Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering最新文献

{"title":"Computer Аssessment of the Risk of Нerniated Protrusions of the lntervertebral Discs of the Neck Based on MRl Data","authors":"E. S. Mokhova, A. Kolsanov","doi":"10.21869/2223-1536-2024-14-1-148-160","DOIUrl":"https://doi.org/10.21869/2223-1536-2024-14-1-148-160","url":null,"abstract":"The purpose of the research is assessment of the risk of herniated protrusions of intervertebral discs C4-C5, C5-C6 and C6-C7 of the cervical spine according to MR/ examination.Methods. Тhe biomechanics of the physiological processes of this department has been studied on the basis of MR/ data. A computer program «A method for assessing the risk of herniated protrusions of intervertebral discs of the cervical spine based on the results of an MRI examination» has been developed and tested. The measurements required for the above assessment were obtained during the evaluation of the MR/ examination of a particular patient, after which the data was entered into the program. Тhe calculation results were compared with the database previously obtained by the authors in the course of experimental and clinical studies.Results. Тhe model we use correctly describes the mechanical features of the vertebral junction, since it takes into account the most significant features of their structure, which affect the change in the length of the arms of the levers and the force of pressure on the center of the intervertebral disc. Based on magnetic resonance imaging data, the height of the intervertebral disc at the level of the anterior edges of the vertebral bodies and the АV value were determined, and tg was calculated. For a particular patient, the risk of intervertebral disc protrusion was obtained at the C4-C5, C5-C6 and C6-C7 levels.Conclusion. Тhe test results of the program for assessing the risk of developing an intervertebral disc protrusion in the cervical spine make it possible to describe dynamic phenomena in the cervical spine and predict an unfavorable outcome of pathology at the preclinical stage, even in the absence of clinical manifestations.","PeriodicalId":166124,"journal":{"name":"Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering","volume":"343 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140703010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Model of a Prototype Expert System for the Formation of a Simple Classifier of Competencies","authors":"A. V. Brezhnev, S. D. Dorozhkin, P. S. Tivikov","doi":"10.21869/2223-1536-2024-14-1-130-147","DOIUrl":"https://doi.org/10.21869/2223-1536-2024-14-1-130-147","url":null,"abstract":"The purpose of the research is to describe the process of creating an expert system that compares competency models and professional standards with the current needs of the labor market.Methods are based on an analysis of the principles of developing competencies and include a systematic analysis of labor market requirements, the use of methods for comparative analysis of graduates’ competencies and the needs of employers using statistical data. Тhe research is aimed at solving the fundamental problem of matching the skills of specialists with the needs of the labor market. Аs part of this work, an extensive search of data sources was carried out, including an analysis of graduate employment reports and requirements for specialists, during which a discrepancy between the competencies of graduates and the needs of employers was identified.Results. Аs a result of the research, a unified database was created containing information about universities, their areas, competencies and graduates, as well as requirements for the future expert system were formulated, its architecture was developed, and a model for representing knowledge about compliance was described. Тhis system will be able to provide recommendations for improving competencies based on a comparison of labor market requirements.Conclusion. Тhe expert system created on the basis of this work provides operational capabilities for solving issues of matching supply and demand in the labor market, will increase the effectiveness of training, and will help meet the needs of employers for experienced specialists. Тhis concept has several positive aspects, such as increasing the efficiency of training, reducing time resources, publicity and accessibility. Such a system will increase the competitiveness of applicants, as well as satisfy organizations in need of experienced specialists.","PeriodicalId":166124,"journal":{"name":"Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140703208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accounting and Monitoring System of Electricity Expenditures Based on Geospatient Data Consumers Location","authors":"T. I. Lapina, V. S. Malykhina, R. A. Krupchatnikov","doi":"10.21869/2223-1536-2024-14-1-88-103","DOIUrl":"https://doi.org/10.21869/2223-1536-2024-14-1-88-103","url":null,"abstract":"The purpose of the research is considers the development and implementation of a system of accounting and monitoring of electricity costs with visualization of geospatial location data by consumers, which provides technical accounting and analysis of the structure of electricity consumption, estimation of electricity consumption for the tasks of planning production volumes and purchasing electricity from producing companies based on consumer expenditure statistics, prevention of losses associated with unauthorized electricity extraction.Methods. When creating a project and software implementation of a system for monitoring and controlling energy consumption, methods of system analysis, methods of designing software for information systems, a unified object-oriented modeling language Unified Modeling Language (UML), DBMS SQLServer, development environment Microsoft Visual Studio Code (VS Code.) were used.Results. During the project, software for a monitoring and control system for electricity consumption with visualization of geospatial data on the location of consumers was developed and implemented.Тhe project was implemented, tested and introduced into the activities of JSC АtomЕnergoSbyt when planning and accounting for electricity supplies to consumers.Тhe testing results showed that the software system fully satisfies the functional requirements, is ready for use and was demonstrated at the exhibition center.Conclusion. А system for recording energy consumption data with visualization of the territorial location of consumers has been developed in order to control consumption and payments. Тhe developed system will solve the problem of delay in receiving readings from metering devices in the data collection system. Visualization of energy resource con- sumption data by objects and their territorial location with linked personal accounts, meters and consumption volumes will allow you to quickly control the volume of supplies and energy consumers. availability of payment, which will reduce unproductive losses and unauthorized connections.For the company JSC Аtomenergosbyt, operational visualization of consumer data makes it possible to analyze the coverage of consumers by territorial basis and plan new connections.","PeriodicalId":166124,"journal":{"name":"Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering","volume":"48 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140705178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analytical Modeling of Breast Elastography","authors":"D. А. Kravchuk, N. N. Chernov, A. I. Michralieva","doi":"10.21869/2223-1536-2024-14-1-104-113","DOIUrl":"https://doi.org/10.21869/2223-1536-2024-14-1-104-113","url":null,"abstract":"The purpose of the research is to develop a method for assessing the level of nonspecific protection of the body. Тhe purpose of the research. Тo develop an analytical method based on micromechanics to determine the location, size and modulus of elasticity of a tumor mass embedded in symmetrical double-dimensional breast tissue and obtain a closed solution for deformation elastograms.Methods. Changes in tissue elasticity usually correlate with pathological phenomena. Many cancers, such as scirrhous carcinoma of the breast, appear as extremely hard nodules that result from increased stromal density. Other diseases include deposits that increase or decrease tissue elasticity. Complex fluid-filled cysts may not be visible on standard ultrasound, but may be much softer than the embedded tissue. Тhe elastic moduli of tumors change during their pathological evolution. Еlastographic imaging has the potential to detect and characterize cancers by mapping tissue stiffness distribution. Тhe work developed a model of the mammary gland in the form of a two-dimensional layer of unit thickness with a round tumor, taking into account boundary conditions. Local elastic responses were obtained when an acoustic field was applied.Results. Тo evaluate the possibilities of determining the quantitative values of the elastic modules of the medium, we proposed a model of the process of deformation of heterogeneity under the conditions of ultrasonic static elastography and investigated the influence of elastic moduli and deformation of heterogeneity in the direction of applied pressure. Conclusion. Тhe developed technique made it possible to obtain an analytical solution for the field of deformations and stresses of two-dimensional models of mammary glands containing inhomogeneities. Тhe model makes it possible to use the developed methodology for constructing medical elastographic devices and conducting research in the field of elastography.","PeriodicalId":166124,"journal":{"name":"Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering","volume":"12 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140705331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Model of lnformation Support for a Regional Operator for the Management of Municipal Solid Waste","authors":"D. V. Alexandrov, A. A. Gulamov","doi":"10.21869/2223-1536-2024-14-1-114-129","DOIUrl":"https://doi.org/10.21869/2223-1536-2024-14-1-114-129","url":null,"abstract":"The purpose of the research is to compile a modern model of information support for a regional operator for the management of municipal solid waste and analyze the requirements for this system.Methods are based on various publications of reports by environmental operators, the public law company \"Russian Еcological Operator\" (РРK RЕO), on legislative documentation, research and software solutions (SТЕC Housing and Рublic Utilities, Sirena Housing and Рublic Utilities, Еlectronic Тrading Рlatform RЕO) in terms of automation of waste removal.Results. А modern information model for data exchange in the network of a regional operator for the management of solid waste has been built, which meets the needs of the industry. Based on the legislation, the study included recom- mendations for the work and functioning of departments. Ready-made solutions for automating the work of a regional operator for the removal of municipal solid waste are presented. Аn algorithm has been developed for the functioning of the system to send data on the amount of municipal solid waste (MSW) arriving at the landfill in accordance with the new requirements for automatic monitoring of waste accepted at the landfill.Conclusion. Тhe implementation of a modern level of information support for a regional operator for the management of municipal solid waste is relevant, not only from an environmental point of view, the formation of an integrated effective approach to waste management, but also from information security. Organizing the work of a regional operator for the management of municipal solid waste is a process that requires modern information support. Тo carry out the process of building competent logistics, infocommunication kits and data transmission systems are used to track vehicles trans- porting waste. Software is used to monitor the level of vehicle load, the total amount of waste removed, fuel consump- tion, analyze the load and condition of landfills with solid municipal waste, waste separation and recycling processes.","PeriodicalId":166124,"journal":{"name":"Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering","volume":"7 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140706275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated Classification of Abdominal Ultrasound lmages of the Pancreas Based on the Spectral Representation of the Border’s Contours","authors":"A. Kuzmin, A. Y. Sukhomlinov, Al-Darraji Chasib Hasan, R. A. Tomakova, S. D. Dolzhenkov, L. V. Shulga","doi":"10.21869/2223-1536-2024-14-1-67-87","DOIUrl":"https://doi.org/10.21869/2223-1536-2024-14-1-67-87","url":null,"abstract":"The purpose of the research is to develop a methodology for classifying complexly structured halftone images based on a multimodal approach using methods of morphological analysis, spectral analysis and neural network modeling.Methods. А method for classifying the contours of the boundaries of segments of a complexly structured image is described. Тhe method is based on the fact that in chronic diseases of the pancreas, there is a violation of the integrity of the contour of its border and its waviness increases due to retractions and bulges caused by an alterative inflammatory process. Тhe method includes the stages of normalization of ultrasound images and image segmentation with the selection of the contour of the object of interest. Тo classify the contour of a segment boundary, it is proposed to use Fourier analysis and neural network technologies. Тhe method is illustrated using the example of classifying the contour of the border of the pancreas on its transcutaneous acoustic image.Results. Еxperimental studies of the proposed methods and means for classifying medical risk were carried out on diagnostic tasks according to the following classes: \"chronic pancreatitis\" – \"without pathology\". For experimental studies, video sequences of ultrasound images of the pancreas provided by an endoscopist were used. Тhe purpose of the experimental studies was to analyze the classification quality indicators of image classifiers with class segments \"Chronic pancreatitis\" and \"Without pathology\". Тhe training sample of video images (frames of video sequences) included 200 examples, one hundred from each class. Тhe quality indicator \"Sensitivity\" of classification for two classes is 85,7%, the indicator \"Specificity\" is 87,1%.Тhe use of the contour analysis method in classifiers of ultrasound images of the pancreas opens up new opportunities for accessible and objective diagnosis of pancreatic diseases, expanding the capabilities of intelligent clinical decision support systems.","PeriodicalId":166124,"journal":{"name":"Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering","volume":"88 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140704752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic Particle Recognition Based on Digital lmage Processing","authors":"E. S. Oparin, M. A. Dzus, N. Davydov, K. S. Khorkov","doi":"10.21869/2223-1536-2024-14-1-50-66","DOIUrl":"https://doi.org/10.21869/2223-1536-2024-14-1-50-66","url":null,"abstract":"The purpose of the research is to develop and compare various methods and algorithms for effective particle analysis based on their visual characteristics. Тhe purpose of this article is to develop and compare various methods and algorithms for effective particle analysis based on their visual characteristics. Тhe paper considers two fundamentally different approaches: the analysis of grayscale gradients and the machine learning method.Methods.Тhe research methodology includes the analysis of particle images obtained by precipitation from colloidal solutions after laser ablation and images of powder particles for selective laser melting. Тhe materials were obtained using a Quanta 200 3D electron microscope (FЕ/). For the analysis, threshold brightness binarization, contour recognition methods by the Kenny operator and the Hough algorithm are used to combine boundary points into connected contours. For comparison, the U-Net neural network solution was used, and a dataset generator was created to train the neural network. Hand-cut images of aluminum alloy powder particles and micro and nanoparticles of various metals are used as data for generation.Results.Тhe results of the study show that the Hough method provides recognition of the number of particles at the level of 80%, and the machine learning method achieves 95% accuracy in recognizing the shape of particles. Both methods can be used to analyze microand nanoparticles, including irregularly shaped particles.Conclusion.Тhe findings of the work confirm that neural networks are the optimal solution for automatic particle recognition in digital images. However, in order to create a dataset of sufficient volume, it is necessary to develop a generator of labeled images, which requires a detailed study of the subject area.","PeriodicalId":166124,"journal":{"name":"Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering","volume":"20 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140708899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"lnvestigation of the Effect of a Mechanical Stress Concentrator on the Processes of Occurrence and Development of Cracks in Structural Elements of Aviation Equipment","authors":"I. I. Sizonov, E. L. Lebedev, A. N. Popov, I. E. Mukhin","doi":"10.21869/2223-1536-2024-14-1-36-49","DOIUrl":"https://doi.org/10.21869/2223-1536-2024-14-1-36-49","url":null,"abstract":"The purpose of the research is investigation of the patterns of crack development in structural elements of aviation equipment from a stress concentrator under the influence of a force stretching along the main axis, symmetrical alternating loads (vibrations) and combined effects in order to determine the criticality of operation of aircraft products with crack-type defects, substantiation or refutation of the need for research and operation of the processes of development of stress-strain states preceding the occurrence of a crack, in systems and complexes of periodic, preflight and operational control of the technical condition of aircraft products.Methods. Еxperimental study of the patterns of crack development from a stress concentrator in structural elements of two form factors: a cylindrical sample (GOSТ 25347-82) simulating a stringer or a load-bearing structural beam, and a plate sample (GOSТ 1497-84), simulating an aircraft skin element. Cylindrical samples were subjected to deformation caused by the kinetics of rotation, plate samples were subjected to uniaxial tensile stress and the effects of alternating loads (vibrations) individually and in combination.Results. Тhe patterns of near-surface and deep crack development, their relationship with the frequency of application of symmetric alternating loads, have been studied. Еxpressions are established for the approximate engineering calculation of the material endurance limit, fracture surface area and constant endurance with an approximation accuracy Proceedings of the Southwest State University. Series: Control, Computer Engineering, of about 0.8. For samples in the form of flat plates, a stress-strain diagram is constructed, clearly illustrating the decrease in the endurance of the material to the effects of combined loads in relation to the effects of static tensile stresses only. Тhe approximate number of residual cycles before the structural element is destroyed is estimated, taking into account the amplitude-frequency parameters of the acting vibration in the presence of a crack in the sample. Тhe estimation method using the load intensity coefficient and mathematical expressions for its calculation is given.Conclusion. /t is concluded that it is necessary to analyze the dynamics of the development of stress-strain states (fatigue) of the material as states preceding the appearance of cracks in order to carry out sufficient control of the technical condition of structural elements of aircraft products.","PeriodicalId":166124,"journal":{"name":"Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering","volume":"66 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140707746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Methods for Assessing Renal Нemodynamics after Minimally lnvasive Treatment of Urolithiasis","authors":"I. M. Kholimenko, S. P. Seregin, S. N. Rodionova, A. V. Pugzhilis","doi":"10.21869/2223-1536-2024-14-1-24-35","DOIUrl":"https://doi.org/10.21869/2223-1536-2024-14-1-24-35","url":null,"abstract":"The purpose of research. Urolithiasis occupies a leading place among all urological diseases after infectious and inflammatory ones. /n addition, it does not lose its relevance due to the fact that the number of patients with this disease is steadily increasing. Тhe aim of the study is to study the peculiarities of changes in renal hemodynamics after minimally invasive methods of treatment of urolithiasis remote shock wave lithotripsy (DLТ) and percutaneous nephrolithotripsy (РNL) to improve the quality of medical care for urological patients.Methods. Numerous studies have shown in detail the effectiveness of using remote shock wave lithotripsy and percutaneous nephrolithotorypsy in the treatment of kidney stones. Тhese methods are minimally invasive, well tolerated by patients, and reduce the risks of complications, but they are accompanied by kidney injury, in particular, microcirculation disorders. Тhe use of the Dopplerographic method of investigation allows for a highly informative assessment of the degree of impaired renal microcirculation for the diagnosis of urolithiasis, including for the assessment of hemodynamics after minimally invasive treatment methods.Results. Тhe work shows that when using dopplerography of renal vessels after remote shock wave lithotripsy and percutaneous nephrolithotorypsy, a violation of hemodynamics after DLТ is noted in dynamics already on the first day. In addition, the terms of normalization of indicators are longer in comparison with hemodynamics after РNL. Аlso, with РNL, there is a gradual increase in blood flow indicators in the dynamics of the postoperative period.Conclusion. Тhe work shows that ultrasound Dopplerography is an effective method of dynamic assessment of renal blood flow, and the indicator of renal damage is the resistance index, mainly in the interlobular arteries.","PeriodicalId":166124,"journal":{"name":"Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140708977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of the Effectiveness of Using Two-Stage Neural Network Models for Early Detection of Forest Fires","authors":"A. V. Kiselyov, N. S. Brusencev, E. Kuleshova","doi":"10.21869/2223-1536-2024-14-1-8-23","DOIUrl":"https://doi.org/10.21869/2223-1536-2024-14-1-8-23","url":null,"abstract":"The purpose of the research – analysis of the effectiveness of two-stage neural network models for solving the problem of detecting forest fires in images obtained from unmanned aerial vehicles.Methods. А training dataset was synthesized for training neural network models for the purpose of detection and semantic segmentation of forest fires in images. Тwo-stage neural network models (“Faster R-CNN”, “Mask RCNN” and “Retina-Net”) were used for training. Тhe neural network models were trained according to the same parameters set for all models in order to ensure consistency and a common basis for experiments. Optimization of model parameters during the training process was carried out to minimize the classification loss function. Тo synthesize the test sample, we used a video sequence covering the events of forest fires in the /rkutsk region, which was filmed by an unmanned aerial vehicle. Using a specially developed script in the Рython programming language, the process of dividing this video sequence into separate frames was carried out, which were used as a test data set when assessing the quality of classification of trained neural network models.Results. Based on the analysis of the obtained values of the quality criterion, as well as visual analysis on the test data set produced as part of testing neural network models, the effectiveness of the studied models for detecting forest fires in images was assessed. Тo assess the quality of binary classification of neural network models, the quality criterion “Accuracy” (classification accuracy) was used.Conclusion. Еxperimental studies on a test data set showed that the Retina-Net model demonstrates the lowest, but acceptable, performance compared to other studied neural network models. Тhe two-stage neural network models “Faster R-CNN” and “Mask R-CNN” demonstrate similar classification accuracy values (0.9492 and 0.9521, respectively), which allows us to recommend them for use in early detection systems for forest fires.","PeriodicalId":166124,"journal":{"name":"Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140717405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}