The purpose of research is to increase the efficiency of decoding noise–resistant block codes in conditions of a priori uncertainty about the parameters used.

Methods. In modern systems, the use of noise-resistant block codes with a large codeword length is noted, which allows the permitted code combinations to be sufficiently far apart from each other during encoding and to obtain, during iterative decoding, the possibility of their correct determination at low values of the signal-to-noise ratio in the communication channel. The use of long noise-tolerant codes requires a reduction in the complexity of error correction algorithms, which is estimated by the number of operations of various types per decoding iteration. The number of operations of various types will depend on the parameters of the code and the verification matrix, as well as the decoding algorithm used. The practical implementation of the decoder has a number of limitations, and its design is a difficult task, especially in conditions of a priori uncertainty about the applied code parameters. To solve this problem, it is proposed to use the method of determining the applied LBC verification matrix based on the analysis of the received digital sequence.

Results. In the course of the study, a comparative analysis of known methods for determining the parameters of an interference-resistant block code was carried out and a modification of the Gauss method was proposed to solve a system of linear algebraic equations when finding the LBC verification matrix.

Conclusion. The proposed method avoids performing a strict sequence of actions according to the well-known Gauss method, as well as reducing time complexity by paralleling calculations and significantly increasing the efficiency of practical implementation of the algorithm for finding the LBC verification matrix.

The purpose of research is improving the quality of monitoring safety violations in energy facilities of enterprises through the use of a method of automated incident detection in real time, based on the conveyor application of neural network models.

Methods. The article proposes a pipeline neural network model YOLO – Tesseract – YOLO, designed to solve the problem of automated access control and monitoring compliance with safety regulations in real time at energy facilities of enterprises. A method for access control and monitoring compliance with safety regulations at energy facilities of enterprises is proposed, consisting in the pipeline application of neural network models YOLOv8 and Tesseract-OCR using morphological image processing, allowing to classify a group of electrical safety clearances based on recognized patterns in an employee's ID card and detect safety violations when working with electrical installations in real time.

Results. A number of experiments were conducted, during which error matrices were obtained, which made it possible to evaluate the classification quality of the pipeline neural network model using such metrics as Recall, Precision and F1-measure, the metric values were presented for all classes. The value of the F1-measure metric for the YOLO1 neural network model used to evaluate the overall efficiency, equal to 0.98, indicates a balanced relationship between the accuracy and recall of the model. The value of the F1-measure metric for the YOLO2 neural network model equal to 0.73 indicates acceptable results of the model for solving the classification problem in real time, but indicates the need to refine this part of the pipeline neural network model to improve the overall efficiency.

Conclusion. The results obtained during the study indicate an acceptable quality of the pipeline neural network model in solving the problem of automated access control and monitoring compliance with safety regulations in real time. Keywords: monitoring, safety engineering, access control, energy facilities of enterprises, pipeline neural network model, Tesseract-OCR, YOLOv8, classification.

Purpose of research. Digital goods are often innovations compared to their physical counterparts. One of the key technologies that have improved voice interaction with devices is smart home assistants, which have become an important element of digitalization of daily life. The use of the concept of providing such assistants with data in the management of an organization ensures the necessary amount of information storage. The purpose of the research is to develop an information system model to support smart assistants in management, corresponding to the concept of indirect management.

Methods. Methods of system analysis, system engineering and modeling were use Methods. System analysis and modeling methods were used to solve the tasks.

Results. The features of the implementation of providing smart assistants with data when managing an organization based on the provisions of the concept of indirect management are given. The mathematical support of the user query recognition algorithm is presented. The features of the implementation of a data management system for managing an organization based on the concept of indirect management are described. An information system model has been developed that allows one administrator to quickly classify user requests in real time and provide timely and tactical information. In this case, all sets of user requests will be operationally classified and marked in real time.

Conclusion. A model of an information system has been created to support smart home assistants. To administer such a system, one administrator is enough to quickly classify user requests in real time. Practical recommendations on the organization of effective interaction of end users with smart home assistants and similar modern intelligent technologies are presented.

The purpose of research is to develop a mathematical model of a two-link active foot of a rehabilitation exoskeleton for the lower extremities and to obtain data for generating the setting effects on the device drives.

Methods. The article discusses a method for creating reference actions for the drive control system of a two-link foot of a rehabilitation exoskeleton. This device is designed for complex mechanical processing of the ankle joint in order to restore its mobility and bring movements closer to a natural gait. For this purpose, the video trajectory capture method is used in the framework of the experiment, which creates trajectories of movement of characteristic points of the foot taking into account the gait parameters and anthropometry of the patient. When processing the data, a 5th-order Fourier series is used, which allows approximating the obtained experimental trajectories with a given accuracy and ensuring their smoothness.

Results. The work established that the mathematical model of a two-link foot allows analyzing and predicting the movement of the robot's foot in various rehabilitation modes. The model takes into account control and disturbance effects, as well as parameters such as mass, moment of inertia, step length, leg lift height, and other characteristics. The results of mathematical modeling allow synthesizing the robot's drive system - a set of mechanisms that transmit movement from the engine to the foot links. This will help ensure reliable and efficient operation of the device. In addition, the modeling results will be used to design the main structural elements of the robot, such as hinges, fasteners, shock absorbers, etc.

Conclusion. The results of mathematical modeling allow us to calculate the robot's drive system - a set of mechanisms that transmit movement from the engine to the foot links. This will help ensure reliable and efficient operation of the device. In addition, the modeling results will be used to design the main structural elements of the robot, such as hinges, fasteners, shock absorbers, etc. This will allow us to create a durable and long-lasting device that can perform its functions in various operating conditions.

The purpose of research the work is to evaluate the effectiveness and safety of the use of an industrial exoskeleton using EMG in the conditions of modeling labor activity.

Methods. Guided by GOST R 60.5.3.3-2023 and the national standard of the Russian Federation GOST R 60.5.2.1- 2023, a non-invasive technique for the general assessment of the human cardiorespiratory system, electromyography as a key way to assess the bioelectric activity of muscles, as well as conducting interviews with research participants were used.

Results. The data obtained as a result of the study using the selected methods showed significant differences between the registered values of the indicators of volunteers who worked without PE and with its use.

The following results were obtained: during load transfer, the activity of the elbow flexor of the wrist when using IE decreased by an average of 41%, biceps – by 21%; during load retention, the activity of the elbow flexor of the wrist when using IE decreased by an average of 42%, biceps – by 52%.

Endurance experiments showed a 52-42% decrease in muscle activity when using IE, which positively affects the duration of comfortable work, which increased by an average of 2.5 times.

Also, the general physiological condition of the volunteers (pulse, pressure, saturation) when using IE was closer to the standards than without

According to the responses of the volunteers, everyone noticed a slight difference in favor of using IE.

IE's help is especially noticeable after a number of completed approaches.

Conclusion. A study conducted within the framework of the work to determine the effectiveness and safety of the use of PE in the course of work, including to offset the harm from stereotypical work movements, showed a decrease in the activity of the measured muscles when using PE, which also indicates a decrease in human fatigue, which increases the efficiency of his work.

Purpose of research. Nowadays, the digitalization of production is considered as the most important aspect of technological growth to improve the competitiveness of enterprises. An innovative approach combining virtual reality and computer vision technologies into a single tool designed to improve the quality of practice-oriented training in the field of industrial radiography is proposed. Within the framework of the article the research of the most effective models of artificial neural networks in application to the task of detection of defective areas of welded metal joints on radiographic images is carried out. A detailed analysis of the YOLOv8 architecture with respect to the detection of small-sized defects is carried out. A method for synthesizing virtual reality and computer vision technologies in a single educational tool for industrial radiography is described.

Methods. Methods of empirical research, system analysis and synthesis of related information technologies were used in this work.

Results. The empirical study revealed the limited effectiveness of the YOLOv10 model as applied to the generalization of features of objects of small dimensionality and low contrast. YOLOv8 showed more practical results and greater stability when generalizing the contour component of defects. In the process of system analysis of YOLOv8 architecture the loss of spatial information when using sequential convolutional operations preceding upsampling was revealed. Modification of the basic YOLOv8 architecture was performed in order to improve the generalization ability of lowdimensional and low-contrast defects. The methodology of synthesis of virtual reality and computer vision technologies in the form of an intelligent assistant for intellectualization of nondestructive testing process is presented.

Conclusion. The integration of the above synthesis method into a single software product will improve the quality of specialist training and open access to innovative methods of improving professional skills at every stage of a professional career.

Purpose of research. Cardiometry, which has been developing for more than thirty years, has achieved certain results that make it possible to expand the diagnostic capabilities of the ECG. However, the criteria for cardio-metric diagnoses have not yet been included in the regulatory indicators approved by the Ministry of Health. Taking into account the possibilities of cardiometry and the pace of its development, this article provides a comparison of the forecasts obtained by classical and cardiometric methods from the standpoint of interchangeability.

The purpose of research is to compare the cardiological diagnoses made on the basis of ECG obtained by classical and cardiometric methods, using the position of interchangeability.

Methods. In this paper, the principle of superposition is applied, which consists in using one function to process the results of another. The existing classical result is described using a cardiometric function. As a result, in practice there is a logical possibility of moving to a more accurate diagnosis. At the same time, the basis of the classical diagnosis is not destroyed.

Results. A comparative analysis of classical cardiological and cardiometric ECG assessment methods is presented. A total of 11 diagnoses were considered. Specific conclusions and recommendations are made for each comparison. Cardiometry allows a qualitative assessment of: a) The U-wave on the ECG occurs during the early diastole phase. It is associated with the filling of the coronary bloodstream, but the quality of its filling can only be diagnosed using a synchronously recorded rheogram from point T, the end of wave T to the beginning of wave U; b) hyper- and hypocalcemia are evaluated in the S – L phase by the amplitude of the phase; c) hyper- and hypokalemia are evaluated in the L-phase. j by phase amplitude.

Conclusion. This work shows the possibilities of expanding the classical cardiological diagnosis based on an ECG.

The purpose of research is to coordinate the operation of the direction finding channel of radio beacons with the data transmission systems and control of an unmanned aerial vehicle using a remote control.

Methods. Research methods are based on the application of principles of radio electronics, diagnostics and analysis of the technical condition of aircraft. Methods of multicriterial analysis, parametric and structural synthesis were used. The features of direction finding of radio beacons from unmanned aerial vehicles designed to track emergency situations were studied. An analysis of the critical assessment of the maximum range of direction finding of radio beacons from an unmanned aerial vehicle was performed.

Results. Analytical formulas are given for calculating the maximum range of radio beacon direction finding from an unmanned aerial vehicle. The maximum range of radio beacon direction finding is calculated when using 2.4 and 5.8 GHz external antennas on unmanned aerial vehicles used in the Russian Emergencies Ministry and equipped with a digital direction finding system.

Conclusion. The use of direction finding systems on unmanned aerial vehicles (UAVs) provides wide opportunities for application in various fields. This combination makes it possible to effectively detect and track radio sources, which is especially useful in search and rescue operations, environmental monitoring and safety. UAVs equipped with direction finders can quickly cover large areas, providing accurate location of signals that are difficult or impossible to capture from the ground. This makes them indispensable in situations requiring rapid response and high accuracy. In addition, the use of UAVs with direction finding systems reduces the risks to human life, providing the opportunity to perform tasks in hard-to-reach or dangerous areas.

The purpose of the research is to systematize the properties of data centers and to find ways to increase the productivity of a network of centers based on collective access, combining the steps of storing and processing information and its replication.

Methods. The research methods are based on the theory of organization of complex information and analytical systems and artificial intelligence systems. The application of the principles of distributed-territorial organization of centers, deferred data collection, data processing based on computational and analytical models and knowledge representation models allows you to create data center architectures reconfigurable for basic computing processes. To describe the architecture of the upper level, standard and modified information and control cycles of information processing were created and analyzed. Based on graph theory methods, the complexity of the considered cycles is estimated. At the same time, both standard quantitative and structural indicators were used, which made it possible to obtain recommendations on the organization of data centers.

Results. The modified information and control cycle of network information processing is characterized by increased connectivity of vertices and internal processing cycles. A comparison of the calculated average output indicators for standard and modified cycles showed the expediency of combining steps in cycles that simulate certain human cognitive capabilities when processing a large amount of unstructured data (decomposition, aggregation, analysis, generalization). The constructed modified cycle has higher average and relative complexity indicators.

Conclusion. The combination of information storage and processing steps in the information management cycle and the identification of new patterns makes it possible to interpret modern data centers as intelligent network storagesearch engines. The created modified information and control cycle allows iteratively performing the steps of systematization, generalization, and data analysis to obtain new pieces of information. This feature provides an increase in the overall productivity of the Data Center and a reduction in the cost of ownership of information resources.

The purpose of the research is to develop a method for assessing the level of adaptive potential of the central nervous system, which allows improving the quality of decisions made in the tasks of forecasting and diagnosing diseases characteristic of engineering and technical personnel.

Methods. It is shown that the adaptive potential is a fuzzy variable described in the framework of the classical theory of fuzzy logic. Within the framework of this methodology, for the synthesis of decisive rules for assessing the level of adaptive potential of the central nervous system, normalizing functions of the level of adaptation are introduced for indicators selected from a set of test methods describing the state of the system under study, which are aggregated into the desired hybrid fuzzy model. Considering that engineering work is often accompanied by a high level of psychoemotional stress and mental fatigue, a device for monitoring the functions of attention and memory was chosen to assess the state of the central nervous system, which allows forming the volume of initial data necessary to solve the tasks.

Results. In the course of the conducted research, to synthesize the decisive rules for assessing the level of adaptive potential of the central nervous system, taking into account the specifics of the work of engineering and technical workers, a set of informative signs was formed consisting of the level of personal and situational anxiety, concentration of attention and an indicator characterizing the state of RAM blocks, calculated by the method of determining the missing digit. For this set of indicators, the corresponding normalizing functions of the level of adaptation were obtained, the aggregation of which gives the desired fuzzy mathematical model for assessing the level of adaptive potential of the central nervous system.

Conclusion. In the course of the conducted research, a method for assessing the level of adaptive potential of the central nervous system was developed and a corresponding fuzzy model for assessing the level of this potential was obtained, focusing on the peculiarities of the work of engineering and technical workers. During the expert assessment and mathematical modeling, it was shown that the confidence in the correct assessment of the level of adaptive potential of the central nervous system exceeds 0.9.

The purpose of the research to synthesize fuzzy models of early diagnosis of neuroses provoked by risk factors in engineering work that ensure the quality of decisions made is acceptable for practical medicine.

Methods. Analysis of the data structure and the studied classes of neurotic disorders showed that early diagnostic tasks, including early diagnosis of neuroses, belong to the class of poorly formulated tasks. This allows using the methodology of synthesis of hybrid fuzzy decision rules, developed at the South-West State University, as a basic mathematical apparatus. The effectiveness of using this methodology has been repeatedly tested on various problems of forecasting and medical diagnostics with a data structure similar to our problem.

Results. In the course of the research, three levels of checking the quality of the work of the resulting decision-making models were implemented. At the first level, the assessment was carried out by experts by determining confidence levels in the resulting decision rules. At the second level, the experts compiled model control samples, according to which the number of correct and erroneous decisions of the diagnostic model was determined. At the third level of control, control samples were formed in which the presence of early stages was checked using independent generally accepted research methods. The calculations showed that the quality of classification exceeds 0.95.

Conclusion. Fuzzy decisive rules for diagnosing the early stages of neuroses in engineering and technical workers were obtained. provoked by risk factors of engineering work. The assessment of the quality of early diagnosis was carried out using methods of expert assessment, mathematical modeling and statistical analysis and showed that the resulting hybrid fuzzy models provide acceptable quality of early diagnosis of neurotic disorders in engineering and technical workers of various specialties working in conditions of varying work intensity.