2022 IEEE 8th World Forum on Internet of Things (WF-IoT)最新文献_第9页

Benchmarking of Emulated Wireless Edge Cloud Connectivity for Maritime Environments 海洋环境中模拟无线边缘云连接的基准测试

2022 IEEE 8th World Forum on Internet of Things (WF-IoT) Pub Date : 2022-10-26 DOI: 10.1109/WF-IoT54382.2022.10152152

Antti Kolehmainen, M. Komu, Sepehr Javid, Jimmy Kjällman, T. Kauppinen, Fayezeh Ghavimi, B. Silverajan

{"title":"Benchmarking of Emulated Wireless Edge Cloud Connectivity for Maritime Environments","authors":"Antti Kolehmainen, M. Komu, Sepehr Javid, Jimmy Kjällman, T. Kauppinen, Fayezeh Ghavimi, B. Silverajan","doi":"10.1109/WF-IoT54382.2022.10152152","DOIUrl":"https://doi.org/10.1109/WF-IoT54382.2022.10152152","url":null,"abstract":"Remote ship pilotage, smart fairway navigation, autonomous maritime transport and smart maritime logistics present new challenges to the maritime industry. One of the challenges is increasing dependency on reliable network connectivity that can range from low priority entertainment communications to high priority safety critical communications. Traffic prioritization is needed at the open sea, where ships typically resort to expensive satellite connectivity that incurs long latency and narrow bandwidth. Near the coastline, ships can switch to 5G-based communications with low latency and high bandwidth, and possibly even utilize low-latency edge computing capabilities. Our contribution in this paper is a cloud-based networking testbed that supports network traffic shaping to emulate satellite and 5G-based communications between an edge cloud located onboard a ship and another edge cloud located onboard another ship or at the shore under traffic loss scenarios. Potential use-cases for our work include emulation of peer-to-peer communications (i.e., ship-to-ship or ship-to-shore) and mesh networking. The system can also be used as a basis for real-time ship networking, for instance, as building block for traffic prioritization in Kubernetes-based edge clouds.","PeriodicalId":176605,"journal":{"name":"2022 IEEE 8th World Forum on Internet of Things (WF-IoT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128594281","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}

引用次数: 0

A Novel Three-dimensional Mobility Model for mmWave UAV Swarms 一种新型毫米波无人机群三维机动性模型

2022 IEEE 8th World Forum on Internet of Things (WF-IoT) Pub Date : 2022-10-26 DOI: 10.1109/WF-IoT54382.2022.10152129

N. Bharti, M. S. Kiran

{"title":"A Novel Three-dimensional Mobility Model for mmWave UAV Swarms","authors":"N. Bharti, M. S. Kiran","doi":"10.1109/WF-IoT54382.2022.10152129","DOIUrl":"https://doi.org/10.1109/WF-IoT54382.2022.10152129","url":null,"abstract":"Unmanned aerial vehicle (UAV) swarms are expected to become more prevalent in the Internet of Things (IoT) applications such as remote sensing, monitoring, entertainment, etc. The onboard sensors on these UAVs often generate massive data and demand higher data rates for real-time communication to the swarm gateway. The next-generation millimeter-wave (mmWave) communication technologies, such as IEEE 802.11ad/ay, 5G, etc., offer promising speeds and can be suitable for intra-swarm communication. However, to take advantage of these faster speeds, the impact of swarm mobility on the performance of mm Wave communication technologies must be investigated using realistic mobility models. In this paper, we present a three-dimensional group mobility model for UAV swarms guided by the swarm gateway considering real-world restrictions such as obtaining collision-free waypoints for the UAVs while residing within the coverage range of the gateway and maintaining a safe distance from peers. The performance analysis shows that the proposed model offers a superior degree of spatial and temporal dependency in the swarm movement than the existing state-of-the-art models.","PeriodicalId":176605,"journal":{"name":"2022 IEEE 8th World Forum on Internet of Things (WF-IoT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115770045","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}

引用次数: 0

RoadNote: Automated Road Closure Detection using Urban Sensing RoadNote:使用城市传感的自动封路检测

2022 IEEE 8th World Forum on Internet of Things (WF-IoT) Pub Date : 2022-10-26 DOI: 10.1109/WF-IoT54382.2022.10152296

Raiful Hasan, Ragib Hasan

{"title":"RoadNote: Automated Road Closure Detection using Urban Sensing","authors":"Raiful Hasan, Ragib Hasan","doi":"10.1109/WF-IoT54382.2022.10152296","DOIUrl":"https://doi.org/10.1109/WF-IoT54382.2022.10152296","url":null,"abstract":"Maps and navigation applications are essential tools in the modern era, especially for smartphone users. Navigation apps not only guide us on the correct path to the destination but also serve to find convenience and provide connectivity by sharing locations, travel status, and expert guidance. Map applications offer real-time updates which rely on crowdsourcing data from users, historical data, and advanced prediction algorithms. However, due to the dynamic nature of the urban environment, navigational apps fail to provide unscheduled road closure information. This study investigates erroneous situations and found 23 incidences where maps fail to navigate the closure information. We propose ROADNote, an automated system that accommodates urban sensors and provides closures update to users. ROADNote provides real-time traffic conditions by automated detections using future-generation commodity sensors. We built a prototype of ROADNote; after that, we conducted experiments to get real-time road-closer information by visual sensors (i.e., drone, camera). ROADNote facilitates to reduce of average travel time by 3.48 minutes and distance by more than 300 meters.","PeriodicalId":176605,"journal":{"name":"2022 IEEE 8th World Forum on Internet of Things (WF-IoT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126693535","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}

引用次数: 0

Vehicle Routing to Minimize the Average Delay for Collecting the Disaster Damage Information 车辆路径以减少收集灾害损害信息的平均延迟

2022 IEEE 8th World Forum on Internet of Things (WF-IoT) Pub Date : 2022-10-26 DOI: 10.1109/WF-IoT54382.2022.10152070

Sanjukta Khwairakpam, M. Shibata, M. Tsuru

{"title":"Vehicle Routing to Minimize the Average Delay for Collecting the Disaster Damage Information","authors":"Sanjukta Khwairakpam, M. Shibata, M. Tsuru","doi":"10.1109/WF-IoT54382.2022.10152070","DOIUrl":"https://doi.org/10.1109/WF-IoT54382.2022.10152070","url":null,"abstract":"When a large-scale disaster happens, the emergency disaster response headquarters (HQ) is set up to collect the dis-aster damaged information and conduct an appropriate disaster management plan. However, if the high-speed communications infrastructures are unavailable, such information should be brought to HQ by other means such as mobile vehicles. In this paper, therefore, we consider the scenario in which such information in a region are monitored and brought to HQ by patrolling vehicles equipped with cameras, mics, and other sensors. The patrolling vehicles can return to HQ multiple times on the way to drop the monitored information. A metric, Information Delay-time Product (IDP), is defined to represent the average delay time for information collection, i.e., the product of the fraction of the information and its delay time in delivering to HQ. By leveraging Eulerian circuits, we can systematically search good traveling routes for vehicles to incrementally collect the information along all streets. On a grid map as a town's street network with two vehicles, we experimentally show that an appropriate number of returns to HQ with balanced-sized intervals is necessary to minimize the IDP.","PeriodicalId":176605,"journal":{"name":"2022 IEEE 8th World Forum on Internet of Things (WF-IoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126023240","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}

引用次数: 0

Black-Box Adversarial Attack for Deep Learning Classifiers in IoT Applications 物联网应用中深度学习分类器的黑盒对抗攻击

2022 IEEE 8th World Forum on Internet of Things (WF-IoT) Pub Date : 2022-10-26 DOI: 10.1109/WF-IoT54382.2022.10152229

Abhijit Singh, B. Sikdar

{"title":"Black-Box Adversarial Attack for Deep Learning Classifiers in IoT Applications","authors":"Abhijit Singh, B. Sikdar","doi":"10.1109/WF-IoT54382.2022.10152229","DOIUrl":"https://doi.org/10.1109/WF-IoT54382.2022.10152229","url":null,"abstract":"The increasing adoption of Internet of Things (IoT) has resulted in the availability of big data, which can reveal valuable insights if processed efficiently. Classification tasks are very important in such applications, and Artificial Intelligence is widely used to solve these problems. This paper demonstrates that Deep Learning classifiers used in IoT environments are vulnerable to black-box adversarial attacks. Such attacks can render these models ineffective by causing severe performance issues. This paper develops a black-box adversarial attack mechanism to generate adversarial examples for data obtained from smart meters installed in residential houses. An analysis is presented to demonstrate that the statistical properties of these adversarial examples are indistinguishable from those of the true examples, and the performance of the targeted models degrades sharply when exposed to the proposed attack. Further, the inherent properties of the attack mechanism imply that it is able to evade the entire class of gradient masking based defence methods. The effectiveness of the proposed black-box adversarial attack is demonstrated on the publicly available United Kingdom-Domestic Appliance-Level Electricity smart meter dataset.","PeriodicalId":176605,"journal":{"name":"2022 IEEE 8th World Forum on Internet of Things (WF-IoT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127011000","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}

引用次数: 0

A Fuzzy Knowledge-based System for UV Exposure Management 基于模糊知识的紫外线曝光管理系统

2022 IEEE 8th World Forum on Internet of Things (WF-IoT) Pub Date : 2022-10-26 DOI: 10.1109/WF-IoT54382.2022.10152116

C. Kouzinopoulos, Anastasia Kassiani Blitsi, G. Stavropoulos, K. Votis, D. Tzovaras

引用次数: 0

MARTEN: Measurement-Based Trustcheck for Constrained Networks 约束网络的基于度量的信任检查

2022 IEEE 8th World Forum on Internet of Things (WF-IoT) Pub Date : 2022-10-26 DOI: 10.1109/WF-IoT54382.2022.10152058

C. Schmitt, Philipp Pfefferkorn

{"title":"MARTEN: Measurement-Based Trustcheck for Constrained Networks","authors":"C. Schmitt, Philipp Pfefferkorn","doi":"10.1109/WF-IoT54382.2022.10152058","DOIUrl":"https://doi.org/10.1109/WF-IoT54382.2022.10152058","url":null,"abstract":"Due to the digitization more and more devices get connected and are also integrated into our private space. In SmartHomes/Buildings these devices are constrained and, thus, limited with computational capacities but are requested to measure different values (e.g., temperature or humidity) periodically and may trigger others (e.g., ventilation or shading). Due to their deployments and resources security support for communication is very limited calling for trustchecks in gen-eral. Thus, a Measurement-Based Trustcheck for Constrained Networks (MARTEN) was designed and developed in order to include a trustcheck on received measurements of a single node. With this solution trust can be more individually assigned and allows more fine-grained distinction compared to known node- or cluster-based approaches. Thus, MARTEN differs from existing trust- check approaches based on the reputation of reporting nodes or similar. It was evaluated in a SmartHome/Building scenario proving correct labelling of measurements and handling by the network owner (NO). Currently, the integration in an air mobility application is ongoing. We believe MARTEN is feasible here as well as it was designed in a modular structure and, thus, is adaptable with less overhead. Due to MARTEN's automation process the interaction with the NO is decreased to a minimum.","PeriodicalId":176605,"journal":{"name":"2022 IEEE 8th World Forum on Internet of Things (WF-IoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131387352","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}

引用次数: 0

TinyHAR: Benchmarking Human Activity Recognition Systems in Resource Constrained Devices TinyHAR:在资源受限设备中对人类活动识别系统进行基准测试

2022 IEEE 8th World Forum on Internet of Things (WF-IoT) Pub Date : 2022-10-26 DOI: 10.1109/WF-IoT54382.2022.10152039

Sheikh Nooruddin, Md. Milon Islam, F. Karray

{"title":"TinyHAR: Benchmarking Human Activity Recognition Systems in Resource Constrained Devices","authors":"Sheikh Nooruddin, Md. Milon Islam, F. Karray","doi":"10.1109/WF-IoT54382.2022.10152039","DOIUrl":"https://doi.org/10.1109/WF-IoT54382.2022.10152039","url":null,"abstract":"Advances in deep learning, especially Convolutional Neural Networks (CNNs) have revolutionized intelligent frame-works such as Human Activity Recognition (HAR) systems by effectively and efficiently inferring human activity from various modalities of data. However, the training and inference of CNNs are often resource-intensive. Recent research developments are focused on bringing the effectiveness of CNNs in resource con-strained edge devices through Tiny Machine Learning (TinyML). However, this is extremely hard to achieve due to the limitations in memory, compute power, and energy of resource constrained edge devices. This paper provides a benchmark to understand these trade-offs among variations of CNN network architectures, different training methodologies, and different modalities of data in the context of HAR, TinyML, and edge devices. We tested and reported the performance of CNN and Depthwise Separable CNN (DSCNN) models as well as two training methodologies: Quantization Aware Training (QAT) and Post-training Quantization (PTQ) on five commonly used benchmark datasets containing image and time-series data: UP-Fall, Fall Detection Dataset (FDD), PAMAP2, UCI-HAR, and WISDM. We also deployed and tested the performance of the model-based standalone applications on multiple commonly available resource constrained edge devices in terms of inference time and power consumption. The experimental results demonstrate the effectiveness and feasibility of Tiny ML for HAR in edge devices.","PeriodicalId":176605,"journal":{"name":"2022 IEEE 8th World Forum on Internet of Things (WF-IoT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115481131","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}

引用次数: 1

Exposing Adaptive Cruise Control in Advanced Driving Assistance Systems 暴露自适应巡航控制在先进驾驶辅助系统

2022 IEEE 8th World Forum on Internet of Things (WF-IoT) Pub Date : 2022-10-26 DOI: 10.1109/WF-IoT54382.2022.10152232

Mohammad Aminul Hoque, Ragib Hasan

引用次数: 0

Decentralising Access Control for IoT Environment 物联网环境的分散访问控制

2022 IEEE 8th World Forum on Internet of Things (WF-IoT) Pub Date : 2022-10-26 DOI: 10.1109/WF-IoT54382.2022.10152066

Charalampos Savvaidis, Christos Patsonakis, G. Stavropoulos, Anastasia Kassiani Blitsi, Iordanis Papoutsoglou, K. Votis, D. Tzovaras

{"title":"Decentralising Access Control for IoT Environment","authors":"Charalampos Savvaidis, Christos Patsonakis, G. Stavropoulos, Anastasia Kassiani Blitsi, Iordanis Papoutsoglou, K. Votis, D. Tzovaras","doi":"10.1109/WF-IoT54382.2022.10152066","DOIUrl":"https://doi.org/10.1109/WF-IoT54382.2022.10152066","url":null,"abstract":"IoT has a profound impact on businesses and individuals with growing adoption. Security and scalability are key subjects for scaling the adoption. Cyber attacks increase each year, and the emerging technologies' addition such as Machine Learning introduce vulnerabilities with additional complexity. Access control can mitigate security threats with proper rights management. XACML is an appropriate way to enforce complex policies in heterogeneous environments like IoT due to its flexibility. Furthermore, the blockchain's advantages like data immutability and availability can aid in building a trustworthy access control system for IoT. Blockchain can support a de-centralised architecture for policy evaluation and avoid single points of failure for the policy evaluation resulting in enhanced security of the IoT network. Smart contracts accommodate the access control policies' evaluation for delivering a decentralised and tamper-proof system with consistent outcomes. This paper proposes a decentralised access control approach following the XACML standard and enabling the access control decision evaluation using smart contracts. The implementation's impact on a complex real-world environment is described. The reference implementation is extensible to a great degree as it has flexibility in including services on top of the blockchain, such as an audit mechanism on the access decisions.","PeriodicalId":176605,"journal":{"name":"2022 IEEE 8th World Forum on Internet of Things (WF-IoT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115685331","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}

引用次数: 0