Pub Date : 2022-10-19DOI: 10.1109/ICTC55196.2022.9952435
Made Adi Paramartha Putra, Mark Verana, G. Sampedro, Dong‐Seong Kim, Jae-Min Lee
This paper proposes a secure federated learning (FL) approach for 3D printer fault detection, namely 3DFed. Most current 3D fault detection systems were developed with a centralized learning approach, which is less efficient for large-scale deployment due to limited data for training. The FL-based system could be exploited to further increase fault detection accuracy while maintaining high performance by using the FedAvg algorithm. The 2D convolutional neural network (CNN) was used to extract data features from an image array. To further improve security in the simulation work, a certificate authority (CA) was added to maintain secure communication between the FL server and clients. The suggested 3DFed with the proposed CNN-based model can deliver high classification accuracy while preserving minimum time-cost, according to a thorough performance evaluation. Also covered in depth is how total client variance affects the learning process.
{"title":"3DFed: A Secure Federated Learning-based System for Fault Detection in 3D Printer Industry","authors":"Made Adi Paramartha Putra, Mark Verana, G. Sampedro, Dong‐Seong Kim, Jae-Min Lee","doi":"10.1109/ICTC55196.2022.9952435","DOIUrl":"https://doi.org/10.1109/ICTC55196.2022.9952435","url":null,"abstract":"This paper proposes a secure federated learning (FL) approach for 3D printer fault detection, namely 3DFed. Most current 3D fault detection systems were developed with a centralized learning approach, which is less efficient for large-scale deployment due to limited data for training. The FL-based system could be exploited to further increase fault detection accuracy while maintaining high performance by using the FedAvg algorithm. The 2D convolutional neural network (CNN) was used to extract data features from an image array. To further improve security in the simulation work, a certificate authority (CA) was added to maintain secure communication between the FL server and clients. The suggested 3DFed with the proposed CNN-based model can deliver high classification accuracy while preserving minimum time-cost, according to a thorough performance evaluation. Also covered in depth is how total client variance affects the learning process.","PeriodicalId":441404,"journal":{"name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130136591","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 : 2022-10-19DOI: 10.1109/ICTC55196.2022.9952824
Raisa Islam, Mohammad Sahinur Hossen, Dongwan Shin
Application domains like big data and IoT require a lot of user data collected and analyzed to extract useful information, and those data might include user's sensitive and personal information. Hence, it is strongly required to ensure the privacy of user data before releasing them in the public space. Since the fields of IoT and big data are constantly evolving with new types of privacy attacks and prevention mechanisms, there is an urgent need for new research and surveys to develop an overview of the state-of-art. We conducted a systematic mapping study on selected papers related to user privacy in IoT and big data, published between 2010 to 2021. This study focuses on identifying the main privacy objectives, attacks and measures taken to prevent the attacks in the two application domains. Additionally, a visualized classification of the existing attacks is presented along with privacy metrics to draw similarities and dissimilarities among different attacks.
{"title":"A Mapping Study on Privacy Attacks in Big Data and IoT","authors":"Raisa Islam, Mohammad Sahinur Hossen, Dongwan Shin","doi":"10.1109/ICTC55196.2022.9952824","DOIUrl":"https://doi.org/10.1109/ICTC55196.2022.9952824","url":null,"abstract":"Application domains like big data and IoT require a lot of user data collected and analyzed to extract useful information, and those data might include user's sensitive and personal information. Hence, it is strongly required to ensure the privacy of user data before releasing them in the public space. Since the fields of IoT and big data are constantly evolving with new types of privacy attacks and prevention mechanisms, there is an urgent need for new research and surveys to develop an overview of the state-of-art. We conducted a systematic mapping study on selected papers related to user privacy in IoT and big data, published between 2010 to 2021. This study focuses on identifying the main privacy objectives, attacks and measures taken to prevent the attacks in the two application domains. Additionally, a visualized classification of the existing attacks is presented along with privacy metrics to draw similarities and dissimilarities among different attacks.","PeriodicalId":441404,"journal":{"name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130201080","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 : 2022-10-19DOI: 10.1109/ICTC55196.2022.9952706
Junhyeong Jo, Seongjun Kim, Jemin Lee
This paper considers a downlink cellular network in which a base station (BS) transmits multi-type data to a user. In this network, we analyze the weighted sum age of information (AoI) violation probability and develop a probability-based receiving data determination (PRD) policy that stochastically selects one of the data types. We then express an optimal receiving data probability and obtain the closed-form expression of that in the special case. Finally, we show that the proposed policy always outperforms the baseline schemes.
{"title":"Probability-based Data Reception in AoI-sensitive Wireless Networks","authors":"Junhyeong Jo, Seongjun Kim, Jemin Lee","doi":"10.1109/ICTC55196.2022.9952706","DOIUrl":"https://doi.org/10.1109/ICTC55196.2022.9952706","url":null,"abstract":"This paper considers a downlink cellular network in which a base station (BS) transmits multi-type data to a user. In this network, we analyze the weighted sum age of information (AoI) violation probability and develop a probability-based receiving data determination (PRD) policy that stochastically selects one of the data types. We then express an optimal receiving data probability and obtain the closed-form expression of that in the special case. Finally, we show that the proposed policy always outperforms the baseline schemes.","PeriodicalId":441404,"journal":{"name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134406163","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 : 2022-10-19DOI: 10.1109/ICTC55196.2022.9952650
R. Chaparadza, Muslim Elkotob, Benoit Radier, T. B. Meriem, T. Choi, R. Bohn, A. Battou, Tao Zhang
Future Networks, Beyond 5G and 6G, will continue to expand in scale, complexity and interconnectivity, and will be highly shaped by distributed systems that serve various use cases that go beyond current Use Cases like mMTC (massive Machine Type Communications) and URLLC (Ultra Reliable Low Latency Communications). This will be coupled with an increasing demand for autonomy in self-organization and self-management, automation and interoperability on a very dynamic flexible basis. Systems-of-systems architectures will become more relevant as multiple autonomous/semi-autonomous systems adaptively seek to operate and interact with their peers (including the advent of so-called “symbiotic autonomous systems”). Research on autonomous systems and autonomic networks recognizes the benefits to interacting with other systems when needed and should explore frameworks that will enable this dynamic interactivity under the emerging concept of Federation of Autonomic/Autonomous networks (ANs). Autonomy and Degree of Autonomy in ANs should be subjected to “governance by humans” through ANs exposure of Governance Interfaces to make sure ANs solely serve purposes that humans expect of them and not negatively impact environment and society. The use of Federation and in some cases Governance interfaces and mechanisms is a promising technology for interconnecting systems, innovation and service delivery by the federating AN systems; and allowing asset sharing and extending traditional eco-systems and value-chains with further resources and stakeholders (including new ones that were never involved in the traditional ICT ecosystems but should now be involved in 5G and 6G ecosystems). ETSI has standardized the concept of so-called GANA (Generic Autonomic Network Architecture) Knowledge Plane (KP) Platform that drives closed-control-loops for Autonomic Management and Control (AMC) operations for a specific ICT network segment(s)—making the network management and operation of the network segment autonomous to some degree (as an AN). The paper provides an analysis of the aspects of relevance to the broader picture of ANs in standardization efforts, multi-layer autonomic systems design and operational principles, federation and governance of ANs, progress in standards, so as to provide contributions on what needs to be complemented to ongoing efforts in standardization groups. But the major contribution of this paper is on the aspect of Requirements for Knowledge Plane (KP) Platforms Driven Networking, by which KP Platforms play the role of anchors for Federation of Autonomic/Autonomous Networks (ANs) Across Industry Sectors. Whereby we consider that KP Platforms should be the anchor Functional Entities through which Federation and Governance of ANs should be achieved such that the federated ANs deliver end-to-end services in an agile and on-demand manor in fulfilling various dynamic communication services needs required for consumption by humans and by machines, and throu
{"title":"The Era of Knowledge Plane (KP) Platforms Driven Networking—Anchor for Federation of Autonomic/Autonomous Networks (ANs) Across Industry Sectors","authors":"R. Chaparadza, Muslim Elkotob, Benoit Radier, T. B. Meriem, T. Choi, R. Bohn, A. Battou, Tao Zhang","doi":"10.1109/ICTC55196.2022.9952650","DOIUrl":"https://doi.org/10.1109/ICTC55196.2022.9952650","url":null,"abstract":"Future Networks, Beyond 5G and 6G, will continue to expand in scale, complexity and interconnectivity, and will be highly shaped by distributed systems that serve various use cases that go beyond current Use Cases like mMTC (massive Machine Type Communications) and URLLC (Ultra Reliable Low Latency Communications). This will be coupled with an increasing demand for autonomy in self-organization and self-management, automation and interoperability on a very dynamic flexible basis. Systems-of-systems architectures will become more relevant as multiple autonomous/semi-autonomous systems adaptively seek to operate and interact with their peers (including the advent of so-called “symbiotic autonomous systems”). Research on autonomous systems and autonomic networks recognizes the benefits to interacting with other systems when needed and should explore frameworks that will enable this dynamic interactivity under the emerging concept of Federation of Autonomic/Autonomous networks (ANs). Autonomy and Degree of Autonomy in ANs should be subjected to “governance by humans” through ANs exposure of Governance Interfaces to make sure ANs solely serve purposes that humans expect of them and not negatively impact environment and society. The use of Federation and in some cases Governance interfaces and mechanisms is a promising technology for interconnecting systems, innovation and service delivery by the federating AN systems; and allowing asset sharing and extending traditional eco-systems and value-chains with further resources and stakeholders (including new ones that were never involved in the traditional ICT ecosystems but should now be involved in 5G and 6G ecosystems). ETSI has standardized the concept of so-called GANA (Generic Autonomic Network Architecture) Knowledge Plane (KP) Platform that drives closed-control-loops for Autonomic Management and Control (AMC) operations for a specific ICT network segment(s)—making the network management and operation of the network segment autonomous to some degree (as an AN). The paper provides an analysis of the aspects of relevance to the broader picture of ANs in standardization efforts, multi-layer autonomic systems design and operational principles, federation and governance of ANs, progress in standards, so as to provide contributions on what needs to be complemented to ongoing efforts in standardization groups. But the major contribution of this paper is on the aspect of Requirements for Knowledge Plane (KP) Platforms Driven Networking, by which KP Platforms play the role of anchors for Federation of Autonomic/Autonomous Networks (ANs) Across Industry Sectors. Whereby we consider that KP Platforms should be the anchor Functional Entities through which Federation and Governance of ANs should be achieved such that the federated ANs deliver end-to-end services in an agile and on-demand manor in fulfilling various dynamic communication services needs required for consumption by humans and by machines, and throu","PeriodicalId":441404,"journal":{"name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131677846","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 : 2022-10-19DOI: 10.1109/ICTC55196.2022.9952661
D. M. S. Bhatti, Muhammad Haris, Haewoon Nam
Federated learning is a privacy preserving method of training the model on server by utilizing the end users' private data without accessing it. The central server shares the global model with all end users, called clients of the network. The clients are required to train the shared global model using their local datasets. The updated local trained models are forwarded back to the server to further update the global model. This process of training the global model is carried out for several rounds. The procedure of updating the local model and transmitting back to the server rises the communication cost. Since several clients are involved in training the global model, the aggregated communication cost of the network is escalated. This article proposes a communication effective aggregation method for federated learning, which considers the volume and variety of local clients' data before aggregation. The proposed approach is compared with the conventional methods and it achieves highest accuracy and minimum loss with respect to aggregated communication cost.
{"title":"A Communication Efficient Approach of Global Training in Federated Learning","authors":"D. M. S. Bhatti, Muhammad Haris, Haewoon Nam","doi":"10.1109/ICTC55196.2022.9952661","DOIUrl":"https://doi.org/10.1109/ICTC55196.2022.9952661","url":null,"abstract":"Federated learning is a privacy preserving method of training the model on server by utilizing the end users' private data without accessing it. The central server shares the global model with all end users, called clients of the network. The clients are required to train the shared global model using their local datasets. The updated local trained models are forwarded back to the server to further update the global model. This process of training the global model is carried out for several rounds. The procedure of updating the local model and transmitting back to the server rises the communication cost. Since several clients are involved in training the global model, the aggregated communication cost of the network is escalated. This article proposes a communication effective aggregation method for federated learning, which considers the volume and variety of local clients' data before aggregation. The proposed approach is compared with the conventional methods and it achieves highest accuracy and minimum loss with respect to aggregated communication cost.","PeriodicalId":441404,"journal":{"name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131711963","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 : 2022-10-19DOI: 10.1109/ICTC55196.2022.9953006
M. Kang
In this short position paper, we discuss several potential security concerns that can be found at the physical layer of 6th-generation (6G) cellular networks. Discussion on 6G cellular networks is still at its early stage and thus several candidate radio technologies have been proposed but no single technology has yet been finally selected for 6G systems. Among several radio technologies, we focus on three promising ones for 6G physical-layer technologies: reconfigurable intelligent surface (RIS), Open-RAN (O-RAN), and full-duplex radios. We hope this position paper will spark more active discussion on the security concerns in these new radio technologies.
在这篇简短的立场文件中，我们讨论了在第6代(6G)蜂窝网络物理层可能存在的几个潜在安全问题。关于6G蜂窝网络的讨论仍处于早期阶段，因此已经提出了几种候选无线电技术，但尚未最终选定用于6G系统的单一技术。在几种无线电技术中，我们重点关注三种有前途的6G物理层技术:可重构智能表面(RIS)，开放- ran (O-RAN)和全双工无线电。我们希望这份立场文件将引发对这些新无线电技术安全问题的更积极讨论。
{"title":"Potential Security Concerns at the Physical Layer of 6G Cellular Systems","authors":"M. Kang","doi":"10.1109/ICTC55196.2022.9953006","DOIUrl":"https://doi.org/10.1109/ICTC55196.2022.9953006","url":null,"abstract":"In this short position paper, we discuss several potential security concerns that can be found at the physical layer of 6th-generation (6G) cellular networks. Discussion on 6G cellular networks is still at its early stage and thus several candidate radio technologies have been proposed but no single technology has yet been finally selected for 6G systems. Among several radio technologies, we focus on three promising ones for 6G physical-layer technologies: reconfigurable intelligent surface (RIS), Open-RAN (O-RAN), and full-duplex radios. We hope this position paper will spark more active discussion on the security concerns in these new radio technologies.","PeriodicalId":441404,"journal":{"name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132602163","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 : 2022-10-19DOI: 10.1109/ICTC55196.2022.9952845
Yoon-Seok Choi, Jae Woo Kim, Soonchul Jung, Hyeong-Ju Jeon, Jin-Seo Kim
Scientific connoisseurship of painting works is a process of making hypotheses and validating them by carrying out rigorous observation on the artwork. The final conclusions are drawn by the authentication experts based on the measurement data obtained by using chemical and material analysis instruments. Authentication experts and scientists have recently employed various analysis techniques used in chemical and material analysis into the scientific connoisseurship to maximize the accuracy of the process. This paper suggests an integrated software tool to assist the scientific connoisseurship. The software tool developed in this research has the capabilities for effective visualization and efficient data management for the huge amount of analysis data related to the authentication of artwork
{"title":"Efficient Analytical Data Processing and Visualization Methods for Supporting Scientific Connoisseurship on Oil Paintings","authors":"Yoon-Seok Choi, Jae Woo Kim, Soonchul Jung, Hyeong-Ju Jeon, Jin-Seo Kim","doi":"10.1109/ICTC55196.2022.9952845","DOIUrl":"https://doi.org/10.1109/ICTC55196.2022.9952845","url":null,"abstract":"Scientific connoisseurship of painting works is a process of making hypotheses and validating them by carrying out rigorous observation on the artwork. The final conclusions are drawn by the authentication experts based on the measurement data obtained by using chemical and material analysis instruments. Authentication experts and scientists have recently employed various analysis techniques used in chemical and material analysis into the scientific connoisseurship to maximize the accuracy of the process. This paper suggests an integrated software tool to assist the scientific connoisseurship. The software tool developed in this research has the capabilities for effective visualization and efficient data management for the huge amount of analysis data related to the authentication of artwork","PeriodicalId":441404,"journal":{"name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131007704","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 : 2022-10-19DOI: 10.1109/ICTC55196.2022.9952870
N. Mahmood, Hossein Rezaei, Antti Pauanne, Gweon-Do Jo, Jaesheung Shin, H. Chung, A. Pouttu, M. Latva-aho
While the fifth generation (5G) New Radio wireless system is being deployed across the globe, the wireless research community has started exploring what will the sixth generation (6G) be? 6G is expected to cater to societal and economic needs by integrating the biological, physical, and virtual worlds with the networks. The notion of multi-service communication introduced in 5G will be further diversified and expanded to include new service classes representing novel and emerging use cases that were not considered as a part of the 5G landscape. Ultra-reliable low-latency communications (URLLC) and their evolution in 6G are of particular interest given their prominent role in enabling future industrial Internet of Things (IIoT) applications. During 2020-2022, ETRI from South Korea and the University of Oulu from Finland convened a joint project to explore URLLC evolution towards the 6G era. This article summarizes the key highlights of the project and outlines its main findings. The project involved a study of future URLLC service classes and their potential enablers, along with a demonstration of remote monitoring of a smart factory over an intercontinental link. The project's proof-of-concept was able to demonstrate remote monitoring of ETRI's IIoT testbed from Finland at sub-300 ms service round trip time.
{"title":"Remote Monitoring of a Smart Factory Over an Intercontinental Link: Vistas from Etri-Oulu Collaboration Project","authors":"N. Mahmood, Hossein Rezaei, Antti Pauanne, Gweon-Do Jo, Jaesheung Shin, H. Chung, A. Pouttu, M. Latva-aho","doi":"10.1109/ICTC55196.2022.9952870","DOIUrl":"https://doi.org/10.1109/ICTC55196.2022.9952870","url":null,"abstract":"While the fifth generation (5G) New Radio wireless system is being deployed across the globe, the wireless research community has started exploring what will the sixth generation (6G) be? 6G is expected to cater to societal and economic needs by integrating the biological, physical, and virtual worlds with the networks. The notion of multi-service communication introduced in 5G will be further diversified and expanded to include new service classes representing novel and emerging use cases that were not considered as a part of the 5G landscape. Ultra-reliable low-latency communications (URLLC) and their evolution in 6G are of particular interest given their prominent role in enabling future industrial Internet of Things (IIoT) applications. During 2020-2022, ETRI from South Korea and the University of Oulu from Finland convened a joint project to explore URLLC evolution towards the 6G era. This article summarizes the key highlights of the project and outlines its main findings. The project involved a study of future URLLC service classes and their potential enablers, along with a demonstration of remote monitoring of a smart factory over an intercontinental link. The project's proof-of-concept was able to demonstrate remote monitoring of ETRI's IIoT testbed from Finland at sub-300 ms service round trip time.","PeriodicalId":441404,"journal":{"name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131254362","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 : 2022-10-19DOI: 10.1109/ICTC55196.2022.9952625
Bumhwi Kim, Eunryung Lee
This paper deals with the description of a framework that assists medical device imaging developers to develop medical imaging AI software more easily than using existing deep learning libraries to create medical imaging AI software. The framework proposed in this paper includes TensorFlow and PyTorch deep learning libraries, as well as image preprocessing libraries, and systematized them so that beginners to experts can handle them.
{"title":"Medical artificial intelligence framework for the development of medical imaging artificial intelligence devices","authors":"Bumhwi Kim, Eunryung Lee","doi":"10.1109/ICTC55196.2022.9952625","DOIUrl":"https://doi.org/10.1109/ICTC55196.2022.9952625","url":null,"abstract":"This paper deals with the description of a framework that assists medical device imaging developers to develop medical imaging AI software more easily than using existing deep learning libraries to create medical imaging AI software. The framework proposed in this paper includes TensorFlow and PyTorch deep learning libraries, as well as image preprocessing libraries, and systematized them so that beginners to experts can handle them.","PeriodicalId":441404,"journal":{"name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133634984","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 : 2022-10-19DOI: 10.1109/ICTC55196.2022.9952693
Yang Yu, Sanghwan Lee
As the level of autonomous driving(AD) increases, the number of sensors in a single vehicle increases, and the required computing power also increases rapidly. The intelligence level of AD depends on algorithms and hardware performance. However, due to the problems such as limited production cost or computing resources, some vehicles may not have enough computation power for high level of AD. To overcome such obstacles, the distributed AD system architecture based on edge computing has become a trend. We build an edge computing-based distributed AD system on top of Robot Operating System(ROS2) and measure the performance with different settings. Our test results show the feasibility of AD systems centered on edge computing units, which open new research directions for exploiting edge computing in a more diverse way.
{"title":"Measurements of the Benefits of Edge Computing on Autonomous Driving","authors":"Yang Yu, Sanghwan Lee","doi":"10.1109/ICTC55196.2022.9952693","DOIUrl":"https://doi.org/10.1109/ICTC55196.2022.9952693","url":null,"abstract":"As the level of autonomous driving(AD) increases, the number of sensors in a single vehicle increases, and the required computing power also increases rapidly. The intelligence level of AD depends on algorithms and hardware performance. However, due to the problems such as limited production cost or computing resources, some vehicles may not have enough computation power for high level of AD. To overcome such obstacles, the distributed AD system architecture based on edge computing has become a trend. We build an edge computing-based distributed AD system on top of Robot Operating System(ROS2) and measure the performance with different settings. Our test results show the feasibility of AD systems centered on edge computing units, which open new research directions for exploiting edge computing in a more diverse way.","PeriodicalId":441404,"journal":{"name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131265018","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：