The article considers the process of building simulation models of systems with stochastic data processing based on colored Petri nets. A formal description of models based on colored Petri nets is presented. For simulation modeling of data processing tasks, the use of temporal Petri nets is substantiated, which allows to define and describe in detail the time intervals of the simulated process. The algorithm for building simulation models based on colored Petri nets is presented. The peculiarities of the use of temporal Petri nets in the construction of simulation models with complex stochastic data processing processes are determined. Special functions are used to assign random values. A list of functions with their detailed description and ranges of permissible values for input parameters is provided. As an example, the construction of a simulation model of the work process of the application processing center of a commercial firm is considered. The model was built in the CPN Tools environment. System parameters, variables, functions and model parameters are defined and investigated. The method of accumulating information in positions was used to accumulate statistics on the results of the models. The analysis of the results of simulation modeling of the work process of the application processing center of a commercial firm is presented.
{"title":"Simulation modeling of systems with a complex stochastic data processing process using colored Petri nets","authors":"Kalinina Iryna, Gozhyj Oleksandr, Nechahin Vladislav, Shiyan Serhii","doi":"10.34185/1562-9945-6-143-2022-04","DOIUrl":"https://doi.org/10.34185/1562-9945-6-143-2022-04","url":null,"abstract":"The article considers the process of building simulation models of systems with stochastic data processing based on colored Petri nets. A formal description of models based on colored Petri nets is presented. For simulation modeling of data processing tasks, the use of temporal Petri nets is substantiated, which allows to define and describe in detail the time intervals of the simulated process. The algorithm for building simulation models based on colored Petri nets is presented. The peculiarities of the use of temporal Petri nets in the construction of simulation models with complex stochastic data processing processes are determined. Special functions are used to assign random values. A list of functions with their detailed description and ranges of permissible values for input parameters is provided. As an example, the construction of a simulation model of the work process of the application processing center of a commercial firm is considered. The model was built in the CPN Tools environment. System parameters, variables, functions and model parameters are defined and investigated. The method of accumulating information in positions was used to accumulate statistics on the results of the models. The analysis of the results of simulation modeling of the work process of the application processing center of a commercial firm is presented.","PeriodicalId":493145,"journal":{"name":"Sistemnì tehnologìï","volume":"124 17","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136351446","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 : 2023-11-13DOI: 10.34185/1562-9945-4-147-2023-08
Tulub Valentyn
Automated systems play a key role in the modern world, ensuring efficiency and auto-mation of various processes. However, with the constant development of technology and the increasing complexity of tasks, continuous improvement and efficiency of these systems is re-quired. This article explores methods that can improve the efficiency of automated systems. Various aspects are analyzed, such as optimization of work, improvement of productivity, re-duction of task execution time, reduction of errors, and increase of accuracy. The main goal of the article is to focus on the methodologies for increasing the level of efficiency. The table shows the methodologies with a description of their advantages, disadvantages, and areas of application. In addition, additional parameters such as the degree of automation, the degree of system flexibility, and the level of autonomy are proposed. The article also proposes a new algorithm for improving the efficiency of automated systems. The algorithm is based on the use of modern technologies and approaches, such as data analysis and process optimization. The proposed algorithm has the potential to improve the efficiency of automated systems and can be adapted many times over. The research represents a significant contribution to the field of improving the efficiency of automated systems. The algorithm can be useful for re-searchers, engineers, automation professionals, and managers interested in improving and optimizing their systems.
{"title":"Methods of increasing the level efficiency of automated systems","authors":"Tulub Valentyn","doi":"10.34185/1562-9945-4-147-2023-08","DOIUrl":"https://doi.org/10.34185/1562-9945-4-147-2023-08","url":null,"abstract":"Automated systems play a key role in the modern world, ensuring efficiency and auto-mation of various processes. However, with the constant development of technology and the increasing complexity of tasks, continuous improvement and efficiency of these systems is re-quired. This article explores methods that can improve the efficiency of automated systems. Various aspects are analyzed, such as optimization of work, improvement of productivity, re-duction of task execution time, reduction of errors, and increase of accuracy. The main goal of the article is to focus on the methodologies for increasing the level of efficiency. The table shows the methodologies with a description of their advantages, disadvantages, and areas of application. In addition, additional parameters such as the degree of automation, the degree of system flexibility, and the level of autonomy are proposed. The article also proposes a new algorithm for improving the efficiency of automated systems. The algorithm is based on the use of modern technologies and approaches, such as data analysis and process optimization. The proposed algorithm has the potential to improve the efficiency of automated systems and can be adapted many times over. The research represents a significant contribution to the field of improving the efficiency of automated systems. The algorithm can be useful for re-searchers, engineers, automation professionals, and managers interested in improving and optimizing their systems.","PeriodicalId":493145,"journal":{"name":"Sistemnì tehnologìï","volume":"123 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136352152","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 : 2023-11-13DOI: 10.34185/1562-9945-6-143-2022-05
Dmytro Zelentsov, Shaptala Taras
Analysis of the literature made it clear that the problem associated with improving the performance and acceleration of ANN learning is quite actual, as ANNs are used every day in more and more industries. The concepts of finding more profitable activation functions have been outlined a lot, but changing their behavior as a result of learning is a fresh look at the problem. The aim of the study is to find new models of optimization tasks for the formulated prob-lem and effective methods for their implementation, which would improve the quality of ANN training, in particular by overcoming the problem of local minima. A studied of models and methods for training neural networks using an extended vector of varying parameters is conducted. The training problem is formulated as a continuous mul-tidimensional unconditional optimization problem. The extended vector of varying parameters implies that it includes some parameters of activation functions in addition to weight coeffi-cients. The introduction of additional varying parameters does not change the architecture of a neural network, but makes it impossible to use the back propagation method. A number of gradient methods have been used to solve optimization problems. Different formulations of optimization problems and methods for their solution have been investigated according to ac-curacy and efficiency criteria. The analysis of the results of numerical experiments allowed us to conclude that it is expedient to expand the vector of varying parameters in the tasks of training ANNs with con-tinuous and differentiated activation functions. Despite the increase in the dimensionality of the optimization problem, the efficiency of the new formulation is higher than the generalized one. According to the authors, this is due to the fact that a significant share of computational costs in the generalized formulation falls on attempts to leave the neighborhood of local min-ima, while increasing the dimensionality of the solution space allows this to be done with much lower costs.
{"title":"Models and methods of learning neural networks with differentiated activation functions","authors":"Dmytro Zelentsov, Shaptala Taras","doi":"10.34185/1562-9945-6-143-2022-05","DOIUrl":"https://doi.org/10.34185/1562-9945-6-143-2022-05","url":null,"abstract":"Analysis of the literature made it clear that the problem associated with improving the performance and acceleration of ANN learning is quite actual, as ANNs are used every day in more and more industries. The concepts of finding more profitable activation functions have been outlined a lot, but changing their behavior as a result of learning is a fresh look at the problem. The aim of the study is to find new models of optimization tasks for the formulated prob-lem and effective methods for their implementation, which would improve the quality of ANN training, in particular by overcoming the problem of local minima. A studied of models and methods for training neural networks using an extended vector of varying parameters is conducted. The training problem is formulated as a continuous mul-tidimensional unconditional optimization problem. The extended vector of varying parameters implies that it includes some parameters of activation functions in addition to weight coeffi-cients. The introduction of additional varying parameters does not change the architecture of a neural network, but makes it impossible to use the back propagation method. A number of gradient methods have been used to solve optimization problems. Different formulations of optimization problems and methods for their solution have been investigated according to ac-curacy and efficiency criteria. The analysis of the results of numerical experiments allowed us to conclude that it is expedient to expand the vector of varying parameters in the tasks of training ANNs with con-tinuous and differentiated activation functions. Despite the increase in the dimensionality of the optimization problem, the efficiency of the new formulation is higher than the generalized one. According to the authors, this is due to the fact that a significant share of computational costs in the generalized formulation falls on attempts to leave the neighborhood of local min-ima, while increasing the dimensionality of the solution space allows this to be done with much lower costs.","PeriodicalId":493145,"journal":{"name":"Sistemnì tehnologìï","volume":"124 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136351322","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 : 2023-11-13DOI: 10.34185/1562-9945-4-147-2023-02
Maliienko Stanislav, Selivorstova Tatyana
The article provides a comprehensive review of mathematical models and information technologies used for analyzing large amounts of data in web applications. The latest re-search and publications in the field are analyzed, including a comparative analysis of ma-chine learning methods, text, image, video analysis, social network analysis, and graph algo-rithms. The goal of this research is to analyze the effectiveness and applicability of mathe-matical models and information technologies in business analysis of large web data. The arti-cle presents the results of the research and a comparative analysis of the efficiency of meth-ods, which will help business analysts choose the optimal tools for processing and analyzing large amounts of data in web applications. The article begins with an overview of the problem and the latest research and publica-tions in the field. The article provides a detailed description of various mathematical models and information technologies, including their strengths and weaknesses. A comparative analysis of these methods is presented, with a focus on their effectiveness and applicability in business analysis. The article also provides a detailed description of the applications of mathematical models and information technologies in various industries, such as e-commerce and supply chain management. The article analyzes the challenges and opportunities associated with the use of these technologies in business analysis and provides recommendations for businesses that want to take advantage of these technologies. Overall, the article provides a comprehensive overview of mathematical models and in-formation technologies used in business analysis of large web data. The article is a valuable resource for business analysts, data scientists, and researchers who want to learn more about the latest developments in this field.
{"title":"Review of mathematical models and information technologies for business analysis of the big web data","authors":"Maliienko Stanislav, Selivorstova Tatyana","doi":"10.34185/1562-9945-4-147-2023-02","DOIUrl":"https://doi.org/10.34185/1562-9945-4-147-2023-02","url":null,"abstract":"The article provides a comprehensive review of mathematical models and information technologies used for analyzing large amounts of data in web applications. The latest re-search and publications in the field are analyzed, including a comparative analysis of ma-chine learning methods, text, image, video analysis, social network analysis, and graph algo-rithms. The goal of this research is to analyze the effectiveness and applicability of mathe-matical models and information technologies in business analysis of large web data. The arti-cle presents the results of the research and a comparative analysis of the efficiency of meth-ods, which will help business analysts choose the optimal tools for processing and analyzing large amounts of data in web applications. The article begins with an overview of the problem and the latest research and publica-tions in the field. The article provides a detailed description of various mathematical models and information technologies, including their strengths and weaknesses. A comparative analysis of these methods is presented, with a focus on their effectiveness and applicability in business analysis. The article also provides a detailed description of the applications of mathematical models and information technologies in various industries, such as e-commerce and supply chain management. The article analyzes the challenges and opportunities associated with the use of these technologies in business analysis and provides recommendations for businesses that want to take advantage of these technologies. Overall, the article provides a comprehensive overview of mathematical models and in-formation technologies used in business analysis of large web data. The article is a valuable resource for business analysts, data scientists, and researchers who want to learn more about the latest developments in this field.","PeriodicalId":493145,"journal":{"name":"Sistemnì tehnologìï","volume":"123 51","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136351329","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 : 2023-11-13DOI: 10.34185/1562-9945-4-147-2023-07
Bubenko Maksym, Karpenko Nadiia, Gerasimov Volodymyr, Morozov Alexander
An important practical task for developers is the rapid creation and maintenance of high-quality multi-level software. It is assumed that the developed product will meet the qual-ity characteristics. And, if we talk about testing applications of different types, then you should pay attention to their features. For example, web applications have critical areas that must be checked. Thus, the purpose of this article is to analyse various methods and technics for testing web applications. The article provides a detailed analysis of the latest publications related to testing web applications. It turned out that most of the articles are aimed at describing terms or general information about testing. Several articles describe automated testing with Selenium, IBM Rational, SilkPerformer, TestComplete, HP QuickTest Professional, JUnit and compare them in terms of efficiency in various applications. However, most of the articles are devoted to various aspects of manual testing. In order to identify the factors that distinguish web application testing from desktop ap-plication testing, a table has been compiled comparing them according to the following crite-ria: environment, platform, deployment and updating, architecture, connectivity, availability. This comparison shows that web applications have several features that need to be consid-ered when testing them. In our opinion, the main critical areas of web applications that require additional de-scription and instructions are unity of design, navigation and "friendliness" to the user, func-tionality, security, compatibility with browsers and operating systems, and productivity. The article describes the specifics of testing critical zones and gives an estimate of the resource consumption of their testing. Tests are also recommended, which are useful for testing web and desktop applications.
{"title":"Analysis of web application testing methods","authors":"Bubenko Maksym, Karpenko Nadiia, Gerasimov Volodymyr, Morozov Alexander","doi":"10.34185/1562-9945-4-147-2023-07","DOIUrl":"https://doi.org/10.34185/1562-9945-4-147-2023-07","url":null,"abstract":"An important practical task for developers is the rapid creation and maintenance of high-quality multi-level software. It is assumed that the developed product will meet the qual-ity characteristics. And, if we talk about testing applications of different types, then you should pay attention to their features. For example, web applications have critical areas that must be checked. Thus, the purpose of this article is to analyse various methods and technics for testing web applications. The article provides a detailed analysis of the latest publications related to testing web applications. It turned out that most of the articles are aimed at describing terms or general information about testing. Several articles describe automated testing with Selenium, IBM Rational, SilkPerformer, TestComplete, HP QuickTest Professional, JUnit and compare them in terms of efficiency in various applications. However, most of the articles are devoted to various aspects of manual testing. In order to identify the factors that distinguish web application testing from desktop ap-plication testing, a table has been compiled comparing them according to the following crite-ria: environment, platform, deployment and updating, architecture, connectivity, availability. This comparison shows that web applications have several features that need to be consid-ered when testing them. In our opinion, the main critical areas of web applications that require additional de-scription and instructions are unity of design, navigation and \"friendliness\" to the user, func-tionality, security, compatibility with browsers and operating systems, and productivity. The article describes the specifics of testing critical zones and gives an estimate of the resource consumption of their testing. Tests are also recommended, which are useful for testing web and desktop applications.","PeriodicalId":493145,"journal":{"name":"Sistemnì tehnologìï","volume":"129 30","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136351995","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}
The work is devoted to studying the effectiveness of computing service management platforms in the organization of Fog Computing. As part of the work, the effectiveness of container orchestration platforms with the Fog computing organization is being studied. During the research, it is necessary to complete the following tasks: 1) select literature, scientific publications and Internet articles necessary for the research; 2) inspect container orchestration platforms; 3) determine the key requirements and criteria for conducting the study; 4) design and implement an automatic testing utility; 5) conduct a study of the effec-tiveness of container orchestration platforms with the organization of fog computing; 6) ana-lyze the results obtained and draw related conclusions. Deployment of Docker containers is organized. Docker Swarm is used to create a clus-ter. The problems of measuring the following parameters are solved: deployment time of one container, deployment time of a group of containers, response time of the horizontal zoom task, transmission delay time. The analysis of the obtained test results is carried out.
{"title":"Research of the efficiency of computing services management platforms in the organization of fog computing","authors":"Ostrovska Kateryna, Sherstyanikh Mykita, Stovchenko Ivan, Kaliberda Yury","doi":"10.34185/1562-9945-6-143-2022-09","DOIUrl":"https://doi.org/10.34185/1562-9945-6-143-2022-09","url":null,"abstract":"The work is devoted to studying the effectiveness of computing service management platforms in the organization of Fog Computing. As part of the work, the effectiveness of container orchestration platforms with the Fog computing organization is being studied. During the research, it is necessary to complete the following tasks: 1) select literature, scientific publications and Internet articles necessary for the research; 2) inspect container orchestration platforms; 3) determine the key requirements and criteria for conducting the study; 4) design and implement an automatic testing utility; 5) conduct a study of the effec-tiveness of container orchestration platforms with the organization of fog computing; 6) ana-lyze the results obtained and draw related conclusions. Deployment of Docker containers is organized. Docker Swarm is used to create a clus-ter. The problems of measuring the following parameters are solved: deployment time of one container, deployment time of a group of containers, response time of the horizontal zoom task, transmission delay time. The analysis of the obtained test results is carried out.","PeriodicalId":493145,"journal":{"name":"Sistemnì tehnologìï","volume":"129 19","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136351839","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 : 2023-11-13DOI: 10.34185/1562-9945-4-147-2023-03
Dmytriieva Iryna, Bimalov Dmytro
A huge number of spheres of human activity leads to the emergence of information re-sources that reflect social communication. The study of the identification of emotions in text communication is an actual direction of research in the field of natural language processing and machine learning. The main goal of the work is to develop a software module that implements algorithms and models that can automatically determine a person's emotional state based on text messages. This work is de-voted to the review of some models and an algorithm for improving data processing in the middle of text communication of users. One of the methods used in the work is the filtering method. The filtering method deter-mines the discussions of the text, which it records in the form of a hierarchical tree-like struc-ture. Discourse greatly simplifies the work and allows you to more accurately determine the emotion in the text. It also builds a semantic model, the data of which is obtained from the text communica-tion of users. Using the described structures, the filtering method finds emotional words re-corded in the database. The search is based on keywords. In turn, keywords are defined by case. The work deals with the issue of finding emotions in text messages and the development of a software module for its implementation. Two algorithms for determining emotions are considered - vector and Boolean. During the research, it was determined that the Boolean algorithm is most suitable for searching for emotional words. In the work, emotional words were found by identifying and analyzing the semantics of the sentence.
{"title":"Development of a software module for the identification of the emotional state of the user","authors":"Dmytriieva Iryna, Bimalov Dmytro","doi":"10.34185/1562-9945-4-147-2023-03","DOIUrl":"https://doi.org/10.34185/1562-9945-4-147-2023-03","url":null,"abstract":"A huge number of spheres of human activity leads to the emergence of information re-sources that reflect social communication. The study of the identification of emotions in text communication is an actual direction of research in the field of natural language processing and machine learning. The main goal of the work is to develop a software module that implements algorithms and models that can automatically determine a person's emotional state based on text messages. This work is de-voted to the review of some models and an algorithm for improving data processing in the middle of text communication of users. One of the methods used in the work is the filtering method. The filtering method deter-mines the discussions of the text, which it records in the form of a hierarchical tree-like struc-ture. Discourse greatly simplifies the work and allows you to more accurately determine the emotion in the text. It also builds a semantic model, the data of which is obtained from the text communica-tion of users. Using the described structures, the filtering method finds emotional words re-corded in the database. The search is based on keywords. In turn, keywords are defined by case. The work deals with the issue of finding emotions in text messages and the development of a software module for its implementation. Two algorithms for determining emotions are considered - vector and Boolean. During the research, it was determined that the Boolean algorithm is most suitable for searching for emotional words. In the work, emotional words were found by identifying and analyzing the semantics of the sentence.","PeriodicalId":493145,"journal":{"name":"Sistemnì tehnologìï","volume":"130 15","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136352125","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}
Overhead cranes are widely in operation in sea and river ports for cargo transshipment in open and closed storage areas. Since they are the main link in technological processes, the productivity of Port production lines depends on their reliable and continuous operation. It is known that during the operation of cranes, 90% of the running wheels fail and are replaced with new ones due to intensive wear of the edges, and 60-70% of crane rails due to wear of their side faces. Since the service life is the main indicator of the durability of parts and assemblies, therefore, increasing the installation of wheel life is an urgent task, which will reduce the cost of repair and operation of cranes. As the experience of operation shows, running wheels have the most worn elements of movement mechanisms. Thus, their service life ranges from several months to 2-3 years. This is due to the fact that replacing the wheels is cheaper compared to replacing the crane track. Since the service life is the main indicator of the durability of parts and assemblies, therefore, increasing the installation of wheel life is an urgent task, which will reduce the cost of repair and operation of cranes. Analysis of studies of complex technical systems shows that the reliability of overhead crane mechanisms operated for more than 30 years in the Seaport is not fully understood, the nature of wheel damage depends on the operating conditions. For research, 4 identical overhead cranes with a lifting capacity of 10 tons were selected, which operate in Hook mode in seaports. Crane wheels are made of 65g steel by casting. Crane mechanisms were visually examined and wheel wear was measured after 3 months during 4 years of operation. Based on the research results, the parameters of the Wear model from time to time in the form of a step function are calculated. The obtained values of the correlation coefficient indicate that there is a fairly tight relationship between wear and operating time. The average error value for the proposed model does not exceed 6.1%, which is quite acceptable for engineering calculations. It is established that the service life of Crane wheels does not exceed 3.3...3.4 years of operation, which is less than 4 years specified by the manufacturer.
{"title":"Modeling of operational reliability of running wheels of overhead cranes of seaports","authors":"Strelbitskyi Viktor, Bovnegra Liubov, Pavlyshko Andrii","doi":"10.34185/1562-9945-6-143-2022-07","DOIUrl":"https://doi.org/10.34185/1562-9945-6-143-2022-07","url":null,"abstract":"Overhead cranes are widely in operation in sea and river ports for cargo transshipment in open and closed storage areas. Since they are the main link in technological processes, the productivity of Port production lines depends on their reliable and continuous operation. It is known that during the operation of cranes, 90% of the running wheels fail and are replaced with new ones due to intensive wear of the edges, and 60-70% of crane rails due to wear of their side faces. Since the service life is the main indicator of the durability of parts and assemblies, therefore, increasing the installation of wheel life is an urgent task, which will reduce the cost of repair and operation of cranes. As the experience of operation shows, running wheels have the most worn elements of movement mechanisms. Thus, their service life ranges from several months to 2-3 years. This is due to the fact that replacing the wheels is cheaper compared to replacing the crane track. Since the service life is the main indicator of the durability of parts and assemblies, therefore, increasing the installation of wheel life is an urgent task, which will reduce the cost of repair and operation of cranes. Analysis of studies of complex technical systems shows that the reliability of overhead crane mechanisms operated for more than 30 years in the Seaport is not fully understood, the nature of wheel damage depends on the operating conditions. For research, 4 identical overhead cranes with a lifting capacity of 10 tons were selected, which operate in Hook mode in seaports. Crane wheels are made of 65g steel by casting. Crane mechanisms were visually examined and wheel wear was measured after 3 months during 4 years of operation. Based on the research results, the parameters of the Wear model from time to time in the form of a step function are calculated. The obtained values of the correlation coefficient indicate that there is a fairly tight relationship between wear and operating time. The average error value for the proposed model does not exceed 6.1%, which is quite acceptable for engineering calculations. It is established that the service life of Crane wheels does not exceed 3.3...3.4 years of operation, which is less than 4 years specified by the manufacturer.","PeriodicalId":493145,"journal":{"name":"Sistemnì tehnologìï","volume":"123 35","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136352255","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 : 2023-11-13DOI: 10.34185/1562-9945-4-147-2023-10
Soldatenko Dmytro, Hnatushenko Viktorija
Satellite image recognition is a crucial application of computer vision that has the po-tential to be applied in various fields such as disaster management, agriculture, and urban planning. The objective of this study is to determine the optimal amount of input data required and select the most effective methods of augmentation necessary for training a convolutional neural network (CNN) for satellite image recognition. To achieve this, we perform a series of experiments to investigate the effect of input data quantity on several performance metrics, including model accuracy, convergence, and generalization. Additionally, we explore the impact of various data augmentation techniques, such as rotation, scaling, and flipping, on model performance. The study suggests several strategies for identifying the saturation point and mitigating the effects of overtraining, in-cluding early stopping and dropout regularization. The findings from this study can significantly contribute to the development of more ef-ficient satellite recognition models. Furthermore, they can help improve the performance of existing models, in addition to providing guidance for future research. The study emphasizes the importance of carefully selecting input data and augmentation methods to achieve optimal performance in CNNs, which is fundamental in advancing the field of computer vision. In addition to the above, the study investigates the potential of transfer learning by pre-training the model on a related dataset and fine-tuning it on the satellite imagery dataset. This approach can reduce the amount of required data and training time and increase model performance. Overall, this study provides valuable insights into the optimal amount of input data and augmentation techniques for training CNNs for satellite image recognition, and its findings can guide future research in this area.
{"title":"Improving deep learning performance by augmenting training data","authors":"Soldatenko Dmytro, Hnatushenko Viktorija","doi":"10.34185/1562-9945-4-147-2023-10","DOIUrl":"https://doi.org/10.34185/1562-9945-4-147-2023-10","url":null,"abstract":"Satellite image recognition is a crucial application of computer vision that has the po-tential to be applied in various fields such as disaster management, agriculture, and urban planning. The objective of this study is to determine the optimal amount of input data required and select the most effective methods of augmentation necessary for training a convolutional neural network (CNN) for satellite image recognition. To achieve this, we perform a series of experiments to investigate the effect of input data quantity on several performance metrics, including model accuracy, convergence, and generalization. Additionally, we explore the impact of various data augmentation techniques, such as rotation, scaling, and flipping, on model performance. The study suggests several strategies for identifying the saturation point and mitigating the effects of overtraining, in-cluding early stopping and dropout regularization. The findings from this study can significantly contribute to the development of more ef-ficient satellite recognition models. Furthermore, they can help improve the performance of existing models, in addition to providing guidance for future research. The study emphasizes the importance of carefully selecting input data and augmentation methods to achieve optimal performance in CNNs, which is fundamental in advancing the field of computer vision. In addition to the above, the study investigates the potential of transfer learning by pre-training the model on a related dataset and fine-tuning it on the satellite imagery dataset. This approach can reduce the amount of required data and training time and increase model performance. Overall, this study provides valuable insights into the optimal amount of input data and augmentation techniques for training CNNs for satellite image recognition, and its findings can guide future research in this area.","PeriodicalId":493145,"journal":{"name":"Sistemnì tehnologìï","volume":"123 22","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136352265","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 : 2023-11-13DOI: 10.34185/1562-9945-4-147-2023-12
Khrystyna Lipianina-Honcharenko
The relevance of the topic lies in the complexity of selecting a location for starting a business in smart cities, as it requires analyzing a large amount of data and considering vari-ous factors such as population, competition, infrastructure, and other parameters. The use of an intelligent method based on machine learning enables the collection, processing, and analysis of large volumes of data for accurate location assessment and providing recommen-dations to entrepreneurs. This enhances the decision-making process, ensures more informed choices, and increases the chances of business success in a smart city. The problem statement involves the need to expedite the process of selecting an optimal location for business placement in a smart city. This task is challenging and long-term, re-quiring the analysis of extensive data and consideration of various factors that impact busi-ness success, such as geographical position, competition, potential customer base, and other relevant aspects. It is also crucial to provide entrepreneurs with fast access to information and precise recommendations to make informed decisions regarding their business location. Solving this problem will facilitate efficient resource utilization and ensure business success in a smart city. The purpose of the study is to develop an intelligent method for choosing a location for starting a business in a smart city. This method aims to use large amounts of data collected from various sources to determine the most optimal locations for starting a new business. The method is based on existing machine learning techniques such as image recognition, data preprocessing, classification, and clustering of numerical data. Results and key conclusions. A method has been developed, the implementation of which will allow recommending optimal locations for business in smart cities. This will help to increase customer satisfaction, improve the quality of life and increase the profit of entre-preneurs. The intelligent method is a powerful tool for solving the problems of choosing a lo-cation for starting a business in smart cities.
{"title":"Intellectual method for business location selection in smart cities","authors":"Khrystyna Lipianina-Honcharenko","doi":"10.34185/1562-9945-4-147-2023-12","DOIUrl":"https://doi.org/10.34185/1562-9945-4-147-2023-12","url":null,"abstract":"The relevance of the topic lies in the complexity of selecting a location for starting a business in smart cities, as it requires analyzing a large amount of data and considering vari-ous factors such as population, competition, infrastructure, and other parameters. The use of an intelligent method based on machine learning enables the collection, processing, and analysis of large volumes of data for accurate location assessment and providing recommen-dations to entrepreneurs. This enhances the decision-making process, ensures more informed choices, and increases the chances of business success in a smart city. The problem statement involves the need to expedite the process of selecting an optimal location for business placement in a smart city. This task is challenging and long-term, re-quiring the analysis of extensive data and consideration of various factors that impact busi-ness success, such as geographical position, competition, potential customer base, and other relevant aspects. It is also crucial to provide entrepreneurs with fast access to information and precise recommendations to make informed decisions regarding their business location. Solving this problem will facilitate efficient resource utilization and ensure business success in a smart city. The purpose of the study is to develop an intelligent method for choosing a location for starting a business in a smart city. This method aims to use large amounts of data collected from various sources to determine the most optimal locations for starting a new business. The method is based on existing machine learning techniques such as image recognition, data preprocessing, classification, and clustering of numerical data. Results and key conclusions. A method has been developed, the implementation of which will allow recommending optimal locations for business in smart cities. This will help to increase customer satisfaction, improve the quality of life and increase the profit of entre-preneurs. The intelligent method is a powerful tool for solving the problems of choosing a lo-cation for starting a business in smart cities.","PeriodicalId":493145,"journal":{"name":"Sistemnì tehnologìï","volume":"128 15","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136351583","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：