Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110813
O. Kuzyakov, S. Sorokina, E. A. Shutova
The article proposes components of a screening system based on the analysis of computed tomography images using convolutional neural networks (CNN), with several strategies for the accurate diagnosis of malignant pulmonary lymphoma nodes. The study provides an analysis of literature data on traditional methods of diagnosing lung pathologies and methods using artificial intelligence technologies. As a result of the study, the functional model and algorithm of the screening system, the DICOM image preprocessing module (Digital Imaging and Communications in Medicine) are presented. A data set for CNN training and testing has been created; the AlexNet CNN architecture has been trained and tested; a module for integrating the results of computed tomography image analysis into the metadata of a DICOM file has been presented.
本文提出了一种基于卷积神经网络(CNN)计算机断层扫描图像分析的筛查系统的组成部分，并提出了几种准确诊断恶性肺淋巴瘤淋巴结的策略。本研究对传统肺部病理诊断方法和人工智能技术方法的文献资料进行了分析。在此基础上，提出了筛选系统的功能模型和算法，并给出了DICOM图像预处理模块(Digital Imaging and Communications in Medicine)。为CNN的训练和测试创建了一个数据集;AlexNet CNN架构已经过培训和测试;提出了一个将计算机断层扫描图像分析结果集成到DICOM文件元数据中的模块。
{"title":"Development of an Automated Diagnostic System of Lung Pathologies in Lymphoma","authors":"O. Kuzyakov, S. Sorokina, E. A. Shutova","doi":"10.1109/SmartIndustryCon57312.2023.10110813","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110813","url":null,"abstract":"The article proposes components of a screening system based on the analysis of computed tomography images using convolutional neural networks (CNN), with several strategies for the accurate diagnosis of malignant pulmonary lymphoma nodes. The study provides an analysis of literature data on traditional methods of diagnosing lung pathologies and methods using artificial intelligence technologies. As a result of the study, the functional model and algorithm of the screening system, the DICOM image preprocessing module (Digital Imaging and Communications in Medicine) are presented. A data set for CNN training and testing has been created; the AlexNet CNN architecture has been trained and tested; a module for integrating the results of computed tomography image analysis into the metadata of a DICOM file has been presented.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130734176","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110834
I. Jumanov, S. Kholmonov
Scientific and methodological foundations for the optimal identification of non-stationary objects based on the use of neural networks have been developed. Models and algorithms for detection, extraction of hidden relationships, useful properties and patterns in data, formation of a database and knowledge bases are proposed. Mechanisms have been developed for using the statistical, dynamic and specific characteristics of images, unique features of three, five-layer neural networks and combined models for setting variables with typical recognition and classification tools. Have been developed computational schemes for determining and adjusting the weights of neurons, choosing a suitable activation function, coefficients of synaptic and interneuronal connections, rational neural network architecture, the number of layers and neurons in the layers of the network, a set of functions of nonlinear dependencies "inputs - outputs". Data pre-processing algorithms are implemented that perform the functions of informative features selection, segmentation, object image contour extraction, search based on methods with annealing, prohibition, and stochastic search. Tested neural networks of Hopfield, Hamming, Hebb, Kohonen, bidirectional associative memory were tested. Schemes for two and three-dimensional image reconstruction based on the synthesis of tools for calculating Mellin transform functions, initial values of centroids, and the formation of a suboptimal set of variables are proposed. The identification software package in C++ was developed and implemented in the CUDA parallel computing environment.
{"title":"Optimization of Micro-object Identification Based on the Mellin Transform and the Use of Parallel Computing","authors":"I. Jumanov, S. Kholmonov","doi":"10.1109/SmartIndustryCon57312.2023.10110834","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110834","url":null,"abstract":"Scientific and methodological foundations for the optimal identification of non-stationary objects based on the use of neural networks have been developed. Models and algorithms for detection, extraction of hidden relationships, useful properties and patterns in data, formation of a database and knowledge bases are proposed. Mechanisms have been developed for using the statistical, dynamic and specific characteristics of images, unique features of three, five-layer neural networks and combined models for setting variables with typical recognition and classification tools. Have been developed computational schemes for determining and adjusting the weights of neurons, choosing a suitable activation function, coefficients of synaptic and interneuronal connections, rational neural network architecture, the number of layers and neurons in the layers of the network, a set of functions of nonlinear dependencies \"inputs - outputs\". Data pre-processing algorithms are implemented that perform the functions of informative features selection, segmentation, object image contour extraction, search based on methods with annealing, prohibition, and stochastic search. Tested neural networks of Hopfield, Hamming, Hebb, Kohonen, bidirectional associative memory were tested. Schemes for two and three-dimensional image reconstruction based on the synthesis of tools for calculating Mellin transform functions, initial values of centroids, and the formation of a suboptimal set of variables are proposed. The identification software package in C++ was developed and implemented in the CUDA parallel computing environment.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123767433","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110785
N. Duc, A. Galimyanov, I. Z. Akhmetov
In this paper, we have developed an artificial neural network (ANN) method for finding solutions to the Dirichlet problem for fractional order differential equations (FODEs) 0 <α<1 using the definition of a conformable fractional derivative. Here, we used a feedforward neural architecture, L-BFGS (Broyden – Fletcher – Goldfarb - Shanno) optimization method to minimize the error function and change the parameters (weights and biases). The main idea is that if the sum of the norms of the residuals of the equation on the domain of definition and the boundary conditions tends to zero when the unknown function y(x) is replaced by its neural network approximation N(x), then N(x) is an approximate solution of the differential equation. Some illustrative examples are given demonstrating the accuracy and efficiency of this method and comparing the results of the current method with mathematical results.
{"title":"Neural Network Method for Solving Fractional Differential Equations α with the Dirichlet Problem","authors":"N. Duc, A. Galimyanov, I. Z. Akhmetov","doi":"10.1109/SmartIndustryCon57312.2023.10110785","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110785","url":null,"abstract":"In this paper, we have developed an artificial neural network (ANN) method for finding solutions to the Dirichlet problem for fractional order differential equations (FODEs) 0 <α<1 using the definition of a conformable fractional derivative. Here, we used a feedforward neural architecture, L-BFGS (Broyden – Fletcher – Goldfarb - Shanno) optimization method to minimize the error function and change the parameters (weights and biases). The main idea is that if the sum of the norms of the residuals of the equation on the domain of definition and the boundary conditions tends to zero when the unknown function y(x) is replaced by its neural network approximation N(x), then N(x) is an approximate solution of the differential equation. Some illustrative examples are given demonstrating the accuracy and efficiency of this method and comparing the results of the current method with mathematical results.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115356320","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110776
A. Ushkov, N. O. Strelkov, V. V. Krutskikh, A. Chernikov
Water covers most of the surface of our planet and is a strategic resource for human activities. The recent decades saw a significant increase in adverse impacts on industrial production on the hydrosphere. Pollution and reduced quality of water resources call for the assessment of waterbody parameters and the clearance of polluted waterways. This article reviews the possibility of technological solution integration with the systems of the industrial Internet of Things to implement the environmental monitoring of water quality and assess the efficiency of water supply filters. The authors developed hardware and software solutions to collect and process the data from the AquaTROLL 600 multi-parameter water quality analyzer. The visualization and tracking of the data are carried out using the algorithms for the transfer of water resource data to a local or an MQTT server. The proposed structure allows for the simple scaling of the metering module and using it under various external impacts. Experimental research showed the efficiency of using industrial Internet of Things platforms for the analysis and protection of the environment.
{"title":"Industrial Internet of Things Platform for Water Resource Monitoring","authors":"A. Ushkov, N. O. Strelkov, V. V. Krutskikh, A. Chernikov","doi":"10.1109/SmartIndustryCon57312.2023.10110776","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110776","url":null,"abstract":"Water covers most of the surface of our planet and is a strategic resource for human activities. The recent decades saw a significant increase in adverse impacts on industrial production on the hydrosphere. Pollution and reduced quality of water resources call for the assessment of waterbody parameters and the clearance of polluted waterways. This article reviews the possibility of technological solution integration with the systems of the industrial Internet of Things to implement the environmental monitoring of water quality and assess the efficiency of water supply filters. The authors developed hardware and software solutions to collect and process the data from the AquaTROLL 600 multi-parameter water quality analyzer. The visualization and tracking of the data are carried out using the algorithms for the transfer of water resource data to a local or an MQTT server. The proposed structure allows for the simple scaling of the metering module and using it under various external impacts. Experimental research showed the efficiency of using industrial Internet of Things platforms for the analysis and protection of the environment.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115658544","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110765
A. Rogachev, E. Melikhova, N. Zolotykh
In the tasks of agricultural production, it is necessary to identify unfavorable situations of agricultural farming that arise in the process of cultivating agricultural crops. These include soil erosion or salinization, damage from crop diseases, pests, and others. Timely and prompt identification of such situations is possible with the use of technical vision and methods of intellectual analysis and image processing. The most effective means of machine learning (ML) for such tasks are deep neural networks (DNN), primarily based on a parallel architecture containing convolutional layers of neurons. The purpose of the study was to build and study the effectiveness of DNN, which are used in intellectual land use tasks. The Python-based Google Collaboration cloud service, including ML libraries, was used as the DNN development environment.. When designing DNN, the features of the functioning of the CPU and GPU were taken into account. The results obtained make it possible to optimize the architecture and hyperparameters of DNN, as well as their training time. This approach increases the efficiency of the information and analytical complexes being developed to support the solution of various land use problems.
{"title":"Building Deep Neural Networks for solving Machine Learning Problems in Agricultural Production","authors":"A. Rogachev, E. Melikhova, N. Zolotykh","doi":"10.1109/SmartIndustryCon57312.2023.10110765","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110765","url":null,"abstract":"In the tasks of agricultural production, it is necessary to identify unfavorable situations of agricultural farming that arise in the process of cultivating agricultural crops. These include soil erosion or salinization, damage from crop diseases, pests, and others. Timely and prompt identification of such situations is possible with the use of technical vision and methods of intellectual analysis and image processing. The most effective means of machine learning (ML) for such tasks are deep neural networks (DNN), primarily based on a parallel architecture containing convolutional layers of neurons. The purpose of the study was to build and study the effectiveness of DNN, which are used in intellectual land use tasks. The Python-based Google Collaboration cloud service, including ML libraries, was used as the DNN development environment.. When designing DNN, the features of the functioning of the CPU and GPU were taken into account. The results obtained make it possible to optimize the architecture and hyperparameters of DNN, as well as their training time. This approach increases the efficiency of the information and analytical complexes being developed to support the solution of various land use problems.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124980219","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110726
F. M. Nazarov, Sherzodjon Yarmatov
Analysis and evaluation of socio-economic processes based on intellectual models leads to effective results. The use of intelligent systems for real estate valuation and price prediction is very important nowadays. As a result, investors can effectively finance their projects. The main objective of this study is to develop Voting ensemble regression and Gradient Boosting Algorithms based on several machine learning algorithms to predict real property prices. Mean absolute deviation (MAE), root mean squared error (RMSE) and coefficient of determination (R-squared) were calculated to check the accuracy of the developed model and algorithms. Algorithms developed on the basis of ensemble methods have been found to give much better results than among the standalone Machine learning models. Based on the developed model and algorithms, an effective method of real estate assessment and price prediction for investors is proposed.
{"title":"Optimization of Prediction Results Based on Ensemble Methods of Machine Learning","authors":"F. M. Nazarov, Sherzodjon Yarmatov","doi":"10.1109/SmartIndustryCon57312.2023.10110726","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110726","url":null,"abstract":"Analysis and evaluation of socio-economic processes based on intellectual models leads to effective results. The use of intelligent systems for real estate valuation and price prediction is very important nowadays. As a result, investors can effectively finance their projects. The main objective of this study is to develop Voting ensemble regression and Gradient Boosting Algorithms based on several machine learning algorithms to predict real property prices. Mean absolute deviation (MAE), root mean squared error (RMSE) and coefficient of determination (R-squared) were calculated to check the accuracy of the developed model and algorithms. Algorithms developed on the basis of ensemble methods have been found to give much better results than among the standalone Machine learning models. Based on the developed model and algorithms, an effective method of real estate assessment and price prediction for investors is proposed.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128888765","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110811
D. Topolsky, A. Belyakov, Veronica Pochinskaia
During the process of decision support system development there is a problem associated with the heterogeneity of the data in terms of relevance, quality and completeness of the research objects description. The solution to this problem is digital twins based on data lake technology implementation. The aim of the work is to create a prototype of an electronic passport (e-passport) of materials as the basis of their digital twin. The digital twin is to contain a set of data on the composition, structure, calculated and experimentally measured properties, participation in the composition of chemical reactions, constructed models and "structure-property" patterns as well. It is proposed to combine the information on a specific material or compound into an information structure — electronic passports of the research object. At the same time, it is advisable to consider the electronic passport as a comprehensive description of the object, including information about the static and dynamic parameters of the atomic-molecular system of the research object. The e-passport as an information object gives a systematic data on the composition of a substance, structure, calculated and experimentally measured properties, the participation of elements in the composition of chemical reactions, constructed models and "structure-property" patterns, thus acting as a generalizing tool convenient for users to present information available in the database of digital twins of materials.
{"title":"Electronic Passport as the Basis of the Digital Twin","authors":"D. Topolsky, A. Belyakov, Veronica Pochinskaia","doi":"10.1109/SmartIndustryCon57312.2023.10110811","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110811","url":null,"abstract":"During the process of decision support system development there is a problem associated with the heterogeneity of the data in terms of relevance, quality and completeness of the research objects description. The solution to this problem is digital twins based on data lake technology implementation. The aim of the work is to create a prototype of an electronic passport (e-passport) of materials as the basis of their digital twin. The digital twin is to contain a set of data on the composition, structure, calculated and experimentally measured properties, participation in the composition of chemical reactions, constructed models and \"structure-property\" patterns as well. It is proposed to combine the information on a specific material or compound into an information structure — electronic passports of the research object. At the same time, it is advisable to consider the electronic passport as a comprehensive description of the object, including information about the static and dynamic parameters of the atomic-molecular system of the research object. The e-passport as an information object gives a systematic data on the composition of a substance, structure, calculated and experimentally measured properties, the participation of elements in the composition of chemical reactions, constructed models and \"structure-property\" patterns, thus acting as a generalizing tool convenient for users to present information available in the database of digital twins of materials.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124731234","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110780
I. Kalmykov, N. Chistousov, N. Kalmykova
Low-orbit Satellite Internet Systems (LOSIS) are used to provide Internet access in any point of the Earth. They can contain more than 2,000 spacecrafts. Thus, several spacecraft can be located in the field of view of the satellite Internet receiver at once. As a result, there is a possibility of imposing someone else's content. This possibility can be eliminated by conducting preliminary authentication of the spacecraft. To do this, we can use Schnorr authentication protocol with high cryptographic strength, which is achieved by performing calculations on a large module (140 or more bits). In order to increase the information security of the LOSIS by reducing the authentication time of the spacecraft, it is proposed to modify Schnorr authentication protocol using MC RNS. These codes allow us to increase the speed of authentication by parallelizing calculations at the level of arithmetic operations. As a result of reducing the time spent on spacecraft identification, the information security of the LOSIS will be increased by reducing the time for the selection of the applicant's signal by the intruder satellite. Therefore, modification of Schnorr authentication protocol based on modular code is an urgent task.
{"title":"Modification of Schnorr Authentication Protocol Using Modular Codes","authors":"I. Kalmykov, N. Chistousov, N. Kalmykova","doi":"10.1109/SmartIndustryCon57312.2023.10110780","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110780","url":null,"abstract":"Low-orbit Satellite Internet Systems (LOSIS) are used to provide Internet access in any point of the Earth. They can contain more than 2,000 spacecrafts. Thus, several spacecraft can be located in the field of view of the satellite Internet receiver at once. As a result, there is a possibility of imposing someone else's content. This possibility can be eliminated by conducting preliminary authentication of the spacecraft. To do this, we can use Schnorr authentication protocol with high cryptographic strength, which is achieved by performing calculations on a large module (140 or more bits). In order to increase the information security of the LOSIS by reducing the authentication time of the spacecraft, it is proposed to modify Schnorr authentication protocol using MC RNS. These codes allow us to increase the speed of authentication by parallelizing calculations at the level of arithmetic operations. As a result of reducing the time spent on spacecraft identification, the information security of the LOSIS will be increased by reducing the time for the selection of the applicant's signal by the intruder satellite. Therefore, modification of Schnorr authentication protocol based on modular code is an urgent task.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116380527","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110803
V. Shepelev, A. Glushkov, A. Vorobyev
Many papers on traffic management have dealt with optimizing traffic light signals with the assumption that the traffic flow (TF) speed is fixed or follows a given distribution. In our study, we focused on determining vehicle speed in real time and assessing its impact on the delay of vehicles. A convolutional neural network (YOLOv3) is used to detect vehicles and determine their speed through the real-time processing of video streams from traffic surveillance cameras. The developed system can identify and classify 11 traffic flow types and track the trajectory and speed of vehicles passing through a regulated intersection. When analyzing the obtained data, we identified two important factors contributing to the formation of vehicle queues at intersections during a red light. We revealed the nature and statistically significant measure of reducing free vehicle movement speed depending on the queue size, and determined the maximum vehicle queue size which does not significantly affect the dynamics of passing through an intersection. The obtained data allow us to optimize adaptive regulation and synchronization of traffic lights based on the recommended traffic flow speed.
{"title":"Using Computer Vision to Analyze the Sequence of Vehicles Passing Through Regulated Intersections","authors":"V. Shepelev, A. Glushkov, A. Vorobyev","doi":"10.1109/SmartIndustryCon57312.2023.10110803","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110803","url":null,"abstract":"Many papers on traffic management have dealt with optimizing traffic light signals with the assumption that the traffic flow (TF) speed is fixed or follows a given distribution. In our study, we focused on determining vehicle speed in real time and assessing its impact on the delay of vehicles. A convolutional neural network (YOLOv3) is used to detect vehicles and determine their speed through the real-time processing of video streams from traffic surveillance cameras. The developed system can identify and classify 11 traffic flow types and track the trajectory and speed of vehicles passing through a regulated intersection. When analyzing the obtained data, we identified two important factors contributing to the formation of vehicle queues at intersections during a red light. We revealed the nature and statistically significant measure of reducing free vehicle movement speed depending on the queue size, and determined the maximum vehicle queue size which does not significantly affect the dynamics of passing through an intersection. The obtained data allow us to optimize adaptive regulation and synchronization of traffic lights based on the recommended traffic flow speed.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126517316","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}
Pub Date : 2023-03-27DOI: 10.1109/SmartIndustryCon57312.2023.10110829
Y. Kondrashova, A. Tretyakov, A. Shalimov
The paper offers a visual representation of the main parameters involved in the selection of reliability category, they are reflected in the form of an auxiliary degree of responsibility of electrical consumers (ADREC), assigned to the already known classification of reliability categories. In addition to that, we propose an algorithm (block diagram) to realize this task, the output of which is an auxiliary reliability category that characterizes a particular electrical receiver and visually reflects the reason for selecting exactly this reliability category, which informs the service personnel who has just arrived at the site about the receiver responsibility level. In addition, the auxiliary degree of responsibility can help in evaluating the consequences of accidents at the site, including the importance of the consequences of the accident. It is proposed to create a superstructure on this algorithm, which will be useful in the design of power supply systems, the basis of which is proposed in this article.
{"title":"Analysis of Consumer Category Data in the Context of an Industrial Enterprise","authors":"Y. Kondrashova, A. Tretyakov, A. Shalimov","doi":"10.1109/SmartIndustryCon57312.2023.10110829","DOIUrl":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110829","url":null,"abstract":"The paper offers a visual representation of the main parameters involved in the selection of reliability category, they are reflected in the form of an auxiliary degree of responsibility of electrical consumers (ADREC), assigned to the already known classification of reliability categories. In addition to that, we propose an algorithm (block diagram) to realize this task, the output of which is an auxiliary reliability category that characterizes a particular electrical receiver and visually reflects the reason for selecting exactly this reliability category, which informs the service personnel who has just arrived at the site about the receiver responsibility level. In addition, the auxiliary degree of responsibility can help in evaluating the consequences of accidents at the site, including the importance of the consequences of the accident. It is proposed to create a superstructure on this algorithm, which will be useful in the design of power supply systems, the basis of which is proposed in this article.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126833658","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：