Pub Date : 2022-10-11DOI: 10.23919/WAC55640.2022.9934434
Itaru Kaneko, Daisuke Hirahara, J. Hayano, Óscar Martínez Mozos, E. Yuda
In recent years, from the viewpoint of privacy protection policy, research on the personal identification of human bio-signals has been prominent. However, it is not well known whether indices obtained from biological time series data, such as ECGs, have personal identifiability, and it is not clear and can they be discriminated from animal ECGs. In this study, we visualized Heart Rate Variability (HRV) indices data of a cynomolgus monkey (Macaca Fascicularis) and a newborn using T-SNE, which is often used for data dimensionality compression in unsupervised learning, and UMAP, which is a new method. As a result, it was difficult to discriminate between cynomolgus monkey and newborn HRV indices.
{"title":"Discrimination between Cynomolgus Monkey (Macaca Fascicularis) and Humans using Machine Learning and Heart Rate Variability Indices","authors":"Itaru Kaneko, Daisuke Hirahara, J. Hayano, Óscar Martínez Mozos, E. Yuda","doi":"10.23919/WAC55640.2022.9934434","DOIUrl":"https://doi.org/10.23919/WAC55640.2022.9934434","url":null,"abstract":"In recent years, from the viewpoint of privacy protection policy, research on the personal identification of human bio-signals has been prominent. However, it is not well known whether indices obtained from biological time series data, such as ECGs, have personal identifiability, and it is not clear and can they be discriminated from animal ECGs. In this study, we visualized Heart Rate Variability (HRV) indices data of a cynomolgus monkey (Macaca Fascicularis) and a newborn using T-SNE, which is often used for data dimensionality compression in unsupervised learning, and UMAP, which is a new method. As a result, it was difficult to discriminate between cynomolgus monkey and newborn HRV indices.","PeriodicalId":339737,"journal":{"name":"2022 World Automation Congress (WAC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116724528","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 : 2022-10-11DOI: 10.23919/WAC55640.2022.9934370
Shaohua Zhao
In recent years, economic and information globalization, e-commerce booming, and the application and popularization of the Internet and mobile payments have accelerated the development of the e-commerce industry. People are relying more and more on the Internet for shopping, and all kinds of shopping needs can basically be met online. For e-commerce companies, the construction of e-commerce service platforms can help promote the improvement of corporate economic benefits; for users, it is greatly satisfy their shopping needs. Based on this, the purpose of this paper is to study the construction of e-commerce service platform under hybrid genetic algorithm. This article first conducts a system analysis, expounds the design of an e-commerce service platform based on hybrid genetic algorithm, and clarifies the overall design framework and specific functional modules of the e-commerce service platform. Finally, this article has carried on the performance and the function test to the system. The test results show that the average response time of system login is less than 2 seconds when there are more than 10 to 1500 users concurrently; when more than 10 to 2000 users are concurrently, the business data declaration time is less than 4 seconds. It can be seen that the system has good performance.
{"title":"Construction of E-commerce Service Platform under Hybrid Genetic Algorithm","authors":"Shaohua Zhao","doi":"10.23919/WAC55640.2022.9934370","DOIUrl":"https://doi.org/10.23919/WAC55640.2022.9934370","url":null,"abstract":"In recent years, economic and information globalization, e-commerce booming, and the application and popularization of the Internet and mobile payments have accelerated the development of the e-commerce industry. People are relying more and more on the Internet for shopping, and all kinds of shopping needs can basically be met online. For e-commerce companies, the construction of e-commerce service platforms can help promote the improvement of corporate economic benefits; for users, it is greatly satisfy their shopping needs. Based on this, the purpose of this paper is to study the construction of e-commerce service platform under hybrid genetic algorithm. This article first conducts a system analysis, expounds the design of an e-commerce service platform based on hybrid genetic algorithm, and clarifies the overall design framework and specific functional modules of the e-commerce service platform. Finally, this article has carried on the performance and the function test to the system. The test results show that the average response time of system login is less than 2 seconds when there are more than 10 to 1500 users concurrently; when more than 10 to 2000 users are concurrently, the business data declaration time is less than 4 seconds. It can be seen that the system has good performance.","PeriodicalId":339737,"journal":{"name":"2022 World Automation Congress (WAC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123765353","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 : 2022-10-11DOI: 10.23919/WAC55640.2022.9934494
Wang Dawei, Meng Xiaomeng
The definition of image color is closely related to the plane visual effect of the interactive interface of mobile intelligent devices. In order to improve the visual effect of plane visual image color, the plane visual image color enhancement system of the interactive interface of mobile intelligent devices is deeply studied, and the image acquisition module is designed to extract image information and transmit it to the image color enhancement module. The image color enhancement module uses the color image enhancement algorithm based on visual characteristics to enhance the overall brightness of the plane visual image in the way of histogram nonlinear adaptive lifting; The local contrast of the plane visual image is enhanced according to the correlation between the current point and the regional pixel, and the overall clarity of the plane visual image of the interactive interface of the mobile intelligent device is enhanced.
{"title":"Research on color enhancement method of planar image in interactive interface of mobile intelligent device","authors":"Wang Dawei, Meng Xiaomeng","doi":"10.23919/WAC55640.2022.9934494","DOIUrl":"https://doi.org/10.23919/WAC55640.2022.9934494","url":null,"abstract":"The definition of image color is closely related to the plane visual effect of the interactive interface of mobile intelligent devices. In order to improve the visual effect of plane visual image color, the plane visual image color enhancement system of the interactive interface of mobile intelligent devices is deeply studied, and the image acquisition module is designed to extract image information and transmit it to the image color enhancement module. The image color enhancement module uses the color image enhancement algorithm based on visual characteristics to enhance the overall brightness of the plane visual image in the way of histogram nonlinear adaptive lifting; The local contrast of the plane visual image is enhanced according to the correlation between the current point and the regional pixel, and the overall clarity of the plane visual image of the interactive interface of the mobile intelligent device is enhanced.","PeriodicalId":339737,"journal":{"name":"2022 World Automation Congress (WAC)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126033164","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 : 2022-10-11DOI: 10.23919/WAC55640.2022.9934002
Yong Zhu, Lang Liu
From the birth of the Internet to the present, research on the Internet has been going on. Especially development with the integration of new technologies such as Artificial Intelligence (AI), big data, and the Internet of Things (IoT), with the Internet, people are paying more and more attention to the Internet, and the research on the differences between the IoT AI and the traditional Internet is also becoming more and more intense. The purpose of this article is to study the difference between the AI of the IoT and the traditional Internet. This article first summarizes the differences between the IoT AI and the traditional Internet, and then designs the IoT AI architecture system based on the BP neural network, and gives a detailed description of each layer in the architecture. This article introduces the hardware and software environment for deploying the AI system architecture of the IoT, and verifies the usability of the proposed architecture through performance tests. Through the average response time test of the cloud computing layer deployed with single and dual server load balancing, the data shows that when the number of concurrent clients is 1, the single server response time is 18.4ms, and the dual server response time is 17.2ms. When the number is 900, the single server response time is 573.6ms, and the dual server response time is 237.7ms. It can be seen that as the number of concurrent threads increases, the response time of the server is also longer. Moreover, under the condition of equal concurrent threads, the response time of two servers is shorter than that of the cloud computing layer deployed by a single server.
{"title":"Difference between Artificial Intelligence of the Internet of Things and the Traditional Internet","authors":"Yong Zhu, Lang Liu","doi":"10.23919/WAC55640.2022.9934002","DOIUrl":"https://doi.org/10.23919/WAC55640.2022.9934002","url":null,"abstract":"From the birth of the Internet to the present, research on the Internet has been going on. Especially development with the integration of new technologies such as Artificial Intelligence (AI), big data, and the Internet of Things (IoT), with the Internet, people are paying more and more attention to the Internet, and the research on the differences between the IoT AI and the traditional Internet is also becoming more and more intense. The purpose of this article is to study the difference between the AI of the IoT and the traditional Internet. This article first summarizes the differences between the IoT AI and the traditional Internet, and then designs the IoT AI architecture system based on the BP neural network, and gives a detailed description of each layer in the architecture. This article introduces the hardware and software environment for deploying the AI system architecture of the IoT, and verifies the usability of the proposed architecture through performance tests. Through the average response time test of the cloud computing layer deployed with single and dual server load balancing, the data shows that when the number of concurrent clients is 1, the single server response time is 18.4ms, and the dual server response time is 17.2ms. When the number is 900, the single server response time is 573.6ms, and the dual server response time is 237.7ms. It can be seen that as the number of concurrent threads increases, the response time of the server is also longer. Moreover, under the condition of equal concurrent threads, the response time of two servers is shorter than that of the cloud computing layer deployed by a single server.","PeriodicalId":339737,"journal":{"name":"2022 World Automation Congress (WAC)","volume":"17 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125715409","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 : 2022-10-11DOI: 10.23919/WAC55640.2022.9934265
Yuqing Chen
In recent years, with the progress and rapid development of digital information technology in our country, the preservation and inheritance of historical and cultural heritage has also been more and more integrated, and it has become a more ideal way. This article aims to study the construction of human geography data statistics and historical and cultural heritage protection system based on data mining. Based on the analysis of the research characteristics of human geography data, the characteristics of historical and cultural heritage, the process of data mining, the analysis of system requirements and the design of data mining algorithms, the historical and cultural heritage. The protection system was designed, and finally the functional modules of the system were tested. The test results show that during the testing process of the historical and cultural heritage protection system, the functions checked are all operating normally. The system has a friendly interface, simple operation, easy to use and maintain, and provides detailed user documents. The system efficiency is in line with the design documents.
{"title":"Construction of Human Geographical Data Statistics and Historical and Cultural Heritage Protection System Based on Data Mining","authors":"Yuqing Chen","doi":"10.23919/WAC55640.2022.9934265","DOIUrl":"https://doi.org/10.23919/WAC55640.2022.9934265","url":null,"abstract":"In recent years, with the progress and rapid development of digital information technology in our country, the preservation and inheritance of historical and cultural heritage has also been more and more integrated, and it has become a more ideal way. This article aims to study the construction of human geography data statistics and historical and cultural heritage protection system based on data mining. Based on the analysis of the research characteristics of human geography data, the characteristics of historical and cultural heritage, the process of data mining, the analysis of system requirements and the design of data mining algorithms, the historical and cultural heritage. The protection system was designed, and finally the functional modules of the system were tested. The test results show that during the testing process of the historical and cultural heritage protection system, the functions checked are all operating normally. The system has a friendly interface, simple operation, easy to use and maintain, and provides detailed user documents. The system efficiency is in line with the design documents.","PeriodicalId":339737,"journal":{"name":"2022 World Automation Congress (WAC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126673207","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 : 2022-10-11DOI: 10.23919/WAC55640.2022.9934365
Maaya Yano, Naoki Masuyama, Y. Nojima
This paper proposes scalable constrained multimodal distance minimization problems to evaluate algorithm behaviors against a multi-modal property and constraints that often appear in real-world optimization problems. Our previous study proposed two-dimensional constrained multi-modal distance minimization problems (CMDMPs), which include the above characteristics. This paper extends CMDMPs to scalable problems which can define any number of decision variables. They can be used to examine the effects of the number of decision variables on the search performance of constrained multiobjective evolutionary algorithms (MOEAs). In computational experiments, we evaluate two MOEAs, i.e., NSGA-II and DNEA, and three constraint handling methods, i.e., CDP, IEpsilon, and SP, using the proposed CMDMPs.
{"title":"Behavior Analysis of Constrained Multiobjective Evolutionary Algorithms using Scalable Constrained Multi-Modal Distance Minimization Problems","authors":"Maaya Yano, Naoki Masuyama, Y. Nojima","doi":"10.23919/WAC55640.2022.9934365","DOIUrl":"https://doi.org/10.23919/WAC55640.2022.9934365","url":null,"abstract":"This paper proposes scalable constrained multimodal distance minimization problems to evaluate algorithm behaviors against a multi-modal property and constraints that often appear in real-world optimization problems. Our previous study proposed two-dimensional constrained multi-modal distance minimization problems (CMDMPs), which include the above characteristics. This paper extends CMDMPs to scalable problems which can define any number of decision variables. They can be used to examine the effects of the number of decision variables on the search performance of constrained multiobjective evolutionary algorithms (MOEAs). In computational experiments, we evaluate two MOEAs, i.e., NSGA-II and DNEA, and three constraint handling methods, i.e., CDP, IEpsilon, and SP, using the proposed CMDMPs.","PeriodicalId":339737,"journal":{"name":"2022 World Automation Congress (WAC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133720762","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 : 2022-10-11DOI: 10.23919/WAC55640.2022.9934415
Ying Zhou
As a new type of technology, biochemical sensing technology has received great attention from scientific researchers. It is mainly used to develop artificial intelligence sensing equipment. The use of deep neural network algorithms to assist research and development can improve the speed and accuracy of data processing. By constructing a deep neural network model, it is possible to improve the data fitting ability in biochemical sensing equipment and reduce the cost of research and development. This article investigates the current situation of users using biochemical sensing equipment, and the results of the investigation are as follows: Users who know about biochemical sensing equipment account for 51.01% of the total number of people, and users who have never heard of biochemical sensing equipment are only 6.57%; doctors and scientific researchers use more biochemical sensing equipment, accounting for 36% and 34% of the total, respectively. The least users are workers, indicating that the educational level has certain limitations on the popularization of new technologies; among the common biochemical sensing equipment, there are 65 users who know the food composition analyzer and 78 users who know the enzyme electrode sensor, indicating that the two major concerns of users are medical health and food safety.
{"title":"Biochemical Sensing Technology Based on Deep Neural Network Algorithm","authors":"Ying Zhou","doi":"10.23919/WAC55640.2022.9934415","DOIUrl":"https://doi.org/10.23919/WAC55640.2022.9934415","url":null,"abstract":"As a new type of technology, biochemical sensing technology has received great attention from scientific researchers. It is mainly used to develop artificial intelligence sensing equipment. The use of deep neural network algorithms to assist research and development can improve the speed and accuracy of data processing. By constructing a deep neural network model, it is possible to improve the data fitting ability in biochemical sensing equipment and reduce the cost of research and development. This article investigates the current situation of users using biochemical sensing equipment, and the results of the investigation are as follows: Users who know about biochemical sensing equipment account for 51.01% of the total number of people, and users who have never heard of biochemical sensing equipment are only 6.57%; doctors and scientific researchers use more biochemical sensing equipment, accounting for 36% and 34% of the total, respectively. The least users are workers, indicating that the educational level has certain limitations on the popularization of new technologies; among the common biochemical sensing equipment, there are 65 users who know the food composition analyzer and 78 users who know the enzyme electrode sensor, indicating that the two major concerns of users are medical health and food safety.","PeriodicalId":339737,"journal":{"name":"2022 World Automation Congress (WAC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129375755","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 : 2022-10-11DOI: 10.23919/WAC55640.2022.9934346
Qiuyan Tian, Huayan Jiang
With the rapid development of science, technology and social economy, China has stepped into the information age, and "big data" has been transformed from an abstract conceptual vocabulary into something that has deep penetration in all fields of economy and society, has brought enormous commercial value and impetus for change to all walks of life, apps such as Taobao, jd.com, alipay, Didi Dache and Sina Weibo, which are based on big data technology, have brought convenience to people's lives and great opportunities for business development. However, it must be noted that today, with the continuous development of informatization and big data, public information security issues arising with the development of the Internet have become more prominent, and more and more high-value and sensitive documents and materials rely on the Internet for their dissemination, once the computer network security problems caused by data leakage, will bring serious economic losses to users and enterprises, and even to public interests and national security, causing incalculable losses. Therefore, how to apply the big data technology to the public information security maintenance, make the information storage, application and transmission more secure and reliable, and promote the enterprise value-added and benefit-added becomes the key problem that the big data development needs to face.
{"title":"Application of Big Data Technology in Information Security","authors":"Qiuyan Tian, Huayan Jiang","doi":"10.23919/WAC55640.2022.9934346","DOIUrl":"https://doi.org/10.23919/WAC55640.2022.9934346","url":null,"abstract":"With the rapid development of science, technology and social economy, China has stepped into the information age, and \"big data\" has been transformed from an abstract conceptual vocabulary into something that has deep penetration in all fields of economy and society, has brought enormous commercial value and impetus for change to all walks of life, apps such as Taobao, jd.com, alipay, Didi Dache and Sina Weibo, which are based on big data technology, have brought convenience to people's lives and great opportunities for business development. However, it must be noted that today, with the continuous development of informatization and big data, public information security issues arising with the development of the Internet have become more prominent, and more and more high-value and sensitive documents and materials rely on the Internet for their dissemination, once the computer network security problems caused by data leakage, will bring serious economic losses to users and enterprises, and even to public interests and national security, causing incalculable losses. Therefore, how to apply the big data technology to the public information security maintenance, make the information storage, application and transmission more secure and reliable, and promote the enterprise value-added and benefit-added becomes the key problem that the big data development needs to face.","PeriodicalId":339737,"journal":{"name":"2022 World Automation Congress (WAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129653225","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 : 2022-10-11DOI: 10.23919/WAC55640.2022.9934458
Bo Fang
At present, coal resource mining has been regarded as the most dangerous industry in China. It is especially affected by gas explosion disasters. Its serious destructive ability, economic loss and heavy casualties have brought serious damage to the safety of coal mining in our country. This article aims to study the risk decision-making evaluation of mine gas explosion emergency rescue under the Vague set. Based on the analysis of the Vague set, the influencing factors of mine emergency rescue, the risk analysis link and the identification of mine gas explosion hazards, the risk of emergency response to gas explosion was constructed. The empirical research results show that the evaluation results are completely consistent with the evaluation objectives of the basic emergency measures, and have certain guiding significance for the prevention of gas explosions and disaster rescue in the later period.
{"title":"Risk Decision Evaluation of Mine Gas Explosion Emergency Rescue Based on Vague Set","authors":"Bo Fang","doi":"10.23919/WAC55640.2022.9934458","DOIUrl":"https://doi.org/10.23919/WAC55640.2022.9934458","url":null,"abstract":"At present, coal resource mining has been regarded as the most dangerous industry in China. It is especially affected by gas explosion disasters. Its serious destructive ability, economic loss and heavy casualties have brought serious damage to the safety of coal mining in our country. This article aims to study the risk decision-making evaluation of mine gas explosion emergency rescue under the Vague set. Based on the analysis of the Vague set, the influencing factors of mine emergency rescue, the risk analysis link and the identification of mine gas explosion hazards, the risk of emergency response to gas explosion was constructed. The empirical research results show that the evaluation results are completely consistent with the evaluation objectives of the basic emergency measures, and have certain guiding significance for the prevention of gas explosions and disaster rescue in the later period.","PeriodicalId":339737,"journal":{"name":"2022 World Automation Congress (WAC)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126960559","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 : 2022-10-11DOI: 10.23919/WAC55640.2022.9934508
Ren Morita, Saya Ando, Daisuke Fujita, Shoichiro Ishikawa, Koji Onoue, K. Ando, R. Ishikura, Syoji Kobashi
Brain imaging is used to diagnose pediatric brain diseases. However, there is no quantitative method to estimate developmental conditions such as underdevelopment or early growth, and qualitative diagnosis is based on the experience of skilled physicians. Therefore, we are developing a computer-aided diagnosis system to estimate brain age from pediatric brain CT images. This system segmented cranial regions from CT images and calibrated their posture and position. The system also extracts features from CT images using a 3D convolutional neural network (3D CNN) and predicts brain age using a fully connected layer. This paper focuses on the cranial region segmentation method, which is an essential analysis processing method for the system. We investigated two different methods of region segmentation, and a comparison experiment with 204 subjects aged 0 to 3 years (47 months) showed that we could improve 32% of the prediction accuracy of the 3D CNN model.
{"title":"Pediatric Brain CT Image Segmentation Methods for Effective Age Prediction Models","authors":"Ren Morita, Saya Ando, Daisuke Fujita, Shoichiro Ishikawa, Koji Onoue, K. Ando, R. Ishikura, Syoji Kobashi","doi":"10.23919/WAC55640.2022.9934508","DOIUrl":"https://doi.org/10.23919/WAC55640.2022.9934508","url":null,"abstract":"Brain imaging is used to diagnose pediatric brain diseases. However, there is no quantitative method to estimate developmental conditions such as underdevelopment or early growth, and qualitative diagnosis is based on the experience of skilled physicians. Therefore, we are developing a computer-aided diagnosis system to estimate brain age from pediatric brain CT images. This system segmented cranial regions from CT images and calibrated their posture and position. The system also extracts features from CT images using a 3D convolutional neural network (3D CNN) and predicts brain age using a fully connected layer. This paper focuses on the cranial region segmentation method, which is an essential analysis processing method for the system. We investigated two different methods of region segmentation, and a comparison experiment with 204 subjects aged 0 to 3 years (47 months) showed that we could improve 32% of the prediction accuracy of the 3D CNN model.","PeriodicalId":339737,"journal":{"name":"2022 World Automation Congress (WAC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121177925","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：