Irina Zeleneva
Irina Zeleneva has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
Tetiana Holub
4 shared publications- Anzhelika Parkhomenko
National University Zaporizhzhia Polytechnic
3 shared publications Svitlana Hrushko
3 shared publications- Danylo Kotelevskyi2 shared publications
- Galyna Tabunshchyk
Fachhochschule Dortmund
2 shared publications - Sergei A. Subbotin
Plant Pest Diagnostic Center, https://dx.doi.org/11144California Department of Food and Agriculture, 3294 Meadowview Road, Sacramento, CA 95832, USA
2 shared publications
Latest Publications
- 1 April 2026
- Published by Springer Nature
- p. 198-205
An Integrated Approach to Designing and Testing Digital Twins in Teaching IT Students
- 1 April 2026
- Published by Springer Nature
- p. 198-205
An Integrated Approach to Designing and Testing Digital Twins in Teaching IT Students
- 15 January 2026
- Published by Donetsk National Technical University in Problems of Modeling and Design Automatization
- Vol. 1 (23)
HARDWARE IMPLEMENTATION OF AN FPGA-BASED EDUCATIONAL DATA VERIFICATION SYSTEM
This article presents the development and implementation of a field-programmable gate array (FPGA)-based assessment verification system to ensure the integrity of academic data in the context of digitalization of the educational process. A modular architecture is proposed, using the Jenkins hash function as a training example, ensuring rapid data verification with minimal resource consumption. The proposed training system features a distributed architecture with multiple FPGA nodes networked to a central routing server, enabling students to learn the principles of building scalable data processing systems. The developed system is intended for educational purposes and to demonstrate the principles of hardware implementation of hashing algorithms. Keywords: FPGA, data verification, hashing, data integrity, Cyclone V, training platform.
- 15 January 2026
- Published by Donetsk National Technical University in Problems of Modeling and Design Automatization
- Vol. 1 (23)
HARDWARE IMPLEMENTATION OF AN FPGA-BASED EDUCATIONAL DATA VERIFICATION SYSTEM
This article presents the development and implementation of a field-programmable gate array (FPGA)-based assessment verification system to ensure the integrity of academic data in the context of digitalization of the educational process. A modular architecture is proposed, using the Jenkins hash function as a training example, ensuring rapid data verification with minimal resource consumption. The proposed training system features a distributed architecture with multiple FPGA nodes networked to a central routing server, enabling students to learn the principles of building scalable data processing systems. The developed system is intended for educational purposes and to demonstrate the principles of hardware implementation of hashing algorithms. Keywords: FPGA, data verification, hashing, data integrity, Cyclone V, training platform.
- 1 January 2026
- Published by Donetsk National Technical University in Scientific papers of Donetsk National Technical University. Series: Informatics, Cybernetics and Computer Science
- Vol. 2 (43)
ADVISORY AI-BASED VHDL CODE VERIFICATION SYSTEM FOR IT STUDENTS
An AI-based advisory system for VHDL code verification presents an approach to minimizing errors and increasing the reliability of digital circuit designs on FPGAs. This task is relevant because the current stage of digital electronics development is characterized by the rapid growth in the complexity of FPGA designs, and the logic capacity of microchips is growing much faster than developer productivity and the effectiveness of traditional code verification tools. At the same time, AI tools, particularly LLM, are rapidly evolving. Education, especially when training IT students, must adapt to these new conditions. The proposed advisory system enables the correct selection of LLM tools for VHDL code verification and provides explanations for detected errors. This helps students improve their understanding of the task, enhance the quality of their designs, and ultimately increase motivation. The system is scalable and flexible and can be used for both undergraduate and aspiring digital hardware designers.
- 1 January 2026
- Published by Donetsk National Technical University in Scientific papers of Donetsk National Technical University. Series: Informatics, Cybernetics and Computer Science
- Vol. 2 (43)
ADVISORY AI-BASED VHDL CODE VERIFICATION SYSTEM FOR IT STUDENTS
An AI-based advisory system for VHDL code verification presents an approach to minimizing errors and increasing the reliability of digital circuit designs on FPGAs. This task is relevant because the current stage of digital electronics development is characterized by the rapid growth in the complexity of FPGA designs, and the logic capacity of microchips is growing much faster than developer productivity and the effectiveness of traditional code verification tools. At the same time, AI tools, particularly LLM, are rapidly evolving. Education, especially when training IT students, must adapt to these new conditions. The proposed advisory system enables the correct selection of LLM tools for VHDL code verification and provides explanations for detected errors. This helps students improve their understanding of the task, enhance the quality of their designs, and ultimately increase motivation. The system is scalable and flexible and can be used for both undergraduate and aspiring digital hardware designers.
- 1 January 2026
- Published by Donetsk National Technical University in Scientific papers of Donetsk National Technical University. Series: Informatics, Cybernetics and Computer Science
- Vol. 1 (42)
VERIFICATION OF VHDL CODE USING LARGE LANGUAGE MODELS: COMPARATIVE ANALYSIS AND SOFTWARE IMPLEMENTATION
Current trends in hardware resource scaling create a fundamental industry problem – the so-called "verification gap." This article analyzes the potential of generative AI in the context of digital circuit design for improving code verification in hardware description languages. Thanks to the self-attention mechanism based on the Transformer architecture, large language models are capable of analyzing complex dependencies between code elements. This problem is particularly relevant in the context of using the VHDL hardware description language. Unlike Verilog or SystemVerilog, which have a more concise C-like syntax, VHDL is characterized by strong typing, verbosity, and rigid syntactic constructs. The object of this study is the process of automated verification of VHDL code using large language models. A comparative analysis of nine modern LLMs is conducted based on accuracy, performance, and cost criteria, and an appropriate experimental research method is proposed, including the development of a unified prompt and normalization of the obtained data. The English language is substantiated and defined as a unified standard for both the user interface and system prompts and internal code generation. A specialized dataset consisting of 25 test cases was developed during the study. Each case contains a VHDL file with a pre-introduced error (or reference-correct code) and a corresponding JSON file describing the expected result. A test dataset with error distribution by category was generated, and correct test files were used to identify possible false positives, facilitating comprehensive verification of AI models. To correctly process input data by different LLMs, a normalization algorithm using an "arbiter model" was developed. The study solved a pressing scientific and applied problem of increasing the efficiency of FPGA design verification through the informed selection of optimal large language models. The proposed LLM analysis algorithm can conceptually be applied to other hardware description languages. Practical application is possible in digital system design, as well as in the educational process of training IT specialists. The most promising direction for further research is the integration of RAG (Retrieval-Augmented Generation) technology. This will allow for supplementing the technical documentation (datasheets) of specific FPGA architectures, taking into account current families.
- 1 January 2026
- Published by Donetsk National Technical University in Scientific papers of Donetsk National Technical University. Series: Informatics, Cybernetics and Computer Science
- Vol. 1 (42)
VERIFICATION OF VHDL CODE USING LARGE LANGUAGE MODELS: COMPARATIVE ANALYSIS AND SOFTWARE IMPLEMENTATION
Current trends in hardware resource scaling create a fundamental industry problem – the so-called "verification gap." This article analyzes the potential of generative AI in the context of digital circuit design for improving code verification in hardware description languages. Thanks to the self-attention mechanism based on the Transformer architecture, large language models are capable of analyzing complex dependencies between code elements. This problem is particularly relevant in the context of using the VHDL hardware description language. Unlike Verilog or SystemVerilog, which have a more concise C-like syntax, VHDL is characterized by strong typing, verbosity, and rigid syntactic constructs. The object of this study is the process of automated verification of VHDL code using large language models. A comparative analysis of nine modern LLMs is conducted based on accuracy, performance, and cost criteria, and an appropriate experimental research method is proposed, including the development of a unified prompt and normalization of the obtained data. The English language is substantiated and defined as a unified standard for both the user interface and system prompts and internal code generation. A specialized dataset consisting of 25 test cases was developed during the study. Each case contains a VHDL file with a pre-introduced error (or reference-correct code) and a corresponding JSON file describing the expected result. A test dataset with error distribution by category was generated, and correct test files were used to identify possible false positives, facilitating comprehensive verification of AI models. To correctly process input data by different LLMs, a normalization algorithm using an "arbiter model" was developed. The study solved a pressing scientific and applied problem of increasing the efficiency of FPGA design verification through the informed selection of optimal large language models. The proposed LLM analysis algorithm can conceptually be applied to other hardware description languages. Practical application is possible in digital system design, as well as in the educational process of training IT specialists. The most promising direction for further research is the integration of RAG (Retrieval-Augmented Generation) technology. This will allow for supplementing the technical documentation (datasheets) of specific FPGA architectures, taking into account current families.
- 23 March 2025
- Published by Springer Nature
- p. 377-384
Challenges and Approaches to the Artificial Intelligence in Education
- 23 March 2025
- Published by Springer Nature
- p. 377-384
Challenges and Approaches to the Artificial Intelligence in Education
- 1 February 2024
- Published by Springer Nature
- p. 247-254
Framework for the Online Education with the Distributed Educational Resources
- 1 February 2024
- Published by Springer Nature
- p. 247-254
Framework for the Online Education with the Distributed Educational Resources
- 1 January 2021
- Published by Theoretical and Applied Aspects of Device Development on Microcontrollers and FPGAs
- p. 13-14
FPGA Implementation of Floating-Point Significand Multiplier
?Development of high-performance computational devices needs fast methods of operations with numbers which are presented in floating-point format. One of the most common approaches to build a significand multiplier is using a Wallace CSA-adder tree structure which shows good performance in adding partial sums. Significand multiplier was implemented in FPGA as a part of floating-point multiplier which works with single precision numbers in IEEE754 standard. Keywords?multiplier, floating-point number, carry-save adder, FPGA
- 1 January 2021
- Published by Theoretical and Applied Aspects of Device Development on Microcontrollers and FPGAs
- p. 13-14
FPGA Implementation of Floating-Point Significand Multiplier
?Development of high-performance computational devices needs fast methods of operations with numbers which are presented in floating-point format. One of the most common approaches to build a significand multiplier is using a Wallace CSA-adder tree structure which shows good performance in adding partial sums. Significand multiplier was implemented in FPGA as a part of floating-point multiplier which works with single precision numbers in IEEE754 standard. Keywords?multiplier, floating-point number, carry-save adder, FPGA