Vadim Ziyadinov

Dr. Vadim Ziyadinov

Moscow Technical University of Communication and Informatics, Moscow, Moskva, Russia
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 February 2022 in Sensors
Verified
Journal Article
Open access
PDF file
VZVadim Ziyadinov
Vadim Ziyadinov
Maxim V. TereshonokMaxim V. Tereshonok
Maxim V. Tereshonok
The problem surrounding convolutional neural network robustness and noise immunity is currently of great interest. In this paper, we propose a technique that involves robustness estimation and stability improvement. We also examined the noise immunity of convolutional neural networks and estimated the influence of uncertainty in the training and testing datasets on recognition probability. For this purpose, we estimated the recognition accuracies of multiple datasets with different uncertainties; we analyzed these data and provided the dependence of recognition accuracy on the training dataset uncertainty. We hypothesized and proved the existence of an optimal (in terms of recognition accuracy) amount of uncertainty in the training data for neural networks working with undefined uncertainty data. We have shown that the determination of this optimum can be performed using statistical modeling. Adding an optimal amount of uncertainty (noise of some kind) to the training dataset can be used to improve the overall recognition quality and noise immunity of convolutional neural networks.

6 July 2022 in Symmetry
Verified
Journal Article
Open access
PDF file
OIOlga Ilina
Olga Ilina
VZVadim Ziyadinov
Vadim Ziyadinov
NKNikolay Klenov
Nikolay Klenov
Maxim V. TereshonokMaxim V. Tereshonok
Maxim V. Tereshonok
A number of modern techniques for neural network training and recognition enhancement are based on their structures’ symmetry. Such approaches demonstrate impressive results, both for recognition practice, and for understanding of data transformation processes in various feature spaces. This survey examines symmetrical neural network architectures—Siamese and triplet. Among a wide range of tasks having various mathematical formulation areas, especially effective applications of symmetrical neural network architectures are revealed. We systematize and compare different architectures of symmetrical neural networks, identify genetic relationships between significant studies of different authors’ groups, and discuss opportunities to improve the element base of such neural networks. Our survey builds bridges between a large number of isolated studies with significant practical results in the considered area of knowledge, so that the presented survey acquires additional relevance.

7 November 2023 in Sensors
Verified
Journal Article
Open access
PDF file
VZVadim Ziyadinov
Vadim Ziyadinov
Maxim V. TereshonokMaxim V. Tereshonok
Maxim V. Tereshonok
In this paper, we continue the research cycle on the properties of convolutional neural network-based image recognition systems and ways to improve noise immunity and robustness. Currently, a popular research area related to artificial neural networks is adversarial attacks. The adversarial attacks on the image are not highly perceptible to the human eye, and they also drastically reduce the neural network’s accuracy. Image perception by a machine is highly dependent on the propagation of high frequency distortions throughout the network. At the same time, a human efficiently ignores high-frequency distortions, perceiving the shape of objects as a whole. We propose a technique to reduce the influence of high-frequency noise on the CNNs. We show that low-pass image filtering can improve the image recognition accuracy in the presence of high-frequency distortions in particular, caused by adversarial attacks. This technique is resource efficient and easy to implement. The proposed technique makes it possible to measure up the logic of an artificial neural network to that of a human, for whom high-frequency distortions are not decisive in object recognition.

29 December 2021 in Journal of Communications Technology and Electronics
Verified
Journal Article
Closed access
PDF file
VZVadim Ziyadinov
Vadim Ziyadinov
PKP. S. Kurochkin
P. S. Kurochkin
Maxim V. TereshonokMaxim V. Tereshonok
Maxim V. Tereshonok
Methods for structure optimization of convolutional neural network used for low point density images recognition are proposed to accelerate the training and new images recognition, as well as to reduce the training and recognition procedures resource consumption. Optimized neural network showed a significant increase in speed without accuracy drop in the low point density images recognition, as well as a significantly reduced overfitting tendency.

1 July 2020
Verified
Conference Paper
Closed access
VZVadim Ziyadinov
Vadim Ziyadinov
MTM. V. Tereshonok
M. V. Tereshonok
The most common clustering algorithms in MANET and VANET networks are surveyed, which are a case of ad-hoc networks. Advantages and drawbacks of these algorithms are also reviewed.

14 September 2023 in Preprints.org
Verified
Preprint
Open access
PDF file
VZVadim Ziyadinov
Vadim Ziyadinov
Maxim V. TereshonokMaxim V. Tereshonok
Maxim V. Tereshonok
In this paper, we continue the research cycle on the properties of convolutional neural network-based image recognition systems and ways to improve noise immunity and robustness [1]. Currently, a popular research area related to artificial neural networks is adversarial attacks. The effect of adversarial attacks on the image is not highly perceptible to the human eye, also it drastically reduces the neural network accuracy. Image perception by a machine is highly dependent on the propagation of high frequency distortions throughout the network. At the same time, a human efficiently ignores high-frequency distortions, perceiving the shape of objects as a whole. The approach proposed in this paper can improve the image recognition accuracy in the presence of high-frequency distortions, in particular, caused by adversarial attacks. The proposed technique makes it possible to measure up the logic of artificial neural network to that of a human, for whom high-frequency distortions are not decisive in object recognition.