Pub Date : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583219
Muhammad A. Khan, Anwer Ghani, M. Obaidat, P. Vijayakumar, Khwaja Mansoor, Shehzad Ashraf Chaudhry
As digital content transmission through the internet is convenient and quick, so the outspread of digital content is very high. However, along with this incredible speed and ease, current communication technologies and computers have also brought with them plenty of digital rights management complications. Digital Rights Management Systems are designed to limit the access to the utilization, alternation, and distribution of persevered digital content. This article scrutinized two recent schemes of Lee et al. and Yu et al. and it is found that these schemes are suspected to an insider attack, stolen smart-card attack, Daniel of services (Dos) attack, and impersonation attack. Furthermore, their proposal also suffers from incorrect issues. To fix these flaws, a robust anonymous authentication scheme using biometrics for Digital Rights Management System is proposed in this article. The proposed scheme is checked for correctness and its security is proved through BAN logic. The performance of the scheme is also analyzed using computation time and communication time. The results show that the designed scheme is highly secure with the same computation and communication cost as the existing protocols.
{"title":"A Robust Anonymous Authentication Scheme using Biometrics for Digital Rights Management System","authors":"Muhammad A. Khan, Anwer Ghani, M. Obaidat, P. Vijayakumar, Khwaja Mansoor, Shehzad Ashraf Chaudhry","doi":"10.1109/CCCI52664.2021.9583219","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583219","url":null,"abstract":"As digital content transmission through the internet is convenient and quick, so the outspread of digital content is very high. However, along with this incredible speed and ease, current communication technologies and computers have also brought with them plenty of digital rights management complications. Digital Rights Management Systems are designed to limit the access to the utilization, alternation, and distribution of persevered digital content. This article scrutinized two recent schemes of Lee et al. and Yu et al. and it is found that these schemes are suspected to an insider attack, stolen smart-card attack, Daniel of services (Dos) attack, and impersonation attack. Furthermore, their proposal also suffers from incorrect issues. To fix these flaws, a robust anonymous authentication scheme using biometrics for Digital Rights Management System is proposed in this article. The proposed scheme is checked for correctness and its security is proved through BAN logic. The performance of the scheme is also analyzed using computation time and communication time. The results show that the designed scheme is highly secure with the same computation and communication cost as the existing protocols.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127902870","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583190
Harsh Mankodiya, M. Obaidat, Rajesh Gupta, S. Tanwar
Artificial intelligence (AI) is the most looked up technology with a diverse range of applications across all the fields, whether it is intelligent transportation systems (ITS), medicine, healthcare, military operations, or others. One such application is autonomous vehicles (AVs), which comes under the category of AI in ITS. Vehicular Adhoc Networks (VANET) makes communication possible between AVs in the system. The performance of each vehicle depends upon the information exchanged between AVs. False or malicious information can perturb the whole system leading to severe consequences. Hence, the detection of malicious vehicles is of utmost importance. We use machine learning (ML) algorithms to predict the flaw in the data transmitted. Recent papers that used the stacking ML approach gave an accuracy of 98.44%. Decision tree-based random forest is used to solve the problem in this paper. We achieved accuracy and F1 score of 98.43% and 98.5% respectively on the VeRiMi dataset in this paper. Explainable AI (XAI) is the method and technique to make the complex black-box ML and deep learning (DL) models more interpretable and understandable. We use a particular model interface of the evaluation metrics to explain and measure the model’s performance. Applying XAI to these complex AI models can ensure a cautious use of AI for AVs.
{"title":"XAI-AV: Explainable Artificial Intelligence for Trust Management in Autonomous Vehicles","authors":"Harsh Mankodiya, M. Obaidat, Rajesh Gupta, S. Tanwar","doi":"10.1109/CCCI52664.2021.9583190","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583190","url":null,"abstract":"Artificial intelligence (AI) is the most looked up technology with a diverse range of applications across all the fields, whether it is intelligent transportation systems (ITS), medicine, healthcare, military operations, or others. One such application is autonomous vehicles (AVs), which comes under the category of AI in ITS. Vehicular Adhoc Networks (VANET) makes communication possible between AVs in the system. The performance of each vehicle depends upon the information exchanged between AVs. False or malicious information can perturb the whole system leading to severe consequences. Hence, the detection of malicious vehicles is of utmost importance. We use machine learning (ML) algorithms to predict the flaw in the data transmitted. Recent papers that used the stacking ML approach gave an accuracy of 98.44%. Decision tree-based random forest is used to solve the problem in this paper. We achieved accuracy and F1 score of 98.43% and 98.5% respectively on the VeRiMi dataset in this paper. Explainable AI (XAI) is the method and technique to make the complex black-box ML and deep learning (DL) models more interpretable and understandable. We use a particular model interface of the evaluation metrics to explain and measure the model’s performance. Applying XAI to these complex AI models can ensure a cautious use of AI for AVs.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125674786","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583220
Matthieu Moreau, Tarek Benkhelif
As federated learning (FL) grows and new techniques are created to improve its efficiency and robustness, differential privacy (DP) proved to be a good ally for protecting users’ information. The differentially private version of stochastic gradient descent (DPSGD) is one of the most promising methods for enforcing privacy in machine learning algorithms. The noise added in DPSGD plays an important role in the convergence and performance of a model but also in the resulting privacy guarantee and must thus be chosen carefully. This paper reviews the effects of either selecting fixed or adaptive noise when training federated models under the cross-silo setting. We highlight their strengths and weaknesses and propose a hybrid approach, getting the best of both worlds.
{"title":"DPSGD Strategies for Cross-Silo Federated Learning","authors":"Matthieu Moreau, Tarek Benkhelif","doi":"10.1109/CCCI52664.2021.9583220","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583220","url":null,"abstract":"As federated learning (FL) grows and new techniques are created to improve its efficiency and robustness, differential privacy (DP) proved to be a good ally for protecting users’ information. The differentially private version of stochastic gradient descent (DPSGD) is one of the most promising methods for enforcing privacy in machine learning algorithms. The noise added in DPSGD plays an important role in the convergence and performance of a model but also in the resulting privacy guarantee and must thus be chosen carefully. This paper reviews the effects of either selecting fixed or adaptive noise when training federated models under the cross-silo setting. We highlight their strengths and weaknesses and propose a hybrid approach, getting the best of both worlds.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131957790","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583213
Rajesh Gupta, S. Tanwar, M. Obaidat, Sudhanshu Tyagi, Neeraj Kumar
Machine-to-machine and device-to-device communications are very common in the era of the Internet of things (IoT). In 5G-enabled IoT, massive machine type communication and enhanced Mobile broadband are two supporting protocols ensuring communication among a large number of devices. On the other side, for human-to-machine communication, end-to-end latency, resource availability, high reliability, and end-to-end security are the major hurdles for several applications deployed in different network domains. The above-mentioned issues require a unique solution to maintain Quality of Service and Quality of Experience for industry 4.0 based applications. Therefore, to mitigate the aforementioned issues, here, we present the Tactile Internet, a new technology with its various components in a nutshell. Existing proposals reveal that Tactile Internet can form the interactions between virtual objects and the real environment by maintaining 1ms latency, 99.999% availability, and end-to-end security. Hence, it works like middleware to meet out the ultra-reliable low latency requirements of future 5G-based applications. Moreover, the article provides the possible use cases for Tactile Internet and its usage. Finally, we evaluate the results of applications with Tactile Internet and LTE-A communication networks in the context of data access latency and connection density. Applications with Tactile Internet as a backbone network outperform the traditional LTE-A networks.
{"title":"Capsule: All you need to know about Tactile Internet in a Nutshell","authors":"Rajesh Gupta, S. Tanwar, M. Obaidat, Sudhanshu Tyagi, Neeraj Kumar","doi":"10.1109/CCCI52664.2021.9583213","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583213","url":null,"abstract":"Machine-to-machine and device-to-device communications are very common in the era of the Internet of things (IoT). In 5G-enabled IoT, massive machine type communication and enhanced Mobile broadband are two supporting protocols ensuring communication among a large number of devices. On the other side, for human-to-machine communication, end-to-end latency, resource availability, high reliability, and end-to-end security are the major hurdles for several applications deployed in different network domains. The above-mentioned issues require a unique solution to maintain Quality of Service and Quality of Experience for industry 4.0 based applications. Therefore, to mitigate the aforementioned issues, here, we present the Tactile Internet, a new technology with its various components in a nutshell. Existing proposals reveal that Tactile Internet can form the interactions between virtual objects and the real environment by maintaining 1ms latency, 99.999% availability, and end-to-end security. Hence, it works like middleware to meet out the ultra-reliable low latency requirements of future 5G-based applications. Moreover, the article provides the possible use cases for Tactile Internet and its usage. Finally, we evaluate the results of applications with Tactile Internet and LTE-A communication networks in the context of data access latency and connection density. Applications with Tactile Internet as a backbone network outperform the traditional LTE-A networks.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115267054","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583221
Khaled Rabieh, A. Aydogan, Marianne A. Azer
About 1.2 million people lose their lives on roads yearly due to accidents despite the emerging and uprising technology in contemporary vehicles. In addition, 4.4 million people were seriously injured and required medical attention in crashes last year. By employing Vehicle-to-Pedestrian (V2P) communication between drivers and vulnerable road users, fewer casualties are likely to occur and roads are expected to be much safer. In this paper, we propose a lightweight scheme to protect vulnerable road users based on communication between smartphones and on-board units installed in vehicles. Initially, the signal strength is used to estimate the distance between vehicles and pedestrians and predict the occurrence of a collision. Since signal strength alone can result in false alarms, we propose a collision detection algorithm to confirm a collision. The algorithm is run on both sides; the drivers and vulnerable road users to give appropriate and real-time warnings of a potential accident/collision. Vehicles and road users exchange their Global Positioning System (GPS) locations using Dedicated Short Range Communications (DSRC). The algorithm constructs a vector representing the vehicle path and uses efficient and simple mathematical operations to determine if there is a possibility of collision or not. Our scheme contributes to the safety applications of vehicular ad hoc networks. Our experiment’s results confirm that the proposed scheme can effectively detect collisions with minimum computation overhead.
{"title":"Towards Safer Roads: An Efficient VANET-based Pedestrian Protection Scheme","authors":"Khaled Rabieh, A. Aydogan, Marianne A. Azer","doi":"10.1109/CCCI52664.2021.9583221","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583221","url":null,"abstract":"About 1.2 million people lose their lives on roads yearly due to accidents despite the emerging and uprising technology in contemporary vehicles. In addition, 4.4 million people were seriously injured and required medical attention in crashes last year. By employing Vehicle-to-Pedestrian (V2P) communication between drivers and vulnerable road users, fewer casualties are likely to occur and roads are expected to be much safer. In this paper, we propose a lightweight scheme to protect vulnerable road users based on communication between smartphones and on-board units installed in vehicles. Initially, the signal strength is used to estimate the distance between vehicles and pedestrians and predict the occurrence of a collision. Since signal strength alone can result in false alarms, we propose a collision detection algorithm to confirm a collision. The algorithm is run on both sides; the drivers and vulnerable road users to give appropriate and real-time warnings of a potential accident/collision. Vehicles and road users exchange their Global Positioning System (GPS) locations using Dedicated Short Range Communications (DSRC). The algorithm constructs a vector representing the vehicle path and uses efficient and simple mathematical operations to determine if there is a possibility of collision or not. Our scheme contributes to the safety applications of vehicular ad hoc networks. Our experiment’s results confirm that the proposed scheme can effectively detect collisions with minimum computation overhead.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133520265","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583212
K. Shima
Detecting the anomalous behavior of traffic is one of the important actions for network operators. In this study, we applied term frequency – inverse document frequency (TF–IDF), which is a popular method used in natural language processing, to detect unusual behavior from network access logs. We mapped the term and document concept to the port number and daily access history, respectively, and calculated the TF–IDF. With this approach, we could obtain ports frequently observed in fewer days compared to other port access activities. Such access behaviors are not always malicious activities; however, such information is a good indicator for starting a deeper analysis of traffic behavior. Using a real-life dataset, we could detect two bot-oriented accesses and one unique UDP traffic.
{"title":"Catching Unusual Traffic Behavior using TF–IDF-based Port Access Statistics Analysis","authors":"K. Shima","doi":"10.1109/CCCI52664.2021.9583212","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583212","url":null,"abstract":"Detecting the anomalous behavior of traffic is one of the important actions for network operators. In this study, we applied term frequency – inverse document frequency (TF–IDF), which is a popular method used in natural language processing, to detect unusual behavior from network access logs. We mapped the term and document concept to the port number and daily access history, respectively, and calculated the TF–IDF. With this approach, we could obtain ports frequently observed in fewer days compared to other port access activities. Such access behaviors are not always malicious activities; however, such information is a good indicator for starting a deeper analysis of traffic behavior. Using a real-life dataset, we could detect two bot-oriented accesses and one unique UDP traffic.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133334192","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583193
Mengyao Yang, Junpeng Qi
Due to severe information loss of low-resolution images, the development of single-image super-resolution methods is limited. Recently, the reference-based image super-resolution methods, which super-resolve the low-resolution inputs with the guidance of high-resolution reference images are emerging. In this paper, we design a Dual-Variational AutoEncoder (DVAE) for reference-based image super-resolution task, which can learn the high-frequency information and latent distribution of the high-resolution reference images as priors to improve the restoration quality of image super-resolution. Moreover, a hierarchical variational autoencoder strategy is exploited to further study latent space. Complementary to a quantitative evaluation, we demonstrate the effectiveness of the proposed approach.
{"title":"Reference-based Image Super-Resolution by Dual-Variational AutoEncoder","authors":"Mengyao Yang, Junpeng Qi","doi":"10.1109/CCCI52664.2021.9583193","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583193","url":null,"abstract":"Due to severe information loss of low-resolution images, the development of single-image super-resolution methods is limited. Recently, the reference-based image super-resolution methods, which super-resolve the low-resolution inputs with the guidance of high-resolution reference images are emerging. In this paper, we design a Dual-Variational AutoEncoder (DVAE) for reference-based image super-resolution task, which can learn the high-frequency information and latent distribution of the high-resolution reference images as priors to improve the restoration quality of image super-resolution. Moreover, a hierarchical variational autoencoder strategy is exploited to further study latent space. Complementary to a quantitative evaluation, we demonstrate the effectiveness of the proposed approach.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130517384","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583192
Kajal Chatterjee, M. Obaidat, Debabrata Samanta, B. Sadoun, SK Hafizul Islam, Rajdeep Chatterjee
Classification of soil is crucial for the agricultural domain as it is an essential task in geology and engineering domains. Various procedures are proposed to classify soil types in the literature, but many of them consumed much time or required specially designed equipments/applications. Classification of soil involves the accounting of various factors due to its diversified nature. It can be observed that several critical domain-oriented decisions often depend on the type of soil like farmers might be benefitted from knowing the kind of soil to choose crops accordingly for cultivation. We have employed different Convolution Neural Network (CNN) architectures to identify the soil type accurately in real-time. This paper describes the comparative evaluation in terms of performances of various CNN architectures, namely, ResNet50, VGG19, MobileNetV2, VGG16, NASNetMobile, and InceptionV3. These CNN models are used to classify four types of soils: Clay, Black, Alluvial, and Red. The performance of the ResNet50 model is the best with a training accuracy and training loss of 99.47% and 0.0252, respectively compared to other competing models considered in this paper.
{"title":"Classification of Soil Images using Convolution Neural Networks","authors":"Kajal Chatterjee, M. Obaidat, Debabrata Samanta, B. Sadoun, SK Hafizul Islam, Rajdeep Chatterjee","doi":"10.1109/CCCI52664.2021.9583192","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583192","url":null,"abstract":"Classification of soil is crucial for the agricultural domain as it is an essential task in geology and engineering domains. Various procedures are proposed to classify soil types in the literature, but many of them consumed much time or required specially designed equipments/applications. Classification of soil involves the accounting of various factors due to its diversified nature. It can be observed that several critical domain-oriented decisions often depend on the type of soil like farmers might be benefitted from knowing the kind of soil to choose crops accordingly for cultivation. We have employed different Convolution Neural Network (CNN) architectures to identify the soil type accurately in real-time. This paper describes the comparative evaluation in terms of performances of various CNN architectures, namely, ResNet50, VGG19, MobileNetV2, VGG16, NASNetMobile, and InceptionV3. These CNN models are used to classify four types of soils: Clay, Black, Alluvial, and Red. The performance of the ResNet50 model is the best with a training accuracy and training loss of 99.47% and 0.0252, respectively compared to other competing models considered in this paper.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133813744","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583200
Xiaoling Guo, Y. Yang, Xinyu Song, Hongmiao Yao, Fudong Zhang
Analyzing the structure of complex networks accurately and efficiently has become one hot topic due to the large-scale network in recent academic research. The existing optimization methods for community mining are mostly based on the function Q proposed by Newman. In this paper we introduce two complex network clustering algorithm models FN and spectral clustering. They are both aimed to maximize the value of function Q, the differences are that FN uses overall information and spectral clustering uses spectral graph theory. Then finally we apply these algorithms to analyze Chinese aviation network and come to conclude that Chinese aviation network is mainly composed of East-West and North-South routes, with which we can arrange the community structure.
{"title":"Discover Community Structure in Network by Optimization Algorithm Based on Modular Function","authors":"Xiaoling Guo, Y. Yang, Xinyu Song, Hongmiao Yao, Fudong Zhang","doi":"10.1109/CCCI52664.2021.9583200","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583200","url":null,"abstract":"Analyzing the structure of complex networks accurately and efficiently has become one hot topic due to the large-scale network in recent academic research. The existing optimization methods for community mining are mostly based on the function Q proposed by Newman. In this paper we introduce two complex network clustering algorithm models FN and spectral clustering. They are both aimed to maximize the value of function Q, the differences are that FN uses overall information and spectral clustering uses spectral graph theory. Then finally we apply these algorithms to analyze Chinese aviation network and come to conclude that Chinese aviation network is mainly composed of East-West and North-South routes, with which we can arrange the community structure.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127141502","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 : 2021-10-15DOI: 10.1109/CCCI52664.2021.9583188
A. Valkanis, Georgios I. Papadimitriou, Petros Nicopolitidis, G. Beletsioti, Emmanouel Varvarigos
Elastic optical networks (EONs) are expected to cover the huge bandwidth demands, which will arise in the coming years from both the applications’ evolution and the implementation of 5G and Internet of Things technologies. Harvesting the flexibility offered by EONs in the management of resources, poses challenges for the research community in terms of creating mechanisms that will maximize their efficiency. One of the main research fields in this direction is the prediction of the traffic in the backbone networks and the utilization of this information for efficient resource management. In this work, we present a traffic prediction assisted routing algorithm for elastic optical networks, which improves their overall performance. Detailed simulation scenarios confirm the effectiveness of the proposed routing algorithm, which improves the network blocking probability in comparison to related algorithms from the literature.
{"title":"A Traffic Prediction assisted Routing Algorithm for Elastic Optical Networks","authors":"A. Valkanis, Georgios I. Papadimitriou, Petros Nicopolitidis, G. Beletsioti, Emmanouel Varvarigos","doi":"10.1109/CCCI52664.2021.9583188","DOIUrl":"https://doi.org/10.1109/CCCI52664.2021.9583188","url":null,"abstract":"Elastic optical networks (EONs) are expected to cover the huge bandwidth demands, which will arise in the coming years from both the applications’ evolution and the implementation of 5G and Internet of Things technologies. Harvesting the flexibility offered by EONs in the management of resources, poses challenges for the research community in terms of creating mechanisms that will maximize their efficiency. One of the main research fields in this direction is the prediction of the traffic in the backbone networks and the utilization of this information for efficient resource management. In this work, we present a traffic prediction assisted routing algorithm for elastic optical networks, which improves their overall performance. Detailed simulation scenarios confirm the effectiveness of the proposed routing algorithm, which improves the network blocking probability in comparison to related algorithms from the literature.","PeriodicalId":136382,"journal":{"name":"2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129818339","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：