Search

A review of modern methods and technologies for automatic machine translation for the deaf and hard of hearing is presented, including recognition and synthesis of both spoken and sign languages. These methods aim to facilitate effective communication between deaf/hard-of-hearing and hearing individuals. The proposed solutions have potential applications in contemporary human-machine interaction interfaces. Key aspects of new technologies are examined, including methods for sign language recognition and synthesis, audiovisual speech recognition and synthesis, existing corpora for training neural network models, and current systems for automatic machine translation. Current neural network approaches are presented, including the use of deep learning methods such as convolutional and recurrent neural networks as well as transformers. An analysis of existing corpora for training recognition and synthesis systems is provided, along with an evaluation of the challenges and limitations of existing machine translation systems. The main shortcomings and specific problems of current automatic machine translation technologies are identified, and promising solutions are proposed. Special attention is given to the applicability of automatic machine translation systems in real-world scenarios. The need for further research in data collection and annotation, development of new methods and neural network models, and creation of innovative technologies for processing audio and video data to enhance the quality and efficiency of the existing automatic machine translation systems is highlighted.

Introduction. At present, automatic capture and tracking of moving objects in video data obtained by a video camera mounted on a mobile carrier represents a relevant research task. Its successful solution is challenged by such factors, as a non-uniform background, object overlapping between one another and the background, significant and rapid changes in the size of the object of interest, abrupt changes in the movement trajectory of the mobile carrier.Aim. To develop an automatic method for detecting moving objects followed by their tracking in video data obtained under difficult observation conditions. An additional requirement imposed on the tracking stage consists in the restriction of computing resources.Materials and methods. The method is based on a convolutional neural network with a YOLO architecture. Due to the restriction of computing resources, object tracking is implemented without neural network solutions. In order to ensure stable tracking, several detectors are used simultaneously with the subsequent analysis of the data obtained. The tracking stage involves a detector based on histograms of oriented gradients (HOG), supplemented by a detector based on correlation filtering and motion trajectory prediction based on the Kalman filter.Results. At the automatic detection stage, the TPR, averaged over all video files participating in the experiments, was equal to 0.81, with the FPR corresponding to 0.10. At the tracking stage, the failure rate (tracking failures) was 6·10 –5.Conclusion. The proposed method can be successfully used to detect and track objects at a distance of 1500 m with an object projection size on the frame of 5 × 5 pixels under the conditions of global motion, a non-uniform background, and significant changes in the properties of the object of interest.

When radar stations operate, radio pulses of varying intensity are received at the receiver input depending on the type of target, range to the target and other factors. Adjusting the receiver gain is necessary to adjust its sensitivity in such a way as to provide the best reception of signals with amplitudes that vary widely. The article discusses a logarithmic automatic gain control system, analyzes its advantages and disadvantages compared to classical automatic gain control system, and performs its simulation in the graphical programming environment Matlab/Simulink.

In connection with the beginning transition of mass-produced battery electric vehicle (BEV) powertrains from single-gear gearboxes to specially configured automatic transmissions (AT), the number of publications devoted to justification and research of their architecture, as well as optimization of applied design solutions, is rapidly increasing. A large number of publications focus on dual-clutch AT (i. e. DCT) with two clutches (or frictions) in the first stage application. A clear recent trend in their subject matter is a shift of interest in DCT control, especially in transient automatic gear shifting with joint control of the motorgenerator (MG) and frictions in an integrated powertrain. It is shown that smoothness of shifting here is of no less importance than in classical AT, not only because of shift shocks, which deteriorate comfort, but also because of the possibility of excitation of oscillating modes in the electric drive. The paper analyzes several published variants of a strategy for controlling such shifting processes and their computer and physical implementation. We believe that, given the lack of Russian-language materials on this subject, this information is published for the first time.

Introduction. A number of design features of the rolling stock and operating conditions of the SA-3 automatic coupler in locomotive traction passenger cars cause increased wear of the rubbing surfaces of the automatic coupler, which requires measures to strengthen them. The issue of automatic coupler loading for wagons is studied and presented in research, technical and regulatory documentation. The authors consider the experimental data on longitudinal forces and relative displacements of automatic couplers under operating modes to be insufficient in the case of the SA-3 automatic coupler in a locomotive traction passenger car. Lack of such studies did not allow manufacturers of SA-3 automatic couplers intended for use in passenger rolling stock to reasonably implement processes for hardening of contact surfaces. The study was primarily intended to obtain reliable experimental data on the relative displacements of automatic couplers during motion as part of a passenger train, as well as on the acting longitudinal forces.Materials and methods. The main method of the research was direct measurements of relative displacements using contact displacement sensors. Longitudinal forces were determined by resistance strain gauges mounted on the automatic coupler body. The test ride was preceded by scaling of the measuring circuits by tensile and compressive forces using the bench equipment of the test laboratory of the Tikhvin Trial Centre for Railway Transport.Results. The authors obtained statistically reliable data on longitudinal forces and displacements of automatic couplers when the carriage moves in a locomotive traction passenger train.Discussion and conclusion. The authors determined the longitudinal forces and displacements of the SA-3 automatic coupler used in a locomotive traction passenger car. These data are intended for further use in bench service life testing of the automatic coupler.

Research objective. The main objectives of developing a module for automatic assessment of students’ papers based on the Russian grading scale system are:– Increased grading efficiency: the automatic system can process a larger number of papers in less time than a lecturer, reducing the time spent on checking;– Grading objectivity: the automated system is not subject to bias and other human factors, which ensures more objective grading of papers;– Standardization of grading: the automated system provides a uniform approach to grading, making it more transparent and comparable;– Reduced workload for lecturers: freeing lecturers from the routine work of checking papers allows them to devote more time to individual work with students.Materials and methods. Various methods can be used to develop a module for automatic assessment of students’ work, such as:Machine learning techniques: these techniques allow the module to learn from a set of examples where lecturers have already assessed students’ papers and automatically grade new papers.Natural Language Processing (NLP) methods: these methods allow the module to understand the meaning of text and evaluate it against given criteria.Expert systems methods: these methods allow the module to utilize the knowledge of experts in assessing students’ papers. For this project, we have chosen a combination of Levenshtein and Jaro index algorithms based on the method of assessing students’ knowledge in the Russian system.Results. The following main results were obtained in the course of this research. The module of automatic evaluation of student papers has been successfully developed and implemented on the basis of the Russian system of evaluation scales. Test evaluations of papers showed high accuracy of the module’s predictions and reliability of its work. Comparison of the module with manual assessment confirmed its ability to give comparable results. The module proved to be useful for lecturers, providing them with the ability to quickly and objectively assess students’ papers. Integration of the module with existing learning management systems facilitates its implementation in the educational environment. All the obtained results testify to the high efficiency and prospectivity of the developed module.Conclusion. As a result of this work, a module for automatic evaluation of students’ papers based on the Russian system of evaluation scales was developed and implemented. The main results of the work are that the module has been successfully tested and demonstrated high accuracy and reliability in the assessment of papers. The module has also demonstrated its usefulness for lecturers, providing them with an opportunity to quickly and objectively assess students’ papers. Due to its integration with existing learning management systems, the module can be easily implemented into the educational environment. In general, the results of the work confirm the effectiveness and prospects of using automatic assessment of students’ papers based on the Russian system of assessment scales.

The research paper focuses on the mechanism of semantic parser for automatic text analysis and represents some results of analyzing news with a total volume of 2.2 million clauses. This mechanism models the processes of text comprehension and in this paper it is applied to the evaluation of the text influence on the reader. The parser constructs a semantic representation of the text and maps the meaning of each clause to a particular frame belonging either to the set of 300 emotional or to the set of 4500 rational frames. Comparing the frames of pro- state (federal) and blocked sources in Russia, the authors show that the most frequent frames in federal news represent an interactive dialog between the media and the speaker (note, add, recall, etc.), while the most frequent frames in blocked news introduce the speaker’s utterance that has become known to the news agencies (report, write, say, etc.). This reflects the remoteness of the editors of blocked news from Russian speakers. The federal media more often report about funny or unexpected purchases, as well as about how federal employees rescue people, and this agenda should make a positive impression. The blocked media, on the other hand, are more likely to mention court sentencing and death, which should have a negative impact. The natural-language inference constructed via frame combinations is shown to enable the recognition of emotional situations in derived meanings that are not explicitly expressed in the text and, thus, it allows to analyze automatically more compound mechanisms of manipulation.

Introduction. The topic of implementing a dual-band mode of operation for director dipole antennas is represented by a wide range of works, almost all of which are dedicated to studying the properties of a classic dipole. However, the issue of end excitation of radiators for dual-band director antennas remains open. The development of such radiators requires a deep analysis both from the point of view of developing mathematical and electrodynamics models, which corresponds to the tactical and technical requirements of modern digital antenna arrays.Aim. To substantiate a procedure for determining the initial appearance of a dual-band antenna exciter from the standpoint of the systems approach to the design of antenna elements and nodes. This procedure is suitable for a semi-automated design of more complex antenna systems.Materials and methods. As part of the research, the input impedance of a dual-band system consisting of two active radiators and two passive directors was determined using the method of induced electromotive forces (EMF). Models of dual-band director radiators were developed using the CST Studio Suite 2021 full-wave electromagnetic simulation.Results. The results of developing procedures for a semi-automatic design of antennas with a dual-band function of input impedance are presented. Following a comparative analysis, approaches to implementing the printed layout of an antenna comprising standard radio engineering components, which imply serial production, are proposed.Conclusion. The proposed models can be used when designing director, turnstile, and cardioid antennas, as well as antenna arrays. These designs are analogous to antennas based on a classic central excited dipole.

Background. The work shows how computer models and automatic programming techniques help in developing control system program code using the example of creating software for an automated greenhouse. Materials and methods. The main stages of developing a control program are reflected using certain mathematical patterns and algorithms used in creating the control system code and simplifying the development process itself. The benefits of using an automated greenhouse have been shown, both in households and in agricultural companies. The main technological units that help automate the process of growing plants are presented, as well as the parameters that help control these units. The necessity of introducing a PID controller into the technological process to control the temperature inside the greenhouse is substantiated. An example of setting up a PID controller for specific greenhouse conditions is given. Results. The process of distributing selected parameters of a technological system into data blocks, each of which is located in a separate machine, is described. Conclusions. The article ends with a block diagram that is found in the logic of the automata program and a diagram of the general interaction of computer models in the Automata Programming technique.

The article presents the results of applying an improved method for automatic segmentation of RGB imagery obtained using consumer-grade UAVs, based on the Mask R-CNN neural network architecture. Blocks for the preparation and post-processing of raster and vector files have been developed for working with geospatial data. The model was trained on 7000 crowns identified in pine forest of automorphic habitats in the mixed coniferous-broadleaf forest subzone. Training was carried out using cross-validation. Additional data of 1337 crowns were used for verification. During the sequential filtering by area, confidence level, and duplicate segments, the quality of the final segmentation results improved for all age groups of pine forests. The final average precision is 0.87, recall – 0.81, F1-score – 0.83. The results demonstrate the high efficiency of the filtering algorithm in reducing segment redundancy and increasing data reliability. The Mask R-CNN automatic segmentation method is an effective tool for analyzing the characteristics of pine canopies using RGB imagery from UAV surveys. It is capable of replicating the results of visual interpretation with high accuracy. This method particularly advantageous for scaling studies to large areas where manual delineation becomes labor-intensive.

Introduction. In the poultry industry, the use of local LED lighting systems with changeable light and correlated color temperature of the luminaire optical radiation during the photoperiod is promising. To maintain light intensity accurately at a specified level, the use of an automatic control system (ACS) of lighting is required. Aim of the Study. The study at aimed at determining the parameters for the PI controller of the digital ACS of lighting in all-age cages, providing the required quality indicators of the regulatory process. Materials and Methods. For the study there were used the elements of mathematical statistics, experimental research design theory, correlation and regression analysis, automatic control theory and computer simulation. Real experiments were carried out on a laboratory sample of a digital dynamic local lighting system. Computer simulation was performed in the SimInTech program. Results. A computer model for a digital ACS of lighting has been developed. The tunings of the PI controller were calculated using the CHR, VTI, and Kopelovich methods. A comparative estimation of the control process quality was carried out using graphs of transient processes obtained by computer simulation. The reliability of the results of computer simulation of ACS lighting has been confirmed experimentally. Discussion and Conclusion. High regulator performance indicators for the digital ACS of lighting were ensured by a PI controller with kP = 14.027∙10−3 and TI = 145.72 ms calculated using the Kopelovitch method. A comparative assessment of transient processes in a real ACS and in a computer model of this system allows concluding that the developed model is highly accurate and the choice of simulation parameters in the SimInTech program is correct. It has been experimentally established that the required quality of the control process of ACS is ensured for a wide range of specified lighting: from 1 to 25 lux.

. The goal of the work is to create a new method for automatic re-tuning of PI controllers. It is achieved by solving the following problems. The first problem is to develop a method to identify a FOPDT estimation model by analyzing the dynamics of a control loop with a PI controller. The second problem is to demonstrate that the use of the estimated model allows to obtain better processes in control systems with PI controllers by comparing the resulting FOPDT model with a number of reduced models. The third problem is to develop a five-stage algorithm for automatic re-tuning of PI controllers. The fourth problem is to verify the software implementation of the developed algorithm. The most significant result was that the basis for estimating the FOPDT model in a loop with a Ziegler-Nichols tuned PI controller was the estimation the ratio of the delay to the time constant of the FOPDT model based on an assessment of the process overshoot. When the real control plant dynamics did not match with the dynamics of the FOPDT model this way was found effective for finding the optimal tuning of the PI controller. The significance of the results obtained was a structural robustness in case of estimated FOPDT model usage. The effectiveness of the procedure has been demonstrated on both linear and nonlinear models. The developed procedure is proposed to be used to automate the procedure of re-tuning SISO control systems when the control loop performance degradation has been detected.

Introduction. Interference in the continuous automatic cab signalling channel distorts transmitted signals and causes signalling malfunctions. Reduction of interference in the channel involved a previously proposed receiver with quadrature channels and its implementations with non-linear signal transformation in one or two sections of the receiver. The research is intended to find the best implementations of the quadrature receiver.Materials and methods. The research uses a computer simulation of the operation of the studied receivers under the influence of harmonic interference from a power line. For this purpose, the authors used Simulink visual programming environment and developed receiver simulations, applied the harmonic interference simulation model and conducted experiments to assess noise immunity expressed as a time interval showing receiver malfunction.Results. The researchers determined the effect of non-linear signal transformation on the harmonic noise immunity of the receivers.Discussion and conclusion. The research shows that the receiver with a deadband is the most preferable of all considered variants of quadrature receivers in terms of maximum harmonic noise immunity. The receiver with combined interference suppressor and deadband is slightly inferior.

We present a system that solves simple physics word problems (PWPs) stated in the English language. The main feature of the system is that it is deterministic and yields a correct solution based on real physics formulas. The program generates the solution in a tabular form, showing givens, unknowns, and solution steps. We performed a thorough analysis on the previous work in this field. Most of the research was accumulated in math word problem (MWP) solvers. We have found that these programs are not capable of solving problems from Ukrainian physics textbooks. We identified several types of physics problems: theoretical, value conversion, value comparison, unknowns finding, value change. We developed separate problem-solving strategies for each type. The program uses named entity recognition (NER), a technique in natural language processing (NLP), to identify key elements in the problem text. We created a set of rules for marking these entities. Then, problem type recognition is performed. Depending on the type, the list of entities is converted into the internal problem representation. Value conversion and comparison problems are easy to handle. We developed a recursive algorithm for solving unknowns-finding problems which turned out to be a simplified version of Stanford Research Institute Problem Solver (STRIPS) algorithm. However, developing a universal algorithm for solving value-change problems presents a significant challenge. We believe this problem type belongs to the NP-hard class, indicating inherent difficulty in finding optimal solutions. The interface of the program is a web-application. The user can type the problem text and see the solution on a web page. Additionally, the result of NER is presented. Constructing a general problem solver is challenging. While our program can solve basic physics problems, complex problems involving forces, energy, etc., remain unsolved. However, our solver has great potential for future development. We have thoroughly analyzed its capabilities and limitations and proposed ideas for future research.

The article presents the results of a practical study of the features of fake reviews that are described by marketers and other experts. Due to the abundance of fake reviews on marketplaces, consumer trust falls not only in the seller or platform, but in the genre itself. The paper presents the results of automatic classification of reviews from Russian marketplaces into potentially fake and honest ones using modelling of features that experts call labels of a fake review (presence of template words, exclamation marks, emoji, positive sentiment), and machine learning algorithms. To solve the problem, a corpus of 6 288 texts from the Russian marketplaces Wildberries and Megamarket has been collected. The target variable (predicted class) is the ratio of likes and dislikes given to the review by other buyers. The best result is demonstrated by the support vector machine algorithm in binary classification into reviews with a low and high ratings (without neutral ones). The classification model confirms that the formal features identified by experts as indicating fake reviews indeed have predictive potential. The quality of the model is reduced by the imbalance in classes and insufficient number of reviews with buyer reactions in our corpus, which leaves room for further work.

Purpose: the development of a system for automatic control of car loading, which will be able to combine separate nodes into one common system to ensure greater control and reliability of the process. Research methods are grapho-combinatorial. Methodology: the research is justified by a logical synthesis based on the hardware of embedded control systems, programming in the language of functional blocks of the MEK61131-3 standard. Results: the requirements for the structure of the automation system of coal loading complexes were formulated, the basic automation equipment was selected, and the control algorithms were determined. Based on the requirements for the automation system, a functional scheme and its technical implementation of the automation of coal loading complexes as a single control system were developed. The algorithm was developed and subsequently the SAC program of the local system was developed, which was able to show its performance in the "Owen Logic" environment. This made it possible to adjust and select the correct coefficients and possible calculated data. Scientific novelty: the development of a functional model of the coal loading complex and the use of wireless communications, aimed at combining fragmented local systems into one common one to ensure greater control and reliability of the process. Practical significance: the functional and structural model of the coal loading complex will allow to increase its level of automation, reliability and efficiency of operation, to eliminate the shortcomings of the technical fragmentation of the system and to prevent significant material, time and economic costs for setting up the system.

The purpose of the work is to build the rational system for regulating technological parameters of the single-screw extruder using the frequency-regulated electric drive with limited use of sensors. This goal is achieved by the way of solving the following problems: development the method for controlling the technological parameters of the extruder with a controllable electric drive; development of a structural diagram of a model for estimating the speed of rotation a rotor of the engine without the use of velocity-type transducers; development of a functional diagram of the vector frequency-regulated electric drive with an observer that is built on the basis of a voltage equation corresponding to the main magnetic flux; development of a simulation model of the system of adjustable electric drive of the extruder and carrying out simulations with using the Matlab software package in the environment of Simulink. The most significant results of the researches are: the proposed algorithm for controlling the technological parameters (dynamic viscosity and pressure) by the way of calculating of the electrical power parameters of the adjustable electric drive of the extruder without the use velocity-type transducers; the functional diagram of the vector frequency-regulated electric drive of the single-screw extruder with the observer that was built on the basis of balance of the reactive capacity provides the necessary values of the technological parameters of the extruder. Changes in dynamic viscosity and pressure in the material, provides flexible adjustment without the use of speed sensors and rational use of electricity.

Within the project of developing an automatic feed wagon, the initial task is to determine its overall parameters, which directly depend on the wagon volume. (Research purpose) To simulate the automatic feed wagon operation in order to determine the optimal volume ensuring the versatility of its use in cattle cowsheds accommodating different numbers of animals, and practicing different feeding frequency. (Materials and methods) The solution to the problem is based on the calculation of the feeding time taken by the automatic feed wagon. The time must not exceed the limit values established by zootechnical standards. To calculate the feeding time taken by an automatic feed wagon, a graph-theory-based simulation method was used, taking into account the probabilistic nature of the components of feed mixture distribution time balance. The calculations were performed in MS Excel. (Results and discussion) The paper describes the conditions for simulation and considers two options for the automatic feed wagon operation, in particular the option when one robot serves two cowsheds and the other when each cowshed is served by a separate feed wagon. (Conclusions) The second option with a separate automated feed wagon for each cowshed is proved to be more suitable. It has been obtained that in this case, the reduced movement length results in a 27.9-36.2 percent increase in productivity of the automatic feed wagon; besides there is no need to install automatic gates and build an insulated vestibule to move the robot between the cowsheds. Thus, the programming task becomes simplified. It has been found out that an automatic feed wagon having the volume of 2 cubic meters is enough to feed animals in the cowsheds sized 111.9 meters by 26.6 meters and smaller, accommodating up to 340 cows, and with a feeding frequency of 4-8 times a day.

BACKGROUND: Scoliosis is one of the most common spinal deformations that are usually diagnosed on frontal radiographs using Cobb’s method. Automatic measurement methods based on artificial intelligence can overcome many drawbacks of the usual method and can significantly save radiologist’s time. AIM: To analyze the accuracy, advantages, and disadvantages of a newly developed artificial intelligence program for the automatic diagnosis of scoliosis and measurement of Cobb’s angle on frontal radiographs. MATERIALS AND METHODS: In total, 114 digital radiographs were used to test the agreement of Cobb’s angle measurements between the new automatic method and the radiologist using the Bland–Altman method on Microsoft Excel. A limited clinical accuracy test was also conducted using 120 radiographs. The accuracy of the system in defining the scoliosis grade was evaluated by sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve. RESULTS: The agreement of Cobb’s angle measurement between the system and the radiologist’s calculation was found mostly in grade 1 and 2 scoliosis. Only 2.8% of the results showed a clinically significant angle variability of 5°. The diagnostic accuracy metrics of the limited clinical trial in City Mariinsky Hospital (Saint Petersburg, Russia) also proved the reliability of the system, with a sensitivity of 0.97, specificity of 0.88, accuracy (general validity) of 0.93, and area under the receiver operating characteristic curve of 0.93. CONCLUSION: Overall, the artificial intelligence program can automatically and accurately define the scoliosis grade and measure the angles of spinal curvatures on frontal radiographs.

Purpose: to analyze the issues of development and application of an automatic control system for the technological process of water distribution in the Donskoy main channel (DMC) using proportional-integral differential PID controllers and a control scheme for the upstream. The urgency of this purpose is justified by the fact that effective management of water level in channel is of great importance for agricultural production and water supply to adjacent territories. The analysis of the main components of the control system, including PID controllers and the upstream control scheme is performed. The possibility of using these components for effective control and regulation of water level in the channel is considered. Materials and methods. A detailed analysis of the factors that must be taken into account when designing an automatic control system of water in a channel using PID controllers has been carried out. An algorithm for controlling water level in the upstream channel using PID controllers is proposed. Results. Measures for the water distribution management system development and implementation in the Donskoy main channel are proposed. It is stated that when designing a control system, the configuration of the channel and the measures to ensure a uniform distribution of water along its entire length should be taken into account, considering the unsteady water motion in the Donskoy main channel. The results of the analysis show that the automatic control system using PID controllers and the upstream control scheme has the potential to control the water level in the DMC effectively. Conclusions. Based on the analysis carried out, it was concluded that it is possible to design an automatic water control system in the DMC using PID controllers and a control scheme for the upstream successfully. Further research and development can contribute to the optimization of water distribution management and increase the efficiency of agricultural production in the region.

Quantitative analysis of the structure of metals and alloys is an important part of modern metal science. To obtain quantitative data and build dependencies, metallographic image processing programs are used, oriented both for scientific research and for use in industry. Programs capable of automatically performing metallographic analysis are of great interest to consumers. When advertising such programs, it is often claimed that they allow quantitative analysis of the structure with virtually no time. The purpose of this work was to determine the time spent on quantitative metallographic analysis in some image processing programs presented on the Belarusian market. Connected and unconnected metallographic objects were considered. It is shown that automatic quantitative analysis is possible for unconnected objects (powders, cast iron graphite). The time required is within a minute. For connected objects (structures of metals and alloys after metallographic etching), the time required to detect objects and obtain digital data is 10–40 min or more, depending on the complexity of the object, which is unacceptable for factory laboratories that analyze a large number of samples per shift. Therefore, it is recommended that potential users of metallographic image processing software always require a substantive demonstration of the automatic measurement capabilities of the proposed software.

The results of a comprehensive assessment of working conditions for operator‑casters on automatic lines are presented, including the factors of the production environment that determine these conditions. It has been established that a comprehensive assessment of the working conditions of operator‑casters should take into account the factors of the production environment and their absolute values when performing individual technological operations in obtaining castings.

RELEVANCE. Synchronization is an algorithm of actions to switch on synchronous generators for parallel operation with the power system and is an integral part of the power generation process. In practice, the process of synchronization involves some difficulties. The developed automatic synchronization device is digital and is integrated into the microprocessor terminal of the CPA-M complex, allowing to solve the arising problems by means of synchronization using different methods, including the developed method of accelerated synchronization.THE PURPOSE. Create a comprehensive automated synchronization system based on the CPA-M microprocessor terminal (manufactured by a Novosibirsk company) with a variability of methods. Analyze existing synchronization devices, synthesize traditional synchronization methods, create a non-traditional intermediate method on their basis and integrate it into the automated system. Develop algorithms for the measuring and logical units, as well as for the synchronization system output unit. Experimental testing of algorithms by feeding real signals from voltage sensors on a physical model with a rotating synchronous machine (12 kW generator under test).METHODS. The problem of research studied using theoretical and practical approaches. Theoretical methods - analysis, synthesis and classification. Practical methods - modeling in MatLab® environment, comparison, experiment, observation.RESULTS. The paper describes the architecture, construction principles, settings selection of the synchronization system, as well as the interaction of its logical part with adjacent units (measuring unit, output unit). The work gives a comprehensive description of the system setup and integration of its measuring and logic parts into the CPA-M microprocessor terminal with a test on a physical object.CONCLUSION. The system has extended functionality compared to analogs, allowing the use of traditional methods and the developed method of accelerated synchronization. The results predict reduction of capital costs for automation systems, as one device provides synchronization on several circuit breakers and reduction of generator operation costs, as using this system, machine parts exposed to unacceptable thermal and mechanical effects. The development is relevant for the elimination of emergencies in the power system and reducing thermal and dynamic impacts on the generator. The social importance of the project is the exclusion of the human factor. The prospect of using the development - in the educational process of the university and at real power facilities, in particular on large synchronous generators.

Background. The paper considers the methods of building an information and control complex that affects the human respiratory system. Such systems are used worldwide for the rehabilitation, treatment and prevention of patients with chronic obstructive pulmonary disease and heart failure. A two-circuit control method based on a decisionmaking system built using fuzzy logic allows for adaptive load on the respiratory muscles based on the information received in real time. Materials and methods. The methods of system analysis, fuzzy logic, and approximation theory are used in the work. Results. In the course of the conducted research, a block diagram of the information management complex was obtained, which includes a block for determining the level of human fitness and a decision support system. A method for testing the state of the human respiratory system and an algorithm for assessing the level of approximation of the respiratory system to the «norm» and «pathology» groups have been implemented. Conclusions. The proposed methods and tools make it possible to provide a configurable level of stress on the respiratory system of each patient, taking into account changes over time.

Battery electric vehicles with automatic transmissions are a new rapidly growing segment of electric vehicle and automatic transmission type configured for such applications. A promising direction of their development is integration of mechatronic control systems of automatic transmissions and electric drive, i.e. transition to integrated power units of battery electric vehicles. Pre-defined criteria are required to formulate the specifications for the design of the mechatronic control systems for such a unit. However, not only for mechatronic control systems, but also for battery electric vehicles with automatic transmissions themselves, sufficient experience in production and operation has not yet been accumulated, which determines the relevance of this article. Its purpose is to formulate approaches to the development of specifications on the emerging mechatronic control systems for automatic transmissions of integrated battery electric vehicles power units with automatic transmissions. The analysis (according to the formed information base) of the set of general requirements is carried out to the designs of close analogues — modern mechatronic control systems of automatic transmissions of hybrid electric vehicles, as well as the results of optimization of their parameters, characteristics and control algorithms of stage shifting processes of automatic transmissions for application in battery electric vehicles. It is shown that the compositions of basic functional properties of mechatronic control systems of automatic transmissions in battery and hybrid electric vehicles largely coincide. As a result, the composition of a set of basic criteria is formed for the evaluation of mechatronic control systems of battery electric vehicles. Based on the results of expert evaluation and analysis of analogues that meet modern requirements and are close to the types of domestic equipment, the basic specifications are proposed to the composition and functional characteristics of mechatronic control systems of automatic transmissions of power units of battery electric vehicles power (taking into account the private specifications to the subsystems included in them). The specification lists and their evaluation criteria include a number of established technologies in the global automotive industry. Taking into account that their practical application requires systematized information, which is difficult to find in the Russian-language presentation, the necessary explanations are given.

BACKGROUND: The application of videofixation technologies in embryology is developing significantly. These technologies permit the objective analysis of the process of early embryogenesis of each cultured embryo without the necessity of removing the culture cup from the incubator. Timelapse technologies in routine practice allow for the guaranteed detection of embryo developmental pathologies that are inaccessible to traditional developmental monitoring methods [1, 2]. Nevertheless, the annotation and manual evaluation of all frames captured during the cultivation process can be a time-consuming process. Furthermore, video fixation itself does not eliminate the issue of objectivizing the quality of interpretation of the obtained images [3]. Intelligent technologies, in particular, solutions developed with the use of machine learning, are successfully employed in the resolution of such problems. AIM: The aim of this study is to develop a system for the automated analysis of the morphokinetic state of the human embryo with the aim of assessing its capacity for implantation. MATERIALS AND METHODS: The data were collected at the Family Medical Center (Ufa, Russia) and the Clinical Hospital IDK of the Mother and Child Group of Companies (Samara, Russia). Digital images of the period of preimplantation development of human embryos up to the blastocyst stage (days 0–6 from insemination) were obtained using an incubator for in vitro fertilization laboratories, the EmbryoVisor, with a timelapse (hyperlapse) video fixation system. Embryos were cultured individually in special micro-well WOW dishes (Vitrolife, Sweden). The data set was labelled using Label Studio Community Edition software. A recurrent convolutional neural network was selected to analyse the data and trained using multiple images. RESULTS: The development of the automatic analysis system is based on the classification of the morphokinetic state of the embryo according to the stages of embryogenesis: fertilization, fragmentation, morula formation, and blastocyst formation. Segmentation of multiple objects, such as pronuclei and polar bodies at the fertilization stage or blastomeres at the fragmentation stage, will be performed depending on a certain stage of development. We plan to build a binary classification of the presence of additional features (multinucleation, heterogeneity of the endoplasmic network), classification/regression of additional features (so, fragmentation can be estimated as discrete ranges or absolute values). The result is a system for labeling the morphodynamic profile of an embryo using deep learning. This method automates and accelerates the analysis process, which previously required significant time and human resources. CONCLUSIONS: It is anticipated that the developed system of automatic analysis of morphokinetic state of embryos will simplify the process of evaluating the quality of human embryos in in vitro fertilization laboratories, reducing the time and resources spent on this process. Furthermore, it will enhance the accuracy and reliability of assessing the implantation ability of embryos and could potentially serve as the foundation for the development of a support system for medical decision-making in embryology.

The subject of research, relevance. Exchange of information is an important measure of administrative cooperation between and among tax authorities aimed at the fight with tax evasion. Tax evasion is a problem that has gone beyond national borders, thus individual states can’t cope with it alone. In the light of this problem tax authorities develop new forms of administrative cooperation such as automatic exchange of information. While developing new forms, states should remember about the balance of private and public interest. In the context of automatic exchange of information this problem looks like a problem of finding a balance between confidentiality and tax transparency.The purpose. The article discusses the problem of finding a balance between confidentiality and tax transparency on the example of the United States. The choice of the United States may be explained by its national approach to such a balance that differs from the approach of other states that have implemented the Common Reporting Standard and Mandatory Disclosure Rules.The aim of the article is to show what peculiarities in national and international regulation in the United States influence their unique approach and what is the effect of this approach on the global system of automatic exchange of information and the rights of the US taxpayers.The methodological basis. The following scientific methods were used: comparative-legal, formal-juridical and historic-legal. The research was conducted in compliance with the principles of independence and verification of the results.The main results, scope of application. The conclusion of this article is that the balance of private and public interest in the context of automatic exchange of information is reached by the United States through confidentiality provisions exclusively. They use their national state legislation on beneficial ownership and the lack of reciprocity in intergovernmental agreements implementing FATCA to attract foreign investors (non-resident aliens) wishing to avoid reporting under the Common Reporting Standard. Meanwhile, the United States acquire full information on the financial accounts of their citizens and resident aliens who are beneficial owners of such accounts held in foreign financial institutions. Such a state of affairs is dangerous for the effectiveness of the global system of automatic exchange of information. Moreover, it impairs the rights of Accidental Americans who permanently reside in foreign states and have no connection with the United States except for their citizenship but still have reporting obligations before the US Internal Revenue Service.Conclusions. Automatic exchange of information should be developed in compliance with the principle of balance between tax transparency and confidentiality. States should follow one and the same approach to providing such a balance. At the same time the taxpayers’ rights, in particular the rights of Accidental Americans, should be protected and they can’t be outweighed by the need of administrative cooperation between or among tax authorities.

Background. The work is devoted to the study of the possibility of automatic identification of vessels. Such systems, by exchanging data on the meta-position and parameters of the movement of carriers, have the ability to more accurately calculate the parameters of the approach and the location of the object, transmit the position of the vessel so that other vessels nearby know about its location. Materials and methods. Materials from open Internet sources, simulation modeling, data analysis, systems theory, system approach were used. Results. The main directions of application of automatic identification in maritime transport are presented. The analysis of the prospects of using this technology is carried out. Conclusion. According to the results of the study, the effectiveness and relevance of using the system in real time using the “SEATRACKER” service is shown. The advantages and disadvantages of the main systems used in maritime navigation are considered.

The article describes a numerical-analytical model for gas breakthrough to a well during the development of oil fields with a gas cap using horizontal wells. The employed semi-analytical model allows describing the process of gas cone development and reproducing oil and gas production parameters from the well by matching to the actual production history using several coefficients. The numerical scheme of the model was implemented as a computational library in the Python 3.6 programming language.The algorithm was tested on oil deposits with a gas cap in the South Yamal oil and gas region and showed good results in history matching and forecasting calculations. The average calculation time of one iteration being less than 10 seconds allows for multiple model run scenarios using optimization algorithms for automatic calibration to actual production data. The results of the testing show the possibility of achieving satisfactory convergence using automated calibration to the production history. The developed algorithm reduces the workload of specialists in forecasting production, thereby enhancing the effectiveness of decisions made for development optimization.

The features of building on the basis of programmable logic integrated circuits of “arbiter” physical unclonable functions (APUF) are considered. The problem of asymmetry of pairs of APUF paths is indicated and the negative impact of this phenomenon on their characteristics is noted. A time measuring system based on a ring oscillator scheme, which is used to analyze the time characteristics of APUF paths, is described. A method for automatic balancing of signal propagation delays through the APUF paths based on the calculation of the corrective value is proposed. The consistency of the proposed balancing technique is experimentally confirmed based on the improvement in the characteristics of the APUF after its implementation. A digital scheme of this technique is presented, which can form the basis for the development of a delay auto correction scheme through APUF paths with different levels of autonomy.

The paper presents the results of a study of modern text models in order to identify, on their basis, the semantic similarity of English-language texts. The task of determining semantic similarity of texts is an important component of many areas of natural language processing: machine translation, information retrieval, question and answer systems, artificial intelligence in education. The authors solved the problem of classifying the proximity of student answers to the teacher’s standard answer. The neural network language models BERT and GPT, previously used to determine the semantic similarity of texts, the new neural network model Mamba, as well as stylometric features of the text were chosen for the study. Experiments were carried out with two text corpora: the Text Similarity corpus from open sources and the custom corpus, collected with the help of philologists. The quality of the problem solution was assessed by precision, recall, and F-measure. All neural network language models showed a similar F-measure quality of about 86% for the larger Text Similarity corpus and 50–56% for the custom corpus. A completely new result was the successful application of the Mamba model. However, the most interesting achievement was the use of vectors of stylometric features of the text, which showed 80% F-measure for the custom corpus and the same quality of problem solving as neural network models for another corpus.

The paper examines automatic methods for classifying Russian-language sentences into two classes: ironic and non-ironic. The discussed methods can be divided into three categories: classifiers based on language model embeddings, classifiers using sentiment information, and classifiers with embeddings trained to detect irony. The components of classifiers are neural networks such as BERT, RoBERTa, BiLSTM, CNN, as well as an attention mechanism and fully connected layers. The irony detection experiments were carried out using two corpora of Russian sentences: the first corpus is composed of journalistic texts from the OpenCorpora open corpus, the second corpus is an extension of the first one and is supplemented with ironic sentences from the Wiktionary resource. The best results were demonstrated by a group of classifiers based on embeddings of language models with the maximum F-measure of 0.84, achieved by a combination of RoBERTa, BiLSTM, an attention mechanism and a pair of fully connected layers in experiments on the extended corpus. In general, using the extended corpus produced results that were 2–5% higher than those of the basic corpus. The achieved results are the best for the problem under consideration in the case of the Russian language and are comparable to the best one for English.

Introduction. Near-infrared fluorescence imaging technology is widely used in laparoscopic surgery. Intraoperative fluorescence navigation is based on accurate segmentation of fluorescent regions in near-infrared images (NIR images), thus increasing the accuracy and safety of surgical intervention. Moreover, it is an important auxiliary technology for laparoscopic surgery. Therefore, the search for an automatic method that allows for accurate segmentation of fluorescent regions in NIR images can contribute to an improved efficiency of intraoperative navigation.Aim. Development of a method for automatic segmentation of fluorescent images obtained in the near infrared range. Materials and methods. The proposed method consists of two stages. At the first stage, a preliminary segmentation of the image is performed based on the adaptive threshold found by Otsu’s method. At the second stage, the segmented area is refined using Otsu’s weighted method. The main advantage of the proposed method consists in the automatic determination of parameter α, which determines the performance of Otsu’s weighted method. Experiments were carried out using 276 actual laparoscopic images. The metric misclassification error (ME) was used to assess the quality of segmentation.Results. The average ME of the proposed method was found to be 10.4 %, compared to that obtained by the conventional Otsu’s method of 27.1 %.Conclusion. In comparison with Otsu’s method, the developed method shows an increased efficiency and accuracy of fluorescent image segmentation. This allows for a higher diagnostic accuracy and a more efficient navigation during laparoscopic surgery.

The article is devoted to the modernization of typical cascade automatic control systems with stabilizing and corrective PI controllers. Such automatic control systems, in addition to the main signal (of adjustable value), use an additional leading signal that reacts to the disturbance faster than the main one. The leading signal effectively compensates for internal disturbances arising in the system by adjusting the stabilizing controller. The temperature control system of superheated steam boiler units of thermal power plants may be taken as an example. The task of determining the configuration parameters of such dual-circuit systems is quite difficult. With a relatively low inertia of the internal circuit, the speed of the stabilizing controller is quite high, and transients in it do not affect the quality of regulation in the external circuit with a corrective controller. This makes it possible to calculate the optimal settings of the latter only by the dynamic characteristics of the inertial section using conventional methods developed for single-circuit systems. The main disadvantage of such automatic control systems is that they do not allow, with close inertia of the contours, to significantly improve the quality of working out the main impacts during the jump of the task, internal and external disturbances. To eliminate this drawback, an invariant cascade automatic control system with an internal model is proposed that takes into account the dynamics of both the internal and external contours with an inertial section of the object when choosing the structure and setting up the corrective controller. In this case, the internal model is used to fully compensate for the main feedback of the system when working out the task signal, as well as to isolate an equivalent external disturbance, for which an invariance differentiator is used to compensate. The invariant cascade automatic control system makes it possible to significantly increase the speed and accuracy compared to the standard one.

Based on the analysis of foreign publications, a number of new scientific results are presented in the field of hydrodynamics of working fluid flows in torque converters (TC) of automatic hydromechanical transmissions (AHMT), including cavitation in TC, which were obtained using the new CFD (Computational Fluid Dynamics) technology as part of research to reduce the vibroacoustic loading of AHMT. CFD modelling methods have shown that cavitation in a TC, along with the creation of noise and vibration, significantly degrades its characteristics (in the example given, the transformation coefficient is by 18.1 %, efficiency is by 5.8 %, turbine torque is by 20.3 %), and also creates high-frequency oscillations in a wide range that can resonate with the natural frequencies of the AHMT components. The influence of structural and operational factors on cavitation is investigated. The greatest cavitation occurs on the blades of the TC stator in stop mode when the car accelerates from a standstill. The results of CFD modelling are in good agreement with experimental data. CFD technology has become an effective tool for optimizing the design of an automotive TC, its blade system, flow part, visualization of internal flows, study of the mechanism of occurrence and impact of cavitation. The analysis of methods of attenuation of cavitation is carried out, including the selection and maintenance of the value of the TC recharge pressure. The presented provisions in Russian are published for the first time.

This article outlines the process of creating an automated system for knowledge graph construction from collections of mathematical documents in LATEX format. The MathCollectionOntology, which defines the types of objects and relationships in knowledge graphs, was developed. The introduced toolkit includes methods for extracting mathematical terms, browsing and identifying document topics, extracting entities from LATEX code, and calculating statistical parameters of the graph. The parsed entities are mathematical terms, topics generated through the Latent Dirichlet Allocation, UDC codes, used formulas, author affiliations, cited literature, and others. The knowledge graph captures each extracted object using specific types of relationships defined in the MathCollectionOntology. Here, a knowledge graph was coined for a collection of articles published in Izvestiya VUZov. Matematika journal (1114 Russian-language documents in LATEX format). The thematic terms of the document topics were described. The quantitative parameters of the constructed knowledge graph were obtained.

The article deals with the development of automated technologies for observing the weather in the polar regions with the help of automatic autonomous meteorological stations. The experience of using the best domestic and foreign samples of this equipment is analyzed, ways of its improvement and development of the observation network are determined.

Objectives. As the scope of personal data transmitted online continues to grow, national legislatures are increasingly regulating the storage and processing of digital information. This paper raises the problem of protecting personal data and other confidential information such as bank secrecy or medical confidentiality of individuals. One approach to the protection of confidential data is to depersonalize it, i.e., to transform it so that it becomes impossible to identify the specific subject to whom the data belongs. The aim of the work is to develop a method for the rapid and safe automation of the depersonalization process using machine learning technologies.Methods. The authors propose the use of artificial intelligence models to implement a system for the automatic depersonalization of personal data without the use of human labor to preclude the possibility of recognizing confidential information even in unstructured data with sufficient accuracy. Rule-based algorithms for improving the precision of the depersonalization system are described.Results. In order to solve this problem, a model of named entity recognition is trained on confidential data provided by the authors. In conjunction with rule-based algorithms, an F1 score greater than 0.9 is achieved. For solving specific depersonalization problems, a choice between several implemented anonymization algorithm variants can be made.Conclusions. The developed system solves the problem of automatic anonymization of confidential data. This opens an opportunity to ensure the secure processing and transmission of confidential information in many areas, such as banking, government administration, and advertising campaigns. The automation of the depersonalization process makes it possible to transfer confidential information in cases where it is necessary, but not currently possible due to legal restrictions. The distinctive feature of the developed solution is that both structured data and unstructured data are depersonalized, including the preservation of context.

Background. The organizational structure of a multi-agent system includes many roles of agents, their horizontal and vertical connections, components that control their behavior, as well as rules for their functioning. The efficiency of a multi-agent system largely depends on the choice of organizational structure. During the operation of the MAS, situations are possible (for example, a significant change in environmental parameters) that require its reorganization to be performed automatically. However, existing solutions in this area have a number of significant disadvantages. The object of research is multi-agent systems. The subject of the research is methods for reorganizing the structure of a multi-agent system. The goal of the work is to develop a method for automatically reorganizing the structure of the MAS in a complex, partially observable, dynamic environment. Materials and methods. Simulated hardening algorithm, reinforcement learning paradigm methods. Results. As a result, a method was developed for automatic reorganization of the structure of multi-agent systems, initiated when environmental parameters change, based on the use of a simulated hardening algorithm and a reinforcement learning paradigm. Conclusions. The developed method can find its practical application in the implementation of the following tasks: inspection (or patrolling) of infrastructure facilities by mobile robots; implementation of artificial intelligence in computer games.

The analysis of various means and methods for automatic fire extinguishing of gas-cylinder cars is carried out. From the previously performed analysis of accidents of gas-cylinder cars, it follows that they may be characterized by small leaks of the liquid phase or gas medium. Large fuel leaks, as follows from the statistics, are unlikely. In case of large leaks of the liquid phase and its ignition, if this happens, it is necessary to create conditions for complete burnout of fuel that is safe for the environment while monitoring non-proliferation beyond the combustion zone. In accordance with this concept, the choice of means and method for fire extinguishing of the gas cylinder car should be carried out. For use on gas-cylinder cars, only modular installations with the use of various fire extinguishing compositions can be considered as automatic installations, with the exception of water and water-based extinguishing agents in winter conditions.

The work is devoted to control systems for hybrid heat pumps using the heat of return network water and outside air, designed to operate in district heating systems based on CHPP. The aim of the research is to develop control systems for heat pump operating on qualitative, quantitative and quantitative-qualitative heat schedules. The set goal is achieved by introducing two con-trolled heat exchangers: one of "refrigerant-water" type, installed after the evaporator and "re-frigerant-air" type, installed after the gas cooler. The most important results are the hydraulic scheme of the heat pump, the control system scheme of gas superheater installed after the evap-orator and gas supercooler installed after the gas cooler. The significance of the obtained results consists in obtaining a technical solution, which ensures the operation of the heat pump at dif-ferent heating schedules. Equations of heat pump apparatuses have been obtained, in which the influence of flow rate and temperature of the working body on the heat pump operating mode is emphasized. The obtained heat balance equations allowed obtaining structures of automatic con-trol systems for heat exchange apparatuses, compressors and controlling valves of the hybrid heat pump. The developed scheme of the heat pump air duct allowed using a minimum of heat of return network water in the heat pump. It is established that the scheme of this automatic con-trol system should include a functional converter linking the temperature of the outside air and the coordinates of the working body state at the outlet of the gas subcooler.

There is a global tendency nowadays in the development of transport vehicles to ensure high safety, energy efficiency and comfort, characterized primarily by ergonomic and vibroacoustic indicators. This forces engineers and scientists to constantly strive to reduce a noise level emitted by both the vehicle as a whole and individual units and systems. The paper is a continuation of a series of articles devoted to the development of a verified mathematical model of a promising automatic transmission (AT) for a N2 category vehicle, reliably characterizing its vibroacoustic behavior. The article represents the results of a computational and experimental study of the AT vibroacoustic behavior, including the stages of testing, processing and analysis of their results, verification of the computational model created in the Simcenter 3D software product, identification of the main sources of acoustic radiation and the development of proposals for its reduction. The vibroacoustic characteristics of the object of study are obtained, namely frequencies and corresponding acoustic pressure values, their localization on the AT housing is performed. The developed and verified AT model makes it possible to predict the level of vibration and acoustic radiation with satisfactory accuracy. Based on comparative evaluation modeling of various design modification options, the best ones are determined, which allow to obtain the minimum acoustic pressure level at the measurement points and neutralize the most significant forms of vibrations. The introduction of the developed scientifically-based technical solutions into the design made it possible to reduce the integral level of acoustic pressure in the entire range from 2 to 10 dBA.

The article considers the main factors limiting the use of automatic release technology in electronic customs declarations. The directions of further development of the potential of the investigated technology in the conditions of digitalisation, automation and intellectualisation of customs administration in the Russian Federation have been proposed. In order to expand the coverage of the declaration array by automatic release technology, the main directions for improving the automation mechanism at the release of goods have been designated, trends of automation of customs operations and its influence on the development of foreign economic activity have been defined. The methodological basis of the study was fact-finding, analysis and synthesis, induction and deduction, system and process approaches, logical and statistical methods.

PURPOSE. To develop a variant of the algorithm for the automatic input of the reserve, which consists in transferring the load in case of emergency situations, to make a simulation model in the MatLab® environment corresponding to the developed generalized electrical scheme of the system.METHODS. When solving the problem, the method of digital modeling was used, which consists in the maximum approximation of the system under study to a real object, implemented by means of MatLab.RESULTS. It is proposed to study the methods of synthesis of digital models of compensation of voltage drops by the example of a study of an automatic reserve transfer system, demonstrating an approach to modeling this system. When developing models in the MatLab environment, the parameters of real technical elements and devices and their digital analogues are taken into account. The issue of creating a digital model of an electric drive system, including a model of an asynchronous motor with a short-circuited rotor, is considered. The result, after final refinement, can be used to design a real system in production conditions.CONCLUSIONS. The developed model of the automatic transfer switch system is operable, the time indicators are satisfactory for systems that do not make excessive demands on performances and time intervals. For systems that are sensitive to current inrushes during load transfer, some improvements are required, which are reduced to the implementation of a high-speed automatic switch system. The development of this system is currently at the research stage, namely, the compilation of a load transfer logic that takes into account the phase matching of electrical circuits.

The development of finite state machines and the synthesis of neural networks come with enormous computational difficulties. The problems that are faced both by the creators of control finite state machines and the creators of neural networks are almost the same. In order for a control finite state machine to be implemented, an algorithm for its operation must be created, and then a program must be written, and finally this program must be implemented in hardware in the form of a finite state machine. It is crucial to create a finite state machine, which will be deterministic. As for neural networks, it is necessary either to set the weights on its edges with the help of experts, or it must be trained to obtain optimal weights on its edges. Both tasks, that is, the determination of finite state machines and the training of neural networks, are currently most often performed using approximate (exponential or genetic) algorithms. At the same time, few authors point out the fact that, firstly these algorithms give an error of up to 15 %, and secondly the operating time is quite long and requires large energy costs. The article has proven that control finite state machines and neural networks are equivalent based on their structure, which can be represented as a directed edge graph. Such equivalence makes it possible to use methods of normalizing arbitrary graphs to determine finite automata and synthesize neural networks. Methods of graph normalizing are extremely new, they are based on a fundamentally new approach of the extension of graph theory and will allow performing these operations using algorithms that have linear complexity or can significantly reduce the number of options when using brute force.

Background. Existing methods for studying intrauterine distress, despite their prevalence, still have their limitations, so studying and assessment of fetal movements during ultrasound diagnostics can become a convenient and affordable additional tool for diagnosing this pathological condition. The aim of the study. To assess the prevalence and diagnostic significance of a known set of fetal facial movements for the timely determination of intrauterine distress. Methods. This prospective single-center study included 225 fetuses of a gestational age from 32 to 40 weeks. The FIGO chart was used as fitting criteria of intrauterine distress. The assessment of facial movements in all fetuses was carried out using the BabyFACS technique, where the action unit (AU) used for the assessment; its coding is carried out in strict accordance with the chart of motor descriptors (MD). Statistical data processing was carried out using SPSS Statistics 20 (IBM Corp., USA). The Mann – Whitney test was used as the main statistical parameter, where a threshold level of 0.05 was chosen to interpret the p-tests value. Results. Despite the occurrence of AU1, AU2, AU3, AU4 in both groups, these MDs were recorded in the group with confirmed distress (p = 0.00001). Facial units such as AU9 and AU20 were found only in children with intrauterine distress, which, in the total amount of the MD assessment, can be considered one of the main search signs that specialists should first of all pay attention to. All motor descriptors showed high positive predictive value and diagnostic sensitivity, with the highest results registered for AU9 and AU20. Conclusion. Assessment of facial units during ultrasound diagnostics can be a convenient tool as an additional diagnosis of the development of intrauterine distress and requires further study.

Background. Diabetic retinopathy is a very common, debilitating disease that requires early diagnosis and treatment. The development of new screening methods is a priority area of medicine in recent years. Purpose: Approbation of the software (SW) based on algorithms for automatic segmentation of signs of DR “Retina AI” in clinical practice, the study of the capabilities of the software “Retina AI” in the diagnosis of vision-threatening DR.Methods. Analysis of clinical data obtained from patients undergoing diagnostics and treatment at the Federal Research and Clinical Center for Specialized Types of Medical Care and Medical Technologies of the Federal Medical and Biological Agency of Russia and the Moscow Regional Scientific Research Clinical Institute. 123 photographs of the fundus were analyzed using the RETINA.AI platform. Fundus photography was carried out using a fundus camera VISUCAM 500 (Zeiss).Results. In the process of analyzing fundus photographs with Retina AI algorithms, a high efficiency of automatic detection of vision-threatening retinopathy was revealed. The accuracy of the method in diagnosing vision-threatening DR was 95 %, sensitivity — 96.59 %, specificity — 91.4 %, ROC AUC — 0.94.Conclusion. The DR diagnostic program based on adaptive segmentation algorithms is a tool for solving the DR screening problem.

Aims. To compare the efficacy and safety of semiautonomous Adaptive Support Ventilation (ASV) and fully automated (closed-loop, Intellivent-ASV) mechanical ventilation and oxygenation versus conventional mechanical ventilation mode during respiratory support in cardiac surgery patients.Material and methods. In this study, 40 adult patients were ventilated by conventional mechanical ventilation managed by 8 physicians (control group), whereas other two groups patients were ventilated by Intellivent-ASV (n=40) or in a semiautomatic ASV mode (n=40). The groups received standard care, except for the modes of ventilation.Results. In the Intellivent-ASV group, the number of manual changes in ventilator settings was significantly lower: 0 (0–0) versus 2 (2–3) (ASV) and 4 (3–5) in the control group (P