Pub Date : 2024-05-01DOI: 10.1109/IOTM.001.2200276
Murat Simsek, A. Boukerche, B. Kantarci, Rahman Bitirgen, M. Hancer, Ismail Bayezit
Uncrewed Aerial Vehicles (UAVs) have enabled key duties in emergency preparedness, traffic monitoring, environmental monitoring, and public safety. Since the presence of GPS-enabled contexts is not always guaranteed, a grand challenge with the UAVs is the lack of accomplishing their tasks without the presence of GPS coordinates (latitude, longitude, and altitude). Hence, the performance of UAVs in GPS-denied environments is expected to degrade dramatically when compared to the UAVs employed in GPS-enabled environments. In this article, an alternative approach to the state-of-the-art, Dynamic Artificial Neural Network (D-ANN)-based solution is proposed to assist UAV navigation without GPS positions during a mission. Besides accelerometer and gyroscope data, Pulse Width Modulation (PWM) signals, which have been traditionally used in the design of UAV flight controllers, are proposed to be a part of the input for D-ANN-assisted UAV navigation without GPS data. Since the latitude, longitude, and altitude values of the UAV are not correlated, each position is obtained through a separate D-ANN system. The proposed D-ANN location of a quadrotor UAV assisted by D-ANN has less than 3m average destination error at the end of the testing trajectory and also less than 0.12 average normalized mean square error during the testing trajectory in terms of the 3D GPS coordinates.
{"title":"Dynamic Artificial Neural Network-Assisted GPS-Less Navigation for IoT-Enabled Drones","authors":"Murat Simsek, A. Boukerche, B. Kantarci, Rahman Bitirgen, M. Hancer, Ismail Bayezit","doi":"10.1109/IOTM.001.2200276","DOIUrl":"https://doi.org/10.1109/IOTM.001.2200276","url":null,"abstract":"Uncrewed Aerial Vehicles (UAVs) have enabled key duties in emergency preparedness, traffic monitoring, environmental monitoring, and public safety. Since the presence of GPS-enabled contexts is not always guaranteed, a grand challenge with the UAVs is the lack of accomplishing their tasks without the presence of GPS coordinates (latitude, longitude, and altitude). Hence, the performance of UAVs in GPS-denied environments is expected to degrade dramatically when compared to the UAVs employed in GPS-enabled environments. In this article, an alternative approach to the state-of-the-art, Dynamic Artificial Neural Network (D-ANN)-based solution is proposed to assist UAV navigation without GPS positions during a mission. Besides accelerometer and gyroscope data, Pulse Width Modulation (PWM) signals, which have been traditionally used in the design of UAV flight controllers, are proposed to be a part of the input for D-ANN-assisted UAV navigation without GPS data. Since the latitude, longitude, and altitude values of the UAV are not correlated, each position is obtained through a separate D-ANN system. The proposed D-ANN location of a quadrotor UAV assisted by D-ANN has less than 3m average destination error at the end of the testing trajectory and also less than 0.12 average normalized mean square error during the testing trajectory in terms of the 3D GPS coordinates.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"8 5","pages":"92-99"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141054984","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 : 2024-05-01DOI: 10.1109/IOTM.001.2300259
Yujie Ye, Zitong Zhao, Lei Liu, Jie Feng, Jun Du, Qingqi Pei
Traffic flow prediction holds great promise in prompting the rapid development of intelligent transportation systems. The key challenge for traffic flow prediction lies in effectively modeling the complicated spatiotemporal dependencies of traffic data while considering privacy and cost concerns. Existing methods based on neural networks exhibit limitations, particularly in handling dynamic data and long-distance dependencies. To address these challenges, we have proposed a novel distributed traffic flow prediction architecture that makes the integration of generative artificial intelligence (AI) and hierarchical federated learning. This architecture makes the prediction of traffic flow by incorporating spatial self-attention module and traffic delay-aware feature transformation module, which achieves a better balance between communication and computation costs, enhances training efficiency and guarantees data privacy and security. Next, we have introduced the important characteristics and key technologies used for this devised architecture. Finally, several open issues are given with the aim to attract more attentions for further investigation.
{"title":"Federated Generative Artificial Intelligence Empowered Traffic Flow Prediction Under Vehicular Computing Power Networks","authors":"Yujie Ye, Zitong Zhao, Lei Liu, Jie Feng, Jun Du, Qingqi Pei","doi":"10.1109/IOTM.001.2300259","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300259","url":null,"abstract":"Traffic flow prediction holds great promise in prompting the rapid development of intelligent transportation systems. The key challenge for traffic flow prediction lies in effectively modeling the complicated spatiotemporal dependencies of traffic data while considering privacy and cost concerns. Existing methods based on neural networks exhibit limitations, particularly in handling dynamic data and long-distance dependencies. To address these challenges, we have proposed a novel distributed traffic flow prediction architecture that makes the integration of generative artificial intelligence (AI) and hierarchical federated learning. This architecture makes the prediction of traffic flow by incorporating spatial self-attention module and traffic delay-aware feature transformation module, which achieves a better balance between communication and computation costs, enhances training efficiency and guarantees data privacy and security. Next, we have introduced the important characteristics and key technologies used for this devised architecture. Finally, several open issues are given with the aim to attract more attentions for further investigation.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"21 3","pages":"56-61"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141031354","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 : 2024-05-01DOI: 10.1109/miot.2024.10517519
{"title":"Cover 2","authors":"","doi":"10.1109/miot.2024.10517519","DOIUrl":"https://doi.org/10.1109/miot.2024.10517519","url":null,"abstract":"","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"12 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141024852","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 : 2024-05-01DOI: 10.1109/IOTM.001.2300200
O. Gul, A. Erkmen, B. Kantarci
Through the use of flying objects such as satellites and uncrewed aerial vehicles (UAVs), non-terrestrial networks (NTNs) have recently garnered interest in large-scale and developing wireless communication networks. UAV-assisted networks are quickly becoming part of future communication systems. This article overviews the recent works in which UAV-driven cluster-based data-gathering policies have been proposed for heterogeneous robotics and wireless sensor networks (RWSNs) where a UAV with limited-capacity battery visits a group of cluster head (CH) robots for gathering data by considering their energy consumption and data qualities under data hopping limits and NTN standards. In light of the importance of time-critical communications, an RWSN requires different data collection algorithms from WSN such that it includes no cluster-forming stage unlike the algorithms for WSN. Moreover, in the case of time-sensitive tasks under RWSN and under the quality and energy constraints, maximum latency from a nonvisited CH robot to a visited CH robot needs to be reduced with less number of hops in the RWSN. Further-more, the maximum number of forwarding attempts over a CH robot needs to be reduced, which is presented as an important future research direction.
{"title":"NTN-Aided Quality and Energy-Aware Data Collection in Time-Critical Robotic Wireless Sensor Networks","authors":"O. Gul, A. Erkmen, B. Kantarci","doi":"10.1109/IOTM.001.2300200","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300200","url":null,"abstract":"Through the use of flying objects such as satellites and uncrewed aerial vehicles (UAVs), non-terrestrial networks (NTNs) have recently garnered interest in large-scale and developing wireless communication networks. UAV-assisted networks are quickly becoming part of future communication systems. This article overviews the recent works in which UAV-driven cluster-based data-gathering policies have been proposed for heterogeneous robotics and wireless sensor networks (RWSNs) where a UAV with limited-capacity battery visits a group of cluster head (CH) robots for gathering data by considering their energy consumption and data qualities under data hopping limits and NTN standards. In light of the importance of time-critical communications, an RWSN requires different data collection algorithms from WSN such that it includes no cluster-forming stage unlike the algorithms for WSN. Moreover, in the case of time-sensitive tasks under RWSN and under the quality and energy constraints, maximum latency from a nonvisited CH robot to a visited CH robot needs to be reduced with less number of hops in the RWSN. Further-more, the maximum number of forwarding attempts over a CH robot needs to be reduced, which is presented as an important future research direction.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"268 1","pages":"114-120"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141031877","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 : 2024-05-01DOI: 10.1109/miot.2024.10517520
{"title":"Cover 4","authors":"","doi":"10.1109/miot.2024.10517520","DOIUrl":"https://doi.org/10.1109/miot.2024.10517520","url":null,"abstract":"","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"2004 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141027419","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 : 2024-05-01DOI: 10.1109/IOTM.001.2300276
Kang Peng, Hua He, Jingling Liu, Tao Li, Shenglong Hou, Sibo Qiao
In light of the brisk tempo characterizing contemporary lifestyles and the escalating burden of diverse stressors, the decline in the quality of individuals' sleep has emerged as a consequential issue exerting a notable impact on human physiological health. This article introduces the EdgeGAN system, which proposes a hybrid architecture for medical smart beds aimed at proficiently monitoring sleep quality. The EdgeGAN system seamlessly integrates the Internet of Things (IoT) and edge computing through the incorporation of lightweight Generative Adversarial Networks (GAN) into edge computing devices. The amalgamation of this integration serves to enhance the efficacy of sleep quality monitoring. Relative to conventional sleep monitoring systems, the EdgeGAN system offers reduced computational complexity and streamlined user operation. Furthermore, it adeptly captures long-term temporal dependencies in sleep data, thereby extending the retention time of historical information. It also exhibits exceptional compatibility with sleep monitoring devices. Moreover, the EdgeGAN system possesses the capability to intelligently determine whether to upload pertinent data to the cloud based on user preferences, thereby diminishing reliance on cloud resources. In comparison to traditional cloud platform systems, the EdgeGAN system proposed in this article has the capability to circumvent data blockages arising from increased user requests. This innovation enhances real-time performance and compatibility in sleep monitoring, prioritizing user privacy protection. As a result, it offers an intelligent and convenient solution for the development of future smart medical devices.
{"title":"EdgeGAN: Enhancing Sleep Quality Monitoring in Medical IoT Through Generative AI at the Edge","authors":"Kang Peng, Hua He, Jingling Liu, Tao Li, Shenglong Hou, Sibo Qiao","doi":"10.1109/IOTM.001.2300276","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300276","url":null,"abstract":"In light of the brisk tempo characterizing contemporary lifestyles and the escalating burden of diverse stressors, the decline in the quality of individuals' sleep has emerged as a consequential issue exerting a notable impact on human physiological health. This article introduces the EdgeGAN system, which proposes a hybrid architecture for medical smart beds aimed at proficiently monitoring sleep quality. The EdgeGAN system seamlessly integrates the Internet of Things (IoT) and edge computing through the incorporation of lightweight Generative Adversarial Networks (GAN) into edge computing devices. The amalgamation of this integration serves to enhance the efficacy of sleep quality monitoring. Relative to conventional sleep monitoring systems, the EdgeGAN system offers reduced computational complexity and streamlined user operation. Furthermore, it adeptly captures long-term temporal dependencies in sleep data, thereby extending the retention time of historical information. It also exhibits exceptional compatibility with sleep monitoring devices. Moreover, the EdgeGAN system possesses the capability to intelligently determine whether to upload pertinent data to the cloud based on user preferences, thereby diminishing reliance on cloud resources. In comparison to traditional cloud platform systems, the EdgeGAN system proposed in this article has the capability to circumvent data blockages arising from increased user requests. This innovation enhances real-time performance and compatibility in sleep monitoring, prioritizing user privacy protection. As a result, it offers an intelligent and convenient solution for the development of future smart medical devices.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"14 10","pages":"16-21"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141029615","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 : 2024-05-01DOI: 10.1109/IOTM.001.2300282
Jiahui Liu, Yang Liu, Kun Gao, Liang Wang
With the emergence of generative intelligence at the edge of modern Internet of Things (IoT) networks, promising solutions are proposed to further improve road safety. As a crucial component of proactive traffic safety management, vehicle accident detection (VAD) encounters multiple existing challenges in terms of data accuracy, accident classification, communication latency, etc. Thus, generative edge intelligence (GEI) can be introduced to VAD systems and contribute to improving performance by augmenting data, learning underlying patterns, and so on. In this article, we investigate the integration of GEI technology in VAD systems, focusing on its applications, challenges, and prospects. We begin by reviewing conventional VAD methods and highlighting their limitations. Following this, we explore the potential of GEI in IoT-assisted VAD and then propose a novel architecture for the GEI-VAD system that is based on an end-edge-cloud framework. We delve into the details of each component and layer within the system. Finally, we conclude this article by suggesting avenues for future research.
随着生成智能在现代物联网（IoT）网络边缘的出现，人们提出了前景广阔的解决方案，以进一步改善道路安全。作为主动式交通安全管理的重要组成部分，车辆事故检测（VAD）在数据准确性、事故分类、通信延迟等方面遇到了多重挑战。因此，可以将边缘生成智能（GEI）引入 VAD 系统，通过增强数据、学习潜在模式等方式提高性能。在本文中，我们将研究如何在 VAD 系统中集成生成边缘智能技术，重点关注其应用、挑战和前景。我们首先回顾了传统的 VAD 方法，并强调了它们的局限性。随后，我们探讨了 GEI 在物联网辅助 VAD 中的潜力，然后提出了一种基于端边云框架的 GEI-VAD 系统新架构。我们深入探讨了系统中每个组件和层的细节。最后，我们提出了未来的研究方向，以此结束本文。
{"title":"Generative Edge Intelligence for IoT-Assisted Vehicle Accident Detection: Challenges and Prospects","authors":"Jiahui Liu, Yang Liu, Kun Gao, Liang Wang","doi":"10.1109/IOTM.001.2300282","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300282","url":null,"abstract":"With the emergence of generative intelligence at the edge of modern Internet of Things (IoT) networks, promising solutions are proposed to further improve road safety. As a crucial component of proactive traffic safety management, vehicle accident detection (VAD) encounters multiple existing challenges in terms of data accuracy, accident classification, communication latency, etc. Thus, generative edge intelligence (GEI) can be introduced to VAD systems and contribute to improving performance by augmenting data, learning underlying patterns, and so on. In this article, we investigate the integration of GEI technology in VAD systems, focusing on its applications, challenges, and prospects. We begin by reviewing conventional VAD methods and highlighting their limitations. Following this, we explore the potential of GEI in IoT-assisted VAD and then propose a novel architecture for the GEI-VAD system that is based on an end-edge-cloud framework. We delve into the details of each component and layer within the system. Finally, we conclude this article by suggesting avenues for future research.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"20 2","pages":"50-54"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141023445","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 : 2024-05-01DOI: 10.1109/IOTM.001.2300122
Hussam Ibraiwish, M. Eltokhey, M. Alouini
The reliance on precision agriculture facilitates improving farming outcomes by using information technology in managing resources. The dependence on light-emitting diode (LED)-based grow lights enables further enhancement of farming outcomes because they offer flexibility in growing plants throughout the year by supporting their illumination needs while offering cost and energy-efficiency advantages. Using grow lights also allows adopting visible-light communication (VLC) to provide simultaneous illumination and communication. In this work, we propose using LED-based grow lights to provide unmanned aerial vehicle (UAV)-assisted VLC in precision agriculture systems. The advantages include achieving efficient resource use by relying on grow lights to support communication needs in Internet of Things devices and plant growth needs in areas associated with limited sunlight while minimizing radio frequency interference. We present an overview of the system design and highlight the influence of optimizing UAV locations on system performance before discussing directions for future research.
对精准农业的依赖有助于利用信息技术管理资源，从而改善农业成果。对基于发光二极管（LED）的生长灯的依赖进一步提高了农业成果，因为这些生长灯通过支持植物的照明需求，为植物的全年生长提供了灵活性，同时还具有成本和能效优势。使用生长灯还可以采用可见光通信（VLC）来同时提供照明和通信。在这项工作中，我们建议在精准农业系统中使用基于 LED 的生长灯来提供无人机辅助可见光通信。其优点包括：依靠生长灯支持物联网设备的通信需求和植物生长需求，同时最大限度地减少射频干扰。我们概述了系统设计，并强调了优化无人机位置对系统性能的影响，然后讨论了未来的研究方向。
{"title":"UAV-Assisted VLC Using LED-Based Grow Lights in Precision Agriculture Systems","authors":"Hussam Ibraiwish, M. Eltokhey, M. Alouini","doi":"10.1109/IOTM.001.2300122","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300122","url":null,"abstract":"The reliance on precision agriculture facilitates improving farming outcomes by using information technology in managing resources. The dependence on light-emitting diode (LED)-based grow lights enables further enhancement of farming outcomes because they offer flexibility in growing plants throughout the year by supporting their illumination needs while offering cost and energy-efficiency advantages. Using grow lights also allows adopting visible-light communication (VLC) to provide simultaneous illumination and communication. In this work, we propose using LED-based grow lights to provide unmanned aerial vehicle (UAV)-assisted VLC in precision agriculture systems. The advantages include achieving efficient resource use by relying on grow lights to support communication needs in Internet of Things devices and plant growth needs in areas associated with limited sunlight while minimizing radio frequency interference. We present an overview of the system design and highlight the influence of optimizing UAV locations on system performance before discussing directions for future research.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"21 4","pages":"100-105"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141037010","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}
The lack of transparency, unified standards, and effective regulation, along with the complexity of the supply chain, make it challenging to achieve reliable traceability throughout the entire process of recycling and reusing waste electronic appliances. This poses a challenge for effectively implementing carbon reduction measures. In response to the above issues, we propose a full process data management solution for WEEE recycling based on blockchain technology. In addition, a method combining digital twin and generative AI technology has been proposed to address the performance bottleneck issue of blockchain. Predicting future data flow through generative AI models and utilizing reinforcement learning algorithms to predictively optimize blockchain parameter configurations effectively improve blockchain performance and scalability. The experimental results demonstrate that the proposed method effectively enhances system adaptability and throughput. It achieves an integration of reliable traceability, accurate prediction, and performance optimization throughout the entire process of WEEE recycling and reuse data management.
{"title":"Traceability and Performance Optimization: Application of Generative AI, Digital Twin, and DRL in the Recycling Process of WEEE","authors":"Jinlong Wang, Yixin Li, Shangzhuo Zhou, Yuanyuan Zhang, Xiaoyun Xiong, Weiwei Zhai","doi":"10.1109/IOTM.001.2300261","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300261","url":null,"abstract":"The lack of transparency, unified standards, and effective regulation, along with the complexity of the supply chain, make it challenging to achieve reliable traceability throughout the entire process of recycling and reusing waste electronic appliances. This poses a challenge for effectively implementing carbon reduction measures. In response to the above issues, we propose a full process data management solution for WEEE recycling based on blockchain technology. In addition, a method combining digital twin and generative AI technology has been proposed to address the performance bottleneck issue of blockchain. Predicting future data flow through generative AI models and utilizing reinforcement learning algorithms to predictively optimize blockchain parameter configurations effectively improve blockchain performance and scalability. The experimental results demonstrate that the proposed method effectively enhances system adaptability and throughput. It achieves an integration of reliable traceability, accurate prediction, and performance optimization throughout the entire process of WEEE recycling and reuse data management.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"1 10","pages":"22-28"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141055943","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 : 2024-05-01DOI: 10.1109/IOTM.001.2300171
Love Allen Chijioke Ahakonye, C. I. Nwakanma, Jae Min Lee, Dong‐Seong Kim
Intrusion and attacks have consistently challenged the Industrial Internet of Things (IIoT). Although artificial intelligence (AI) rapidly develops in attack detection and mitigation, building convincing trust is difficult due to its black-box nature. Its unexplained outcome inhibits informed and adequate decision-making of the experts and stakeholders. Explainable AI (XAI) has emerged to help with this problem. However, the ease of comprehensibility of XAI interpretation remains an issue due to the complexity and reliance on statistical theories. This study integrates agnostic post-hoc LIME and SHAP explainability approaches on intrusion detection systems built using representative AI models to explain the model's decisions and provide more insights into interpretability. The decision and confidence impact ratios assessed the significance of features and model dependencies, enhancing cybersecurity experts' trust and informed decisions. The experimental findings highlight the importance of these explainability techniques for understanding and mitigating IIoT intrusions with recourse to significant data features and model decisions.
{"title":"Machine Learning Explainability for Intrusion Detection in the Industrial Internet of Things","authors":"Love Allen Chijioke Ahakonye, C. I. Nwakanma, Jae Min Lee, Dong‐Seong Kim","doi":"10.1109/IOTM.001.2300171","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300171","url":null,"abstract":"Intrusion and attacks have consistently challenged the Industrial Internet of Things (IIoT). Although artificial intelligence (AI) rapidly develops in attack detection and mitigation, building convincing trust is difficult due to its black-box nature. Its unexplained outcome inhibits informed and adequate decision-making of the experts and stakeholders. Explainable AI (XAI) has emerged to help with this problem. However, the ease of comprehensibility of XAI interpretation remains an issue due to the complexity and reliance on statistical theories. This study integrates agnostic post-hoc LIME and SHAP explainability approaches on intrusion detection systems built using representative AI models to explain the model's decisions and provide more insights into interpretability. The decision and confidence impact ratios assessed the significance of features and model dependencies, enhancing cybersecurity experts' trust and informed decisions. The experimental findings highlight the importance of these explainability techniques for understanding and mitigating IIoT intrusions with recourse to significant data features and model decisions.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"46 10","pages":"68-74"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141033223","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：