In view of the COVID-19 pandemic and its highly infectious characteristic, traditional artificial diagnosis based on medical imaging, though capable of detecting pulmonary lesion in human body, is found of lower efficiency. Therefore, it is particularly urgent that we design a set of accurate and automatic pneumonia diagnosis methods with aid of artificial intelligence technology, so that pneumonia in patients can be diagnosed and treated early. This study first introduces DenseNet to the Convolutional Neural Network (CNN) structure to improve sharing of characteristic information of lung image in convolutional layers and thus obtain more accurate image features. Secondly, characteristics of pneumonia disease are discriminated rapidly using the Graphic Attention Network (GAT). The authors adopt the X-ray dataset in Radiological Society of North America (RSNA) Pneumonia Detection Challenge released by Kaggle to train and verify the network. According to experimental results, the accuracy of COVID-19 diagnosis and F-Score both reach 98%. The method provides CT doctors with an end-to-end deep learning technology for pneumonia diagnosis.
{"title":"Automatic Diagnosis of COVID-19 Medical Images based on Graph Attention Network","authors":"Yingxin Lai, Wenlong Yi, Hongyu Jiang, Tingzhuo Chen, Wenjuan Zhao, Keng-Chi Liu","doi":"10.1109/CTS53513.2021.9562907","DOIUrl":"https://doi.org/10.1109/CTS53513.2021.9562907","url":null,"abstract":"In view of the COVID-19 pandemic and its highly infectious characteristic, traditional artificial diagnosis based on medical imaging, though capable of detecting pulmonary lesion in human body, is found of lower efficiency. Therefore, it is particularly urgent that we design a set of accurate and automatic pneumonia diagnosis methods with aid of artificial intelligence technology, so that pneumonia in patients can be diagnosed and treated early. This study first introduces DenseNet to the Convolutional Neural Network (CNN) structure to improve sharing of characteristic information of lung image in convolutional layers and thus obtain more accurate image features. Secondly, characteristics of pneumonia disease are discriminated rapidly using the Graphic Attention Network (GAT). The authors adopt the X-ray dataset in Radiological Society of North America (RSNA) Pneumonia Detection Challenge released by Kaggle to train and verify the network. According to experimental results, the accuracy of COVID-19 diagnosis and F-Score both reach 98%. The method provides CT doctors with an end-to-end deep learning technology for pneumonia diagnosis.","PeriodicalId":371882,"journal":{"name":"2021 IV International Conference on Control in Technical Systems (CTS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131476455","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 : 2021-09-21DOI: 10.1109/CTS53513.2021.9562909
Daria M. Loseva
The report discusses the use of Text Mining algorithms such as semantic analysis of text and search for keywords to solve the problem of categorizing data entering the information system in the form of short messages in text format. An example of the application of such algorithms in the information system for processing user messages is given.
{"title":"Intellectual Analysis of Text Data for Solving the Problem of Information Categorization","authors":"Daria M. Loseva","doi":"10.1109/CTS53513.2021.9562909","DOIUrl":"https://doi.org/10.1109/CTS53513.2021.9562909","url":null,"abstract":"The report discusses the use of Text Mining algorithms such as semantic analysis of text and search for keywords to solve the problem of categorizing data entering the information system in the form of short messages in text format. An example of the application of such algorithms in the information system for processing user messages is given.","PeriodicalId":371882,"journal":{"name":"2021 IV International Conference on Control in Technical Systems (CTS)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121625916","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 : 2021-09-21DOI: 10.1109/CTS53513.2021.9562797
Jurij A. Morozov, S. E. Saradgishvili
In this paper, we experiment with a combination of metrics to calculate the similarity when creating collaborative filtering. The Otai Coefficient and Euclidean Distance are used, resulting in a recommender system that produces a satisfactory result.
{"title":"Improving Collaborative Filtering","authors":"Jurij A. Morozov, S. E. Saradgishvili","doi":"10.1109/CTS53513.2021.9562797","DOIUrl":"https://doi.org/10.1109/CTS53513.2021.9562797","url":null,"abstract":"In this paper, we experiment with a combination of metrics to calculate the similarity when creating collaborative filtering. The Otai Coefficient and Euclidean Distance are used, resulting in a recommender system that produces a satisfactory result.","PeriodicalId":371882,"journal":{"name":"2021 IV International Conference on Control in Technical Systems (CTS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124245772","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 : 2021-09-21DOI: 10.1109/CTS53513.2021.9562814
N. Popov, Natalya V. Shevskaya
In the 21st century, mankind is actively introducing machine learning and artificial intelligence into all spheres of life. But most modern algorithms output the final result of the calculations without revealing the details of obtaining the result, which is the reason for some skepticism towards it. To correct this situation, there is a need to use understandable machine learning methods that increase the transparency of use and the level of trust of people. The work reviews existing solutions to this problem, and also draws a conclusion on the effectiveness of a particular algorithm. Based on the results of the article, ways to further develop the work are proposed.
{"title":"Explainable Artificial Intelligence Methods Based on Feature Space Analysis","authors":"N. Popov, Natalya V. Shevskaya","doi":"10.1109/CTS53513.2021.9562814","DOIUrl":"https://doi.org/10.1109/CTS53513.2021.9562814","url":null,"abstract":"In the 21st century, mankind is actively introducing machine learning and artificial intelligence into all spheres of life. But most modern algorithms output the final result of the calculations without revealing the details of obtaining the result, which is the reason for some skepticism towards it. To correct this situation, there is a need to use understandable machine learning methods that increase the transparency of use and the level of trust of people. The work reviews existing solutions to this problem, and also draws a conclusion on the effectiveness of a particular algorithm. Based on the results of the article, ways to further develop the work are proposed.","PeriodicalId":371882,"journal":{"name":"2021 IV International Conference on Control in Technical Systems (CTS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123081009","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 : 2021-09-21DOI: 10.1109/CTS53513.2021.9562799
V. Kurkina, Marta S. Sirinova, Denis A. Aleksandrov
When automating a technological process, it is necessary to determine the number and location of sensors (sensor network) in such a way as to ensure the possibility of effective diagnostics of the process and at the same time to reduce the cost of measuring equipment. To solve this problem, it is proposed to use the entropy criterion. For this, an analysis is carried out and possible faults and failures that may arise in the process are identified. Next, the changes in entropy when a fault or failure occurs for each of the possible sensors, are considered. Those sensors that provide the greatest decrease in entropy (increase in information) are selected.
{"title":"Ensuring Diagnosability of the Technological Process with a Minimum Number of Sensors Based on the Entropy Criterion","authors":"V. Kurkina, Marta S. Sirinova, Denis A. Aleksandrov","doi":"10.1109/CTS53513.2021.9562799","DOIUrl":"https://doi.org/10.1109/CTS53513.2021.9562799","url":null,"abstract":"When automating a technological process, it is necessary to determine the number and location of sensors (sensor network) in such a way as to ensure the possibility of effective diagnostics of the process and at the same time to reduce the cost of measuring equipment. To solve this problem, it is proposed to use the entropy criterion. For this, an analysis is carried out and possible faults and failures that may arise in the process are identified. Next, the changes in entropy when a fault or failure occurs for each of the possible sensors, are considered. Those sensors that provide the greatest decrease in entropy (increase in information) are selected.","PeriodicalId":371882,"journal":{"name":"2021 IV International Conference on Control in Technical Systems (CTS)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115613341","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 : 2021-09-21DOI: 10.1109/CTS53513.2021.9562864
B. Fomin, O. B. Fomin, T. Kachanova, K. Turalchuk
For many years, the problem of natural classification is an actual problem of classic, scientific, and theoretical systematics. The attempts to create a rational reproducible scientific method for solving this problem have not been successful until recently. New opportunities have arisen from the creation of physics of open systems that has met the challenges of natural classification through the development of ontological prerequisites and operational definition for taxon. This paper provides an overview of the results that allow to overcome complexity of the problem, and to propose a rational reproducible proven method for solving the system-wide task of natural classification on the basis of multidimensional knowledge-centric analytics of physics of open systems. The method is intended for using in different subject areas with regard to open natural, social, anthropogenic, cyber-physical, as well as complex, technical systems with hundreds and thousands of variables. It should be pointed out that initially these systems are taken in their natural scales and real complexity by using huge amount of polymodal heterogeneous empirical data.
{"title":"System Foundations of Natural Classification","authors":"B. Fomin, O. B. Fomin, T. Kachanova, K. Turalchuk","doi":"10.1109/CTS53513.2021.9562864","DOIUrl":"https://doi.org/10.1109/CTS53513.2021.9562864","url":null,"abstract":"For many years, the problem of natural classification is an actual problem of classic, scientific, and theoretical systematics. The attempts to create a rational reproducible scientific method for solving this problem have not been successful until recently. New opportunities have arisen from the creation of physics of open systems that has met the challenges of natural classification through the development of ontological prerequisites and operational definition for taxon. This paper provides an overview of the results that allow to overcome complexity of the problem, and to propose a rational reproducible proven method for solving the system-wide task of natural classification on the basis of multidimensional knowledge-centric analytics of physics of open systems. The method is intended for using in different subject areas with regard to open natural, social, anthropogenic, cyber-physical, as well as complex, technical systems with hundreds and thousands of variables. It should be pointed out that initially these systems are taken in their natural scales and real complexity by using huge amount of polymodal heterogeneous empirical data.","PeriodicalId":371882,"journal":{"name":"2021 IV International Conference on Control in Technical Systems (CTS)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130155338","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 : 2021-09-21DOI: 10.1109/CTS53513.2021.9562883
A. S. Pisarev
The technology of “smart” documents for teaching and research has been developed, which is distinguished by the use of extensible libraries of programs in the VBA language and interaction with services in the Python language, which increases the productivity of solving educational problems in the field of technical systems management, informatics and data analysis. Examples of the application of the developed technology in the educational process are given.
{"title":"Applying Smart Document Technology for Teaching and Research","authors":"A. S. Pisarev","doi":"10.1109/CTS53513.2021.9562883","DOIUrl":"https://doi.org/10.1109/CTS53513.2021.9562883","url":null,"abstract":"The technology of “smart” documents for teaching and research has been developed, which is distinguished by the use of extensible libraries of programs in the VBA language and interaction with services in the Python language, which increases the productivity of solving educational problems in the field of technical systems management, informatics and data analysis. Examples of the application of the developed technology in the educational process are given.","PeriodicalId":371882,"journal":{"name":"2021 IV International Conference on Control in Technical Systems (CTS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128747019","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 : 2021-09-21DOI: 10.1109/CTS53513.2021.9562968
Aleksandr Kulakov, Aleksandr V. Smirnov
Currently, the concept of hardware and software modeling of complex technical objects (CTO) has received rapid development, including in the space industry. The main feature of such objects is the presence of real-time control systems with a complex and sometimes heterogeneous structure. The concept of “X-In-the-Loop” has gained great popularity in foreign literature when considering modeling of CTO. Among the specialized software (SW) for modeling spacecraft (SC), it is worth highlighting open source SW that has sufficient documentation to understand their work and an active community on the Internet. This report proposes a hardware-software modeling technology based on Project 42 (SW for modeling of SC) and microcontroller (MC) STM32. To work with MC STM32 within the framework of this technology, the integrated development environment IAR Embedded Workbench is used.
{"title":"Technology of Hardware and Software Modeling of Spacecraft Attitude Sensors Based on STM32 Microcontrollers","authors":"Aleksandr Kulakov, Aleksandr V. Smirnov","doi":"10.1109/CTS53513.2021.9562968","DOIUrl":"https://doi.org/10.1109/CTS53513.2021.9562968","url":null,"abstract":"Currently, the concept of hardware and software modeling of complex technical objects (CTO) has received rapid development, including in the space industry. The main feature of such objects is the presence of real-time control systems with a complex and sometimes heterogeneous structure. The concept of “X-In-the-Loop” has gained great popularity in foreign literature when considering modeling of CTO. Among the specialized software (SW) for modeling spacecraft (SC), it is worth highlighting open source SW that has sufficient documentation to understand their work and an active community on the Internet. This report proposes a hardware-software modeling technology based on Project 42 (SW for modeling of SC) and microcontroller (MC) STM32. To work with MC STM32 within the framework of this technology, the integrated development environment IAR Embedded Workbench is used.","PeriodicalId":371882,"journal":{"name":"2021 IV International Conference on Control in Technical Systems (CTS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127208695","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 : 2021-09-21DOI: 10.1109/CTS53513.2021.9562961
A. Dorogov
A method of nonparametric clustering of Big Data based on histogram analysis of images in the feature space is proposed. The method allows you to localize cluster zones and cluster centers in subspaces of the feature space without using distance metrics. The proposed method bypasses the “curse of dimensionality” and is suitable for analyzing both numerical and categorical high-dimensional data.
{"title":"Reductive Clustering of High-dimensional Data","authors":"A. Dorogov","doi":"10.1109/CTS53513.2021.9562961","DOIUrl":"https://doi.org/10.1109/CTS53513.2021.9562961","url":null,"abstract":"A method of nonparametric clustering of Big Data based on histogram analysis of images in the feature space is proposed. The method allows you to localize cluster zones and cluster centers in subspaces of the feature space without using distance metrics. The proposed method bypasses the “curse of dimensionality” and is suitable for analyzing both numerical and categorical high-dimensional data.","PeriodicalId":371882,"journal":{"name":"2021 IV International Conference on Control in Technical Systems (CTS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133562353","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 : 2021-09-21DOI: 10.1109/CTS53513.2021.9562780
R. Yusupov, A. A. Musaev, D. A. Grigoriev
The current article dedicated to analyzing the feasibility of using conventional techniques of statistical synthesis of prognostic decisions in the conditions of dynamic chaos, which characterizes management in unstable submersion environments. We show the fundamental difference between unstable system state observation series and probabilistic descriptions of traditional models based on the statistical paradigm. We consider an additive model with a chaotic systemic component and non-stationary noise, which describes the aforementioned observation series most adequately. We propose a method for pragmatic estimation of functional efficiency of forecast techniques in the conditions of chaotic non-determinism.
{"title":"Evaluation of Statistical Forecast Method Efficiency in the Conditions of Dynamic Chaos","authors":"R. Yusupov, A. A. Musaev, D. A. Grigoriev","doi":"10.1109/CTS53513.2021.9562780","DOIUrl":"https://doi.org/10.1109/CTS53513.2021.9562780","url":null,"abstract":"The current article dedicated to analyzing the feasibility of using conventional techniques of statistical synthesis of prognostic decisions in the conditions of dynamic chaos, which characterizes management in unstable submersion environments. We show the fundamental difference between unstable system state observation series and probabilistic descriptions of traditional models based on the statistical paradigm. We consider an additive model with a chaotic systemic component and non-stationary noise, which describes the aforementioned observation series most adequately. We propose a method for pragmatic estimation of functional efficiency of forecast techniques in the conditions of chaotic non-determinism.","PeriodicalId":371882,"journal":{"name":"2021 IV International Conference on Control in Technical Systems (CTS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133765867","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：