Pub Date : 2023-06-01DOI: 10.1109/IOTM.001.2200275
Shahnila Rahim, Limei Peng
The space-air-ground collaborative computing networks (SAGCCN) are promising in providing full connectivity for 5G-Advanced and 6G-driven IoT applications. In particular, the SAGCCN can flexibly integrate the communication and computation resources from terrestrial to the sky, thus providing a viable solution for seamless communication and computation services for massive IoT applications. This article discusses the intelligent technologies required to enable full intelligence in data collection and offloading in SAGCCN. In particular, several machine learning-based trajectory planning scenarios are discussed in detail. Finally, this article explores the challenges and future research opportunities in the area of aerial computing.
{"title":"Intelligent Space-Air-Ground Collaborative Computing Networks","authors":"Shahnila Rahim, Limei Peng","doi":"10.1109/IOTM.001.2200275","DOIUrl":"https://doi.org/10.1109/IOTM.001.2200275","url":null,"abstract":"The space-air-ground collaborative computing networks (SAGCCN) are promising in providing full connectivity for 5G-Advanced and 6G-driven IoT applications. In particular, the SAGCCN can flexibly integrate the communication and computation resources from terrestrial to the sky, thus providing a viable solution for seamless communication and computation services for massive IoT applications. This article discusses the intelligent technologies required to enable full intelligence in data collection and offloading in SAGCCN. In particular, several machine learning-based trajectory planning scenarios are discussed in detail. Finally, this article explores the challenges and future research opportunities in the area of aerial computing.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114797175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.1109/IOTM.001.2300021
Vinayakumar Ravi, T. Pham, M. Alazab
This article presents a deep learning-based approach for network-based intrusion detection in the Internet of medical things (IoMT) systems using features of network flows and patient biometrics. The proposed approach effectively learns optimal feature representation by passing the information of network flows and patient biometrics into more than one hidden layer of deep learning. The network includes a global attention layer which helps to effectively extract the optimal features from the spatial and temporal features of deep learning. To avoid data imbalance, a cost-sensitive learning approach is integrated into the deep learning model. The proposed model showed a 10-fold cross-validation accuracy of 95 percent on network features, 89 percent on patient biometrics, and 99 percent on combined features. In addition to the IoMT environment, the robustness and generalization ability of the proposed model is shown by conducting experiments on other network-based intrusion datasets. The proposed approach outperformed the existing methods in all the test cases mainly showing a 3.9 percent higher accuracy on the IoMT intrusion dataset. The proposed model can be used as an IoMT network monitoring tool to safeguard the IoMT devices and networks from attackers inside the healthcare and medical environment.
{"title":"Deep Learning-Based Network Intrusion Detection System for Internet of Medical Things","authors":"Vinayakumar Ravi, T. Pham, M. Alazab","doi":"10.1109/IOTM.001.2300021","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300021","url":null,"abstract":"This article presents a deep learning-based approach for network-based intrusion detection in the Internet of medical things (IoMT) systems using features of network flows and patient biometrics. The proposed approach effectively learns optimal feature representation by passing the information of network flows and patient biometrics into more than one hidden layer of deep learning. The network includes a global attention layer which helps to effectively extract the optimal features from the spatial and temporal features of deep learning. To avoid data imbalance, a cost-sensitive learning approach is integrated into the deep learning model. The proposed model showed a 10-fold cross-validation accuracy of 95 percent on network features, 89 percent on patient biometrics, and 99 percent on combined features. In addition to the IoMT environment, the robustness and generalization ability of the proposed model is shown by conducting experiments on other network-based intrusion datasets. The proposed approach outperformed the existing methods in all the test cases mainly showing a 3.9 percent higher accuracy on the IoMT intrusion dataset. The proposed model can be used as an IoMT network monitoring tool to safeguard the IoMT devices and networks from attackers inside the healthcare and medical environment.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"319 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132224630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.1109/miot.2023.10145021
{"title":"ComSoc Tech Committees","authors":"","doi":"10.1109/miot.2023.10145021","DOIUrl":"https://doi.org/10.1109/miot.2023.10145021","url":null,"abstract":"","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135939348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.1109/miot.2023.10145052
{"title":"ComSoc Training","authors":"","doi":"10.1109/miot.2023.10145052","DOIUrl":"https://doi.org/10.1109/miot.2023.10145052","url":null,"abstract":"","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135984073","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}
Reconfigurable intelligent surface (RIS) enables an intelligent and programmable communication environment for future sixth-generation (6G) wireless networks, owing to its native passive reflecting and smart phase shifts adjustment. To support the ultra data process for the Internet of Everything (IoE), in this article, new mentalities are investigated in details, such as artificial intelligence (AI) driven RIS, their corresponding designs, deployments, and optimizations. Considering applications and implementations with RIS, the integrating of emerging technologies is also studied to provide a significant performance enhancement in terms of the achievable capacity, power consumption and transmitting security, including physical layer security (PLS), simultaneous wireless information and power transfer (SWIPT), non-orthogonal multiple access (NOMA) and unmanned artificial vehicle (UAV). Then, to address the challenge of channel estimations, RIS-NOMA networks are comprehensively investigated with a simple case study, where the tough issue can be tackled by means of proposed decoding principles. Furthermore, future research trends and open issues of RIS-IoE networks are summarized associated with rate splitting multiple access (RSMA), massive multiple-input multiple-output (mMIMO), and millimeter wave (mmWave), providing constructive directions for the subsequent study.
{"title":"RIS-IoE for Data-Driven Networks: New Mentalities, Trends and Preliminary Solutions","authors":"Biting Zhuo, Juping Gu, Wei Duan, Guoan Zhang, Miaowen Wen, F. Gao","doi":"10.1109/IOTM.001.2200256","DOIUrl":"https://doi.org/10.1109/IOTM.001.2200256","url":null,"abstract":"Reconfigurable intelligent surface (RIS) enables an intelligent and programmable communication environment for future sixth-generation (6G) wireless networks, owing to its native passive reflecting and smart phase shifts adjustment. To support the ultra data process for the Internet of Everything (IoE), in this article, new mentalities are investigated in details, such as artificial intelligence (AI) driven RIS, their corresponding designs, deployments, and optimizations. Considering applications and implementations with RIS, the integrating of emerging technologies is also studied to provide a significant performance enhancement in terms of the achievable capacity, power consumption and transmitting security, including physical layer security (PLS), simultaneous wireless information and power transfer (SWIPT), non-orthogonal multiple access (NOMA) and unmanned artificial vehicle (UAV). Then, to address the challenge of channel estimations, RIS-NOMA networks are comprehensively investigated with a simple case study, where the tough issue can be tackled by means of proposed decoding principles. Furthermore, future research trends and open issues of RIS-IoE networks are summarized associated with rate splitting multiple access (RSMA), massive multiple-input multiple-output (mMIMO), and millimeter wave (mmWave), providing constructive directions for the subsequent study.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117158999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.1109/IOTM.001.2300106
E. Viegas, Altair O. Santin, Pietro Tedeschi
Over the last years, several works introduced network-based intrusion detection schemes based on machine learning techniques for securing IoT devices. Despite the promising results, proposed approaches are rarely adopted in production environments. Networked environments exhibit highly unpredictable behavior, unlike other areas where machine learning has been effectively adopted. Unfortunately, the changing behavior during the time may lead to higher classification errors than those measured in the test phase. In this study, we demonstrate that the existing machine learning techniques applied for network traffic classification fail when facing the characteristics of real-world environments. The experiments analyzed more than 30 TB of data spanning 10 years of real network traffic and 9 intrusion detection datasets. Besides the analysis, we define a set of guidelines to build reliable application of machine learning for network traffic classification, which may guide future research and ensure the reliability of machine learning model deployment in production environments.
{"title":"Toward a Reliable Evaluation of Machine Learning Schemes for Network-Based Intrusion Detection","authors":"E. Viegas, Altair O. Santin, Pietro Tedeschi","doi":"10.1109/IOTM.001.2300106","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300106","url":null,"abstract":"Over the last years, several works introduced network-based intrusion detection schemes based on machine learning techniques for securing IoT devices. Despite the promising results, proposed approaches are rarely adopted in production environments. Networked environments exhibit highly unpredictable behavior, unlike other areas where machine learning has been effectively adopted. Unfortunately, the changing behavior during the time may lead to higher classification errors than those measured in the test phase. In this study, we demonstrate that the existing machine learning techniques applied for network traffic classification fail when facing the characteristics of real-world environments. The experiments analyzed more than 30 TB of data spanning 10 years of real network traffic and 9 intrusion detection datasets. Besides the analysis, we define a set of guidelines to build reliable application of machine learning for network traffic classification, which may guide future research and ensure the reliability of machine learning model deployment in production environments.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116283378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.1109/IOTM.001.2200243
Sandeep Verma, Satnam Kaur
The role of Internet of Things (IoT) in rendering the ever-growing advancements in Maritime Transportation System (MTS), is impeccable and promising. The IoT devices employed for communication for MTS are resource-constrained and can be jeopardized by unknown security attacks or threats. Hence, to pact with the energy limitation and to ensure secure communication, in this article, we propose a novel routing technique named Intelligent Internet of Things ($l^{3}$) for Green and secure communication in IoT-enabled MTS. In this article, we apply a suggested meta-heuristic approach called the Artificial Rabbits Optimization (ARO) for novel selection of the Cluster Head (CH). The ARO ensures the optimized selection of CH while considering various parameters namely, energy index, distance parameter, etc. Extensive experiments of the proposed approach show that $l^{3}$ outperforms the state-of-the-art methods using a variety of performance measures as a benchmark. $l^{3}$ conserves the energy of IoT devices employed for MTS and it also ensures the secure communication among them.
{"title":"Toward Green and Secure Communication in IoT-Enabled Maritime Transportation System","authors":"Sandeep Verma, Satnam Kaur","doi":"10.1109/IOTM.001.2200243","DOIUrl":"https://doi.org/10.1109/IOTM.001.2200243","url":null,"abstract":"The role of Internet of Things (IoT) in rendering the ever-growing advancements in Maritime Transportation System (MTS), is impeccable and promising. The IoT devices employed for communication for MTS are resource-constrained and can be jeopardized by unknown security attacks or threats. Hence, to pact with the energy limitation and to ensure secure communication, in this article, we propose a novel routing technique named Intelligent Internet of Things ($l^{3}$) for Green and secure communication in IoT-enabled MTS. In this article, we apply a suggested meta-heuristic approach called the Artificial Rabbits Optimization (ARO) for novel selection of the Cluster Head (CH). The ARO ensures the optimized selection of CH while considering various parameters namely, energy index, distance parameter, etc. Extensive experiments of the proposed approach show that $l^{3}$ outperforms the state-of-the-art methods using a variety of performance measures as a benchmark. $l^{3}$ conserves the energy of IoT devices employed for MTS and it also ensures the secure communication among them.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128654199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.1109/miot.2023.10145049
{"title":"Cover 3","authors":"","doi":"10.1109/miot.2023.10145049","DOIUrl":"https://doi.org/10.1109/miot.2023.10145049","url":null,"abstract":"","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135984074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.1109/miot.2023.10145047
{"title":"IEEE Foundation","authors":"","doi":"10.1109/miot.2023.10145047","DOIUrl":"https://doi.org/10.1109/miot.2023.10145047","url":null,"abstract":"","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135939344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.1109/miot.2023.10145014
{"title":"ComSoc Publications","authors":"","doi":"10.1109/miot.2023.10145014","DOIUrl":"https://doi.org/10.1109/miot.2023.10145014","url":null,"abstract":"","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135939346","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：