2687-0517 15 3 2022 1-72

RAR RUS 7-21 0000-0002-7060-8826 Shariaty Faridoddin shariaty3@gmail.com Zavialov Sergey 0000-0003-0726-6613 Peter the Great St. Petersburg Polytechnic University Pavlov Vitalii pavlov_va@spbstu.ru

St. Petersburg, Russian Federation

0000-0001-9948-7303 Almazov National Medical Research Centre Pervunina Tatiana ptm.pervunina@yandex.ru

St. Petersburg, Russian Federation

0000-0003-1129-0667 Orooji Mahdi morooji@gmail.com Inf-Seg: Automatic segmentation and quantification method for CT-based COVID-19 diagnosis The global spread of the COVID-19 has increased the need for physicians and accurate and efficient diagnostic tools. The best way to control the spread of COVID-19 is through public vaccination as well as early intervention to prevent the spread of the disease. According to the World Health Organization, chest CT scans in the early stages of COVID-19 disease have good accuracy, which leads to the widespread use of these images in the diagnostics and evaluation of COVID-19 disease. Lung CT scan segmentation is an essential first step for lung image analysis. The purpose of this article is to evaluate the existing computer systems and to present a more efficient computer system for CT scan image segmentation. For this propose, a novel artificial intelligence (AI)-based COVID-19 Lung Infection Segmentation (Inf-Seg) method is proposed to automatically identify infected regions from chest CT scan. In Inf-Seg, after pre-processing of medical image and improving the image quality, texture feature extraction methods are used to collect high-level features and generate a global map. In the next step, we used YOLACT, which consists of a backbone part of a network of feature pyramids for creating multi-scale feature maps and efficient classification and localization of objects of various sizes (with better information than a regular feature pyramid for object detection), a Protonet part and prediction. 10.18721/JCSTCS.15301 004.932.72 automated segmentation COVID-19 artificial intelligence computed tomography scans machine learning deep learning https://infocom.spbstu.ru/article/2022.74.1/

RAR RUS 22-37 0000-0003-0459-7943 Peter the Great St. Petersburg Polytechnic University Ershov Ilya ershov.ia@edu.spbstu.ru

St. Petersburg, Russian Federation

0000-0002-1859-974X Peter the Great St. Petersburg Polytechnic University Danishevskiy Nikita danishevskij.ns@edu.spbstu.ru

St. Petersburg, Russian Federation

Design algorithm of automatic gain control amplifier for RX Automatic Gain Control amplifier (AGC) with feedback loop is proposed. As a variable gain amplifier, we use bandpass amplifier. Automatic gain control is carried out by changing the current cutoff angle of the amplifier. We control the current cutoff angle by measuring power of output signal with the help of peak detector in low signal mode. Supportive amplifier allows us to achieve more tuning flexibility. Required gain tuning range is obtained by changing gain ration of the supportive amplifier. We propose a design algorithm of the AGC system. The algorithm is based on the Sonneborn–Berger score. The proposed method helps to achieve fully analytical computation. To prove algorithm validity, calculations and simulation were carried out. 10.18721/JCSTCS.15302 621.375.4 Automatic gain control variable gain amplifier design algorithm current cutoff angle Sonneborn–Berger score peak detector https://infocom.spbstu.ru/article/2022.74.2/ 22-37.pdf

RAR RUS 38-48 0000-0002-3324-6213 Peter the Great St. Petersburg Polytechnic University Lazovskaya Tatiana lazovskaya_tv@spbstu.ru

St. Petersburg, Russian Federation

Tarkhov Dmitry dtarkhov@gmail.com Peter the Great St. Petersburg Polytechnic University Bortkovskaia Mariia mbort@mail.ru

St. Petersburg, Russian Federation

Peter the Great St. Petersburg Polytechnic University Kaverzneva Tatyana kaverztt@mail.ru

St. Petersburg, Russian Federation

Peter the Great St. Petersburg Polytechnic University Kudryavtseva Vasilisa vasilisa.kudryavtseva1997@gmail.com

St. Petersburg, Russian Federation

0000-0003-1736-5914 Peter the Great St. Petersburg Polytechnic University Kozhanova Polina polinakozhanova@yandex.ru

St. Petersburg, Russian Federation

Peter the Great St. Petersburg Polytechnic University Chernaya Ekaterina Chernaya.kotyk@gmail.com

St. Petersburg, Russian Federation

Comparative analysis of hybrid neural network and multilayer modeling of a circular membrane deflection under a load located asymmetrically to its center This article is devoted to the problem of a hybrid approach in modelling, which combines methods based on mathematical physics equations and data-driven methods. The issue of choosing a hybrid model for circular membrane deflection under a load is considered. To build models, the Laplace equation inaccurately describing the object and measurement data of sufficiently high accuracy are used. With the help of cross-validation methods, an algorithmic comparison of the generalising ability of a multilayer model, a physics informed neural network model and a classical approach is made. The results obtained allow us to recommend neural network and multilayer methods for modelling objects when a sufficiently accurate classical description using a boundary value problem is unknown or excessively difficult and additional information is available in the form of measurement results. Multilayer methods are preferable in case of shortage of data or its dynamic nature, if a compact adaptive model is needed, including for use in embedded systems and digital twins. 10.18721/JCSTCS.15303 519.673, 004.896 hybrid models circular membrane deflection Laplace equation PINN multilayer model physics-based architecture https://infocom.spbstu.ru/article/2022.74.3/

RAR RUS 49-61 0000-0001-5439-4277 Peter the Great St. Petersburg Polytechnic University Zhu Yuqing 1918149382@qq.com

St. Petersburg, Russian Federation

Model of control system for unmanned aerial vehicles (quadcopters) Designing control systems for unmanned aerial vehicles (UAV) based on models eliminates uncertainty, ambiguity, and non-computability. In addition, it is an effective way to ensure the creation of UAV with a high safety factor that meets airworthiness standards. This is the aircraft design process adopted by some well-known international companies. It may be worthwhile for companies and science institutes with sufficient resources to implement “Model-Based Systems Engineering” for drones or quadcopters as small complex systems. Model-based development greatly enhances the safety of small complex systems. Simulation in virtual environments is beneficial for exploring the development process and gaining experience for UAV development. This study presents a three-dimensional model of a quadcopter (one of the UAV varieties) in the SolidWorks program. An analysis of the characteristics and dynamics of the flight of the quadcopter was carried out, then, using Matlab, a model of the mechanism of the system and quadcopter engines was created. A model of quadcopter dynamics is presented and its movements are simulated when performing various tasks. 10.18721/JCSTCS.15304 681.5 unmanned aerial vehicle quadrocopter dynamics model Simscape Multibody analog simulation in Matlab https://infocom.spbstu.ru/article/2022.74.4/ 49-61.pdf

RAR RUS 62-72 Ulyanovsk State Technical University Kurganov Sergey sakurganov@mail.ru

Ulyanovsk, Russian Federation

St. Petersburg Electrotechnical University “LETI” Nedorezov Pyotr pyatakpy@rambler.ru

St. Petersburg, Russian Federation

Ulyanovsk State Technical University Filaretov Vladimir vvfil@mail.ru

Ulyanovsk, Russian Federation

Parametric diagnostics of electrical circuits in static mode by the method of compensation of nonlinear elements To solve the diagnostic problem in static mode, it is proposed to use compensation of nonlinear elements with both unknown and known parameters. This reduces the diagnosis of a nonlinear circuit to the basic task of diagnosing a linear substitution circuit with multiple experiments. The multiplicity of the experiment and the calculation of the substitution circuit is determined by the number of required points of the volt-ampere characteristics of nonlinear resistors and the transfer characteristics of nonlinear controlled sources. The number of measurements in each experiment should not be less than the number of nonlinear elements and linear elements with unknown parameters. Computational costs can be reduced if symbolic analysis methods are used to obtain volt-ampere and transfer characteristics of nonlinear elements in the form of parametric functions. The proposed approach makes it possible to automate the diagnostics of nonlinear elements in a static mode using well-known symbolic and numerical programs for the analysis of linear electrical circuits. An example of finding the volt-ampere characteristics of nonlinear resistors using the developed CirSym symbolic analysis program is given. 10.18721/JCSTCS.15305 621.3.011.7 electric circuit static mode basic diagnostic problem nonlinear resistor nonlinear controlled source indirect compensation volt-ampere characteristic https://infocom.spbstu.ru/article/2022.74.5/ 62-72.pdf