Zinnur M. Gizatullin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zinnur M. Gizatullin has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
R. M. Gizatullin
Kazan National Research Technical University named after A.N. Tupolev—KAI, Kazan, Russia
6 shared publicationsM. G. Nuriev
Kazan National Research Technical University named after A.N. Tupolev—KAI, Kazan, Russia
4 shared publicationsR.R. Mubarakov
4 shared publicationsM. P. Shleimovich
Tupolev Kazan National Research Technical University, Kazan, Russia
3 shared publicationsI.D. Fatykhov
Kazan National Research Technical University named after A.N. Tupolev-KAI, 420111, Russia, Kazan, Karl Marx str., 10
2 shared publications- Maksim S. Shkinderov
Kazan National Research Technical University named after A.N. Tupolev-KAI,Department of Computer Aided Design Systems,Kazan,Russian Federation
2 shared publications
Latest Publications
- 1 April 2026
- Published by Kotelnikov Institute of Radioengineering and Electronics of Russian Academy of Sciences in Journal of Radio Electronics
- Vol. 2026 (4)
Neural network simulation of electromagnetic radiation from electronic computing devices
The relevance of research electromagnetic radiation from electronic computing devices is dictated by aspects of biological safety, information security, and electromagnetic compatibility. The use of artificial neural networks to study electromagnetic radiation represents a transition from classical deterministic models to data mining, which has certain advantages over analytical approaches and physical measurements. The practical technique for constructing a nonlinear approximating function of electromagnetic radiation from electronic computing devices using neural network simulation based on physical measurement data at discrete frequencies this article proposes. Personal computers are considered as electronic computing devices. To demonstrate the feasibility of using this tool, a test experimental setup for preparing training and test data was created. The mean absolute percentage error is used to evaluate the quality of the problem solution for the test set. Training was performed over 220 epochs, and the mean absolute percentage error for the test set was 22%. Examples of predicting electromagnetic radiation intensity using a trained neural network are provided. The obtained results demonstrate the capabilities of neural network simulation in solving electromagnetic compatibility problems.
- 1 April 2026
- Published by Kotelnikov Institute of Radioengineering and Electronics of Russian Academy of Sciences in Journal of Radio Electronics
- Vol. 2026 (4)
Neural network simulation of electromagnetic radiation from electronic computing devices
The relevance of research electromagnetic radiation from electronic computing devices is dictated by aspects of biological safety, information security, and electromagnetic compatibility. The use of artificial neural networks to study electromagnetic radiation represents a transition from classical deterministic models to data mining, which has certain advantages over analytical approaches and physical measurements. The practical technique for constructing a nonlinear approximating function of electromagnetic radiation from electronic computing devices using neural network simulation based on physical measurement data at discrete frequencies this article proposes. Personal computers are considered as electronic computing devices. To demonstrate the feasibility of using this tool, a test experimental setup for preparing training and test data was created. The mean absolute percentage error is used to evaluate the quality of the problem solution for the test set. Training was performed over 220 epochs, and the mean absolute percentage error for the test set was 22%. Examples of predicting electromagnetic radiation intensity using a trained neural network are provided. The obtained results demonstrate the capabilities of neural network simulation in solving electromagnetic compatibility problems.
- 12 December 2025
- Published by YUR-VAK in Computational nanotechnology
- Vol. 12 (4) , 13-19
Triplet-based knowledge mining using pretrained large language models
Extracting structured information from text is a key task in natural language processing. Large language models for information extraction tasks achieve high accuracy thanks to pre-training on huge volumes of data. However, such models require significant computational resources and are unavailable for local use due to their dependence on cloud infrastructure. Therefore, compact, open-source large language models that can be retrained locally are increasingly being used to address this problem. This paper evaluates the effectiveness of retraining compact large language models for automated triplet information extraction from unstructured text. The Mistral model with seven billion parameters was used in the study. The model was fine-tuned on a custom dataset consisting of 650 examples, each containing an instruction, an input text and an expected output. The results confirm the effectiveness of retraining: the F1-score increased several-fold compared to the baseline model. The retrained version of the model demonstrates competitiveness with the large-scale DeepSeek language model with 685 billion parameters. The obtained results highlight the potential of compact open large language models for knowledge extraction tasks under resource constraints, such as knowledge graph construction.
- 12 December 2025
- Published by YUR-VAK in Computational nanotechnology
- Vol. 12 (4) , 13-19
Triplet-based knowledge mining using pretrained large language models
Extracting structured information from text is a key task in natural language processing. Large language models for information extraction tasks achieve high accuracy thanks to pre-training on huge volumes of data. However, such models require significant computational resources and are unavailable for local use due to their dependence on cloud infrastructure. Therefore, compact, open-source large language models that can be retrained locally are increasingly being used to address this problem. This paper evaluates the effectiveness of retraining compact large language models for automated triplet information extraction from unstructured text. The Mistral model with seven billion parameters was used in the study. The model was fine-tuned on a custom dataset consisting of 650 examples, each containing an instruction, an input text and an expected output. The results confirm the effectiveness of retraining: the F1-score increased several-fold compared to the baseline model. The retrained version of the model demonstrates competitiveness with the large-scale DeepSeek language model with 685 billion parameters. The obtained results highlight the potential of compact open large language models for knowledge extraction tasks under resource constraints, such as knowledge graph construction.
- 1 August 2025
- Published by Kotelnikov Institute of Radioengineering and Electronics of Russian Academy of Sciences in Journal of Radio Electronics
- Vol. 2025 (8)
Prediction of spurious electromagnetic emission from an electric power converter using an artificial neural network
Spurious electromagnetic emission arising during operation of power converters can create a significant problem of electromagnetic compatibility for components of complex electronic systems. Therefore, when designing electronic systems, it is necessary to estimate the possible parameters of such emission in advance and, if necessary, take protective measures in advance. Existing approaches to predicting electromagnetic emission often do not allow to fully take into account explicit and implicit electromagnetic processes in power converters and in the operating environment. The article implements a practical technique for predicting the intensity of spurious electromagnetic emission from power converters using an artificial neural network. To demonstrate the possibility of using this tool, an experimental stand for preparing training and test data was created. An example of training an artificial neural network based on experimental data for 100 epochs is given. For the test sample, the average absolute percentage error is no more than 11 %. Examples of predicting the intensity of spurious electromagnetic emission from an electric power converter using a trained neural network are given. Prospects for using this tool are seen in the tasks of predicting electromagnetic interference along power lines, etc.
- 1 August 2025
- Published by Kotelnikov Institute of Radioengineering and Electronics of Russian Academy of Sciences in Journal of Radio Electronics
- Vol. 2025 (8)
Prediction of spurious electromagnetic emission from an electric power converter using an artificial neural network
Spurious electromagnetic emission arising during operation of power converters can create a significant problem of electromagnetic compatibility for components of complex electronic systems. Therefore, when designing electronic systems, it is necessary to estimate the possible parameters of such emission in advance and, if necessary, take protective measures in advance. Existing approaches to predicting electromagnetic emission often do not allow to fully take into account explicit and implicit electromagnetic processes in power converters and in the operating environment. The article implements a practical technique for predicting the intensity of spurious electromagnetic emission from power converters using an artificial neural network. To demonstrate the possibility of using this tool, an experimental stand for preparing training and test data was created. An example of training an artificial neural network based on experimental data for 100 epochs is given. For the test sample, the average absolute percentage error is no more than 11 %. Examples of predicting the intensity of spurious electromagnetic emission from an electric power converter using a trained neural network are given. Prospects for using this tool are seen in the tasks of predicting electromagnetic interference along power lines, etc.
- 1 April 2025
- Published by Kotelnikov Institute of Radioengineering and Electronics of Russian Academy of Sciences in Journal of Radio Electronics
- Vol. 2025 (4)
Prediction of conductive interference from electric power converter using artificial neural network
Conductive interference occurs during operation of power converters and is a significant problem for complex electronic systems. Therefore, when designing electronic systems, it is necessary to evaluate the possible parameters of such interference in advance and take protection measures. The article proposes a practical technique for predicting the amplitude and duration of conductive interference from electricity converters using an artificial neural network. As an example, an experimental study of the parameters of conductive interference from the layout of the electricity generation system on board the aircraft was implemented. A data set for teaching a neural network has been prepared. Examples of training of an artificial neural network based on experimental data are given. For the maximum amplitude and duration of conductive interference, an acceptable divergence of the results is achieved at 795 and 1422 of the training era, respectively. For test sample, it was possible to achieve an average absolute percentage error 14.2 % and 20.3 %, to predict the amplitude and duration of conductive interference. Examples of forecasting the parameters of conductive interference using a trained neural network are given. The results obtained indicate the possibility of practical use of an artificial neural network to solve the tasks of predicting conductive interference. Further prospects for using this tool are seen in the tasks of forecasting side -by -power electromagnetic radiation from electronic devices, exposure to ultra -short pulses, etc.
- 1 April 2025
- Published by Kotelnikov Institute of Radioengineering and Electronics of Russian Academy of Sciences in Journal of Radio Electronics
- Vol. 2025 (4)
Prediction of conductive interference from electric power converter using artificial neural network
Conductive interference occurs during operation of power converters and is a significant problem for complex electronic systems. Therefore, when designing electronic systems, it is necessary to evaluate the possible parameters of such interference in advance and take protection measures. The article proposes a practical technique for predicting the amplitude and duration of conductive interference from electricity converters using an artificial neural network. As an example, an experimental study of the parameters of conductive interference from the layout of the electricity generation system on board the aircraft was implemented. A data set for teaching a neural network has been prepared. Examples of training of an artificial neural network based on experimental data are given. For the maximum amplitude and duration of conductive interference, an acceptable divergence of the results is achieved at 795 and 1422 of the training era, respectively. For test sample, it was possible to achieve an average absolute percentage error 14.2 % and 20.3 %, to predict the amplitude and duration of conductive interference. Examples of forecasting the parameters of conductive interference using a trained neural network are given. The results obtained indicate the possibility of practical use of an artificial neural network to solve the tasks of predicting conductive interference. Further prospects for using this tool are seen in the tasks of forecasting side -by -power electromagnetic radiation from electronic devices, exposure to ultra -short pulses, etc.
- 1 August 2024
- Published by Kotelnikov Institute of Radioengineering and Electronics of Russian Academy of Sciences in Journal of Radio Electronics
- Vol. 2024 (8)
Predicting the magnitude of electrostatic discharge interference in an electronic device using an artificial neural network
Electrostatic discharge is a dangerous source of natural electromagnetic interference to the operation of modern electronic devices. Although measures have been taken to reduce and remove electrostatic discharge from the operating area of electronic devices, the absence of such discharge cannot be guaranteed. Therefore, when designing modern electronic devices, it is necessary to take into account the possibility of such electrostatic discharges in advance and take protective measures. The article proposes a method for predicting the amplitude of interference in the communication line of an electronic device when exposed to an electrostatic discharge on its metal case. The technique is based on the use of an artificial neural network. The technique includes the analysis of significant input parameters that affect the amount of interference in an electronic device; development of an experimental stand for measuring interference; choosing the structure and parameters of a neural network for predicting interference; choosing a training method for an artificial neural network; choosing a metric for assessing the quality of training; normalization of training data; training an artificial neural network using experimental noise data; predicting the amplitude of interference in the communication line of an electronic device when exposed to an electrostatic discharge on its body; where necessary, selecting and implementing electrostatic discharge protection measures. Examples of training an artificial neural network based on experimental data are given. The training was carried out for 572 epochs. For the training and testing sets, the discrepancy between the predicted data and the average measured noise values was 3.61% and 3.95%, respectively. Examples are given of predicting the amplitude of interference when exposed to electrostatic discharge. The results obtained indicate the possibility of practical use of an artificial neural network to solve problems of electromagnetic interference analysis.
- 1 August 2024
- Published by Kotelnikov Institute of Radioengineering and Electronics of Russian Academy of Sciences in Journal of Radio Electronics
- Vol. 2024 (8)
Predicting the magnitude of electrostatic discharge interference in an electronic device using an artificial neural network
Electrostatic discharge is a dangerous source of natural electromagnetic interference to the operation of modern electronic devices. Although measures have been taken to reduce and remove electrostatic discharge from the operating area of electronic devices, the absence of such discharge cannot be guaranteed. Therefore, when designing modern electronic devices, it is necessary to take into account the possibility of such electrostatic discharges in advance and take protective measures. The article proposes a method for predicting the amplitude of interference in the communication line of an electronic device when exposed to an electrostatic discharge on its metal case. The technique is based on the use of an artificial neural network. The technique includes the analysis of significant input parameters that affect the amount of interference in an electronic device; development of an experimental stand for measuring interference; choosing the structure and parameters of a neural network for predicting interference; choosing a training method for an artificial neural network; choosing a metric for assessing the quality of training; normalization of training data; training an artificial neural network using experimental noise data; predicting the amplitude of interference in the communication line of an electronic device when exposed to an electrostatic discharge on its body; where necessary, selecting and implementing electrostatic discharge protection measures. Examples of training an artificial neural network based on experimental data are given. The training was carried out for 572 epochs. For the training and testing sets, the discrepancy between the predicted data and the average measured noise values was 3.61% and 3.95%, respectively. Examples are given of predicting the amplitude of interference when exposed to electrostatic discharge. The results obtained indicate the possibility of practical use of an artificial neural network to solve problems of electromagnetic interference analysis.
- 1 August 2023
- Published by Allerton Press in Russian Aeronautics (Iz VUZ)
- Vol. 66 (3) , 596-604
Research of the Radiated Electromagnetic Interference from Power Devices of the Aircraft under Modernization
A technique and tools for research of radiated interference from power devices of the aircraft at the stage of modernization are proposed. A test bench wit
- 1 August 2023
- Published by Allerton Press in Russian Aeronautics (Iz VUZ)
- Vol. 66 (3) , 596-604
Research of the Radiated Electromagnetic Interference from Power Devices of the Aircraft under Modernization
A technique and tools for research of radiated interference from power devices of the aircraft at the stage of modernization are proposed. A test bench wit
- 1 January 2023
- Published by Allerton Press in Russian Aeronautics (Iz VUZ)
- Vol. 66 (1) , 154-161
A Technique for Research of the Conducted Interferences from Power Devices of the Aircraft under Modernization
A technique for research of conducted interferences from power devices of the aircraft at the stage of modernization is proposed. The technique makes it po
- 1 January 2023
- Published by Allerton Press in Russian Aeronautics (Iz VUZ)
- Vol. 66 (1) , 154-161
A Technique for Research of the Conducted Interferences from Power Devices of the Aircraft under Modernization
A technique for research of conducted interferences from power devices of the aircraft at the stage of modernization is proposed. The technique makes it po
- 1 July 2021
- Published by Allerton Press in Russian Aeronautics (Iz VUZ)
- Vol. 64 (3) , 554-561
Analysis of Noise Immunity of the UAV Onboard Control System Based on Physical Modeling of Induced Interference
The probability of a malfunction in the operation of the onboard control system of an unmanned aerial vehicle under the influence of induced interference f
- 1 July 2021
- Published by Allerton Press in Russian Aeronautics (Iz VUZ)
- Vol. 64 (3) , 554-561
Analysis of Noise Immunity of the UAV Onboard Control System Based on Physical Modeling of Induced Interference
The probability of a malfunction in the operation of the onboard control system of an unmanned aerial vehicle under the influence of induced interference f