) alongside a novel indicator, the Uncertainty/Error Rate (U/E), which captures the proportion of model refusals and “hallucinations.” The findings demonstrate that the highest quality was achieved on the English dataset (Macro-F1 = 69.78%, U/E = 0.05%). When Ukrainian prompts were applied, Macro-F1 decreased to 63.73%; however, the U/E equaled 0%, indicating higher reliability of responses. Using English prompts with Ukrainian-language data preserved nearly the same level of accuracy (Macro-F1 = 69.66%), thereby revealing strong internal translation and generalization mechanisms. The novelty of this study is attributed to the use of a large multidomain parallel corpus, the systematic comparison of prompts in two languages, the application of the state-of-the-art model GPT-4.1-mini, and the introduction of the U/E metric as a reliability criterion. The proposed approach demonstrates the feasibility of applying GPT-4.1-mini to Ukrainian-language information services without additional training, particularly for automatic query routing in financial, medical, legal, and other domains.
- Open Access
- 29 September 2025
- Published by Igor Sikorsky Kyiv Polytechnic Institute in System research and information technologies
- No. 3,p. 48-59
Selection of target function in optical coatings synthesis problems
The article presents general information on the use of optical coatings in various industries and analyzes the main approaches to optimizing optical filter structures. An approach to solving a class of optical coating synthesis problems is proposed, based on the formation of a new optimization model. The primary attention is paid to the formalization and analysis of the target function. To determine the quality of the optical coating, the deviation of the spectral characteristics from the required ones was estimated using the least squares, least absolute deviation, and minimum criteria. As a result, both smooth and two non-smooth target functions are proposed and analyzed. The peculiarities of their application in solving optimization problems related to optical coating synthesis are described, and corresponding numerical experiments are presented.
- 29 September 2025
- Published by Igor Sikorsky Kyiv Polytechnic Institute in System research and information technologies
- No. 3,p. 48-59
Open AccessSelection of target function in optical coatings synthesis problems
The article presents general information on the use of optical coatings in various industries and analyzes the main approaches to optimizing optical filter structures. An approach to solving a class of optical coating synthesis problems is proposed, based on the formation of a new optimization model. The primary attention is paid to the formalization and analysis of the target function. To determine the quality of the optical coating, the deviation of the spectral characteristics from the required ones was estimated using the least squares, least absolute deviation, and minimum criteria. As a result, both smooth and two non-smooth target functions are proposed and analyzed. The peculiarities of their application in solving optimization problems related to optical coating synthesis are described, and corresponding numerical experiments are presented.
- 3 April 2025
- Published by Springer Nature
- p. 156-167
A Comparative Study of Machine Learning Algorithms and the Prompting Approach Using GPT-3.5 Turbo for Text Categorization
- 3 April 2025
- Published by Springer Nature
- p. 156-167
A Comparative Study of Machine Learning Algorithms and the Prompting Approach Using GPT-3.5 Turbo for Text Categorization
- Open Access
- 28 July 2023
- Published by V.M. Glushkov Institute of Cybernetics in Cybernetics and Computer Technologies
- No. 2,p. 32-45
On the Improvement of the Heuristic Algorithm for Packing Circles into a Circle of Minimum Radius
The article is devoted to investigation of a heuristic algorithm for solving the competitive problem "Circles Dense packing into a circle of minimum radius" and development of its improved version using Shor's r-algorithm with step dichotomy. The heuristic algorithm was developed by Bohdan Zadorozhnyi, a third-year student of Uzhhorod National University. The program implemented on its basis took second place in the competition and used less time than the maximum time, which, according to the competition, was allocated for a one-time launch of the program for 50 competitive tasks. The article describes the research results of how the Shor r-algorithm can be used to improve efficiency of the heuristic algorithm. The algorithm for improving the heuristic solution is implemented according to the following scheme. We start from the best arrangement of circles found by the heuristic algorithm. Then, we perform the following four stages of the algorithm: Stage 1. We set a rather large value of the initial step (we determine it depending on the input data or simply choose it as a large step); Stage 2. We run the r-algorithm from the starting point and find the local minimum of the corresponding nonlinear programming problem; Stage 3. If the local minimum found guarantees a smaller radius of the outer circle, then the local minimum point becomes the starting point; the local minimum found does not guarantee a smaller radius of the outer circle, then the size of the step h is reduced by half. Stage 4. If the step value is greater than the specified value, then we proceed to Stage 2. Otherwise, we finish work of the algorithm with solution improvement. Python 3.9.5 programming language and NumPy 1.24.2 library were used for software implementation of both algorithms. For 50 competitive tests and different number of iterations of the heuristic algorithm (10, 20, 30, 40 and 50 iterations), the analysis of the obtained results was conducted according to three parameters: the number of points obtained, program execution time and the number of exchanges of circles in one iteration of the heuristic algorithm. For most of the competitive tests, the refined algorithm allows you to get better results in points, in particular, in most cases the improvement is up to 2 points, and in some cases – from 3 to 6 points. The biggest improvements (6 points) are seen in tests, where the circles have the same or close radii. Here, the heuristic algorithm works not so effectively, therefore, for such tests, due to the algorithm with refinement, it is possible to significantly improve the results of competitive tasks in terms of points.
- 28 July 2023
- Published by V.M. Glushkov Institute of Cybernetics in Cybernetics and Computer Technologies
- No. 2,p. 32-45
Open AccessOn the Improvement of the Heuristic Algorithm for Packing Circles into a Circle of Minimum Radius
The article is devoted to investigation of a heuristic algorithm for solving the competitive problem "Circles Dense packing into a circle of minimum radius" and development of its improved version using Shor's r-algorithm with step dichotomy. The heuristic algorithm was developed by Bohdan Zadorozhnyi, a third-year student of Uzhhorod National University. The program implemented on its basis took second place in the competition and used less time than the maximum time, which, according to the competition, was allocated for a one-time launch of the program for 50 competitive tasks. The article describes the research results of how the Shor r-algorithm can be used to improve efficiency of the heuristic algorithm. The algorithm for improving the heuristic solution is implemented according to the following scheme. We start from the best arrangement of circles found by the heuristic algorithm. Then, we perform the following four stages of the algorithm: Stage 1. We set a rather large value of the initial step (we determine it depending on the input data or simply choose it as a large step); Stage 2. We run the r-algorithm from the starting point and find the local minimum of the corresponding nonlinear programming problem; Stage 3. If the local minimum found guarantees a smaller radius of the outer circle, then the local minimum point becomes the starting point; the local minimum found does not guarantee a smaller radius of the outer circle, then the size of the step h is reduced by half. Stage 4. If the step value is greater than the specified value, then we proceed to Stage 2. Otherwise, we finish work of the algorithm with solution improvement. Python 3.9.5 programming language and NumPy 1.24.2 library were used for software implementation of both algorithms. For 50 competitive tests and different number of iterations of the heuristic algorithm (10, 20, 30, 40 and 50 iterations), the analysis of the obtained results was conducted according to three parameters: the number of points obtained, program execution time and the number of exchanges of circles in one iteration of the heuristic algorithm. For most of the competitive tests, the refined algorithm allows you to get better results in points, in particular, in most cases the improvement is up to 2 points, and in some cases – from 3 to 6 points. The biggest improvements (6 points) are seen in tests, where the circles have the same or close radii. Here, the heuristic algorithm works not so effectively, therefore, for such tests, due to the algorithm with refinement, it is possible to significantly improve the results of competitive tasks in terms of points.
- 4 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 226-231
Ethnocultural, Educational and Scientific Potential of the Interactive Dialects Map
The article analyzes the features of an interactive map of dialects developed by Ukrainian scientists and available on the Internet at dialectmap.org. The client part of the interactive map was created using the React.js library of the JavaScript programming language, and the MOBX state management library was also used. The server side of the information system was written in Ruby programming language using the Ruby on Rails framework. The relational database management system Postgresql was used, and Redis cache was used for caching some frequently used data. Ukrainian universities successfully use the interactive map of dialects to conduct dialectological and ethnolinguistic practices, teach linguistic disciplines, and organize students' research work within linguistic clubs. The information system is a hub that more widely reflects local language features; the map contains materials from various studies created in different periods. The interactive map of dialects has more features than traditional (paper) dialectological atlases, makes the results of dialectological surveys accessible to many people, can hold a large amount of dialect data, and thus contributes to the preservation of linguistic diversity. The interactive map of dialects is developed to represent data from different languages and territories; thus, the project can be expanded to other countries in Europe, Asia, and other continents.
- 4 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 226-231
Ethnocultural, Educational and Scientific Potential of the Interactive Dialects Map
The article analyzes the features of an interactive map of dialects developed by Ukrainian scientists and available on the Internet at dialectmap.org. The client part of the interactive map was created using the React.js library of the JavaScript programming language, and the MOBX state management library was also used. The server side of the information system was written in Ruby programming language using the Ruby on Rails framework. The relational database management system Postgresql was used, and Redis cache was used for caching some frequently used data. Ukrainian universities successfully use the interactive map of dialects to conduct dialectological and ethnolinguistic practices, teach linguistic disciplines, and organize students' research work within linguistic clubs. The information system is a hub that more widely reflects local language features; the map contains materials from various studies created in different periods. The interactive map of dialects has more features than traditional (paper) dialectological atlases, makes the results of dialectological surveys accessible to many people, can hold a large amount of dialect data, and thus contributes to the preservation of linguistic diversity. The interactive map of dialects is developed to represent data from different languages and territories; thus, the project can be expanded to other countries in Europe, Asia, and other continents.
- Open Access
- 30 September 2022
- Published by Department of Informatics and Cybernetics of Melitopol Bohdan Khmelnytsky State Pedagogical University in Ukrainian Journal of Educational Studies and Information Technology
- Vol. 10 (3) , 1-12
Acceleration of software execution time for operations involving sequences or matrices
The article describes three methods for lowering program runtime that are solutions to computer science Olympiad problems involving sequences or matrices. The first method relies on the representation of some sequences as matrices, after which the program for calculating the sequence's members will have asymptotics equivalent to the exponentiation algorithm's time complexity and be O(log (n)). The second strategy is to improve the existing code in order to significantly shorten program runtime. For scientists who create code for scientific inquiries and deal with matrix multiplication operations, understanding this approach is crucial. The author's challenge is presented and solved using the third strategy, which is based on minimizing temporal complexity by looking for regularities.
- 30 September 2022
- Published by Department of Informatics and Cybernetics of Melitopol Bohdan Khmelnytsky State Pedagogical University in Ukrainian Journal of Educational Studies and Information Technology
- Vol. 10 (3) , 1-12
Open AccessAcceleration of software execution time for operations involving sequences or matrices
The article describes three methods for lowering program runtime that are solutions to computer science Olympiad problems involving sequences or matrices. The first method relies on the representation of some sequences as matrices, after which the program for calculating the sequence's members will have asymptotics equivalent to the exponentiation algorithm's time complexity and be O(log (n)). The second strategy is to improve the existing code in order to significantly shorten program runtime. For scientists who create code for scientific inquiries and deal with matrix multiplication operations, understanding this approach is crucial. The author's challenge is presented and solved using the third strategy, which is based on minimizing temporal complexity by looking for regularities.
- Open Access
- 29 April 2022
- Published by Institute for Digitalisation of Education of the National Academy of Educational Sciences of Ukraine in Information Technologies and Learning Tools
- Vol. 88 (2) , 126-138
ІНТЕРАКТИВНА КАРТА ДІАЛЕКТІВ ЯК ІНСТРУМЕНТ ФАХОВОЇ ПІДГОТОВКИ СТУДЕНТІВ ФІЛОЛОГІЧНИХ СПЕЦІАЛЬНОСТЕЙ
У статті репрезентовано інноваційну технологічну розробку науковців Ужгородського національного університету (інтерактивна карта діалектів), упровадження якої в навчальний процес для філологічних спеціальностей дає можливість оптимізувати навчальну й наукову роботу студентів, особливо в умовах дистанційного та змішаного навчання. Створений зусиллями фахівців у сфері інформаційних технологій програмний продукт, контент якого наповнюють лінгвісти, дає можливість користувачам вводити діалектний матеріал (дані друкованих діалектологічних атласів, словників, а також самостійно зібраний у польових умовах) до бази даних, представляючи його в потрібних для вивчення української мови аспектах. Такий інноваційний спосіб фіксації мовних даних оптимізує процеси дослідження особливостей українських діалектів та спрощує рутинні процедури зі збирання, накопичення й аналізу емпіричного матеріалу, що становить значний інтерес для мовознавства, історії, археології, етнографії та етнології, культурології, а також для інших науково-навчальних галузей, пов’язаних з дослідженням і вивченням історії та сучасного стану матеріальної й духовної культури етносів, українського зокрема. Крім міждисциплінарного використання як у навчальному процесі вищої школи, так і в дослідницькому аспекті, перевага розробленого програмного продукту - у можливості його різновекторного масштабування: оскільки потенційно проєкт розрахований не тільки на Україну й українську мову, а й на інші держави й мови, то під час додавання слова доступний вибір країни (на час написання цієї статті доступні Україна та Угорщина). Унікальність розробки полягає в тому, що вона слугує передусім навчально-науковим інструментом, який добре інтегрує дослідницький потенціал студентів-айтівців (виступають розробниками програмного продукту) та студентів-філологів (його перші тестувальники й наповнювачі контенту). Така синергійна діяльність під час підготовки на перший погляд різновекторних фахівців дає результат, який може бути цікавим для студентів й інших напрямків підготовки (майбутніх істориків, культурологів, туризмознавців тощо).
- 29 April 2022
- Published by Institute for Digitalisation of Education of the National Academy of Educational Sciences of Ukraine in Information Technologies and Learning Tools
- Vol. 88 (2) , 126-138
Open AccessІНТЕРАКТИВНА КАРТА ДІАЛЕКТІВ ЯК ІНСТРУМЕНТ ФАХОВОЇ ПІДГОТОВКИ СТУДЕНТІВ ФІЛОЛОГІЧНИХ СПЕЦІАЛЬНОСТЕЙ
У статті репрезентовано інноваційну технологічну розробку науковців Ужгородського національного університету (інтерактивна карта діалектів), упровадження якої в навчальний процес для філологічних спеціальностей дає можливість оптимізувати навчальну й наукову роботу студентів, особливо в умовах дистанційного та змішаного навчання. Створений зусиллями фахівців у сфері інформаційних технологій програмний продукт, контент якого наповнюють лінгвісти, дає можливість користувачам вводити діалектний матеріал (дані друкованих діалектологічних атласів, словників, а також самостійно зібраний у польових умовах) до бази даних, представляючи його в потрібних для вивчення української мови аспектах. Такий інноваційний спосіб фіксації мовних даних оптимізує процеси дослідження особливостей українських діалектів та спрощує рутинні процедури зі збирання, накопичення й аналізу емпіричного матеріалу, що становить значний інтерес для мовознавства, історії, археології, етнографії та етнології, культурології, а також для інших науково-навчальних галузей, пов’язаних з дослідженням і вивченням історії та сучасного стану матеріальної й духовної культури етносів, українського зокрема. Крім міждисциплінарного використання як у навчальному процесі вищої школи, так і в дослідницькому аспекті, перевага розробленого програмного продукту - у можливості його різновекторного масштабування: оскільки потенційно проєкт розрахований не тільки на Україну й українську мову, а й на інші держави й мови, то під час додавання слова доступний вибір країни (на час написання цієї статті доступні Україна та Угорщина). Унікальність розробки полягає в тому, що вона слугує передусім навчально-науковим інструментом, який добре інтегрує дослідницький потенціал студентів-айтівців (виступають розробниками програмного продукту) та студентів-філологів (його перші тестувальники й наповнювачі контенту). Така синергійна діяльність під час підготовки на перший погляд різновекторних фахівців дає результат, який може бути цікавим для студентів й інших напрямків підготовки (майбутніх істориків, культурологів, туризмознавців тощо).