2021 IEEE 7th World Forum on Internet of Things (WF-IoT)最新文献_第3页

DETECTren: Vehicle Object Detection Using Self-Supervised Learning based on Light-Weight Network for Low-Power Devices DETECTren:基于轻量网络的车辆目标检测

2021 IEEE 7th World Forum on Internet of Things (WF-IoT) Pub Date : 2021-06-14 DOI: 10.1109/WF-IoT51360.2021.9594927

Hans Fuhrmann, Anthony Boyko, Mohamed H. Abdelpakey, M. Shehata

{"title":"DETECTren: Vehicle Object Detection Using Self-Supervised Learning based on Light-Weight Network for Low-Power Devices","authors":"Hans Fuhrmann, Anthony Boyko, Mohamed H. Abdelpakey, M. Shehata","doi":"10.1109/WF-IoT51360.2021.9594927","DOIUrl":"https://doi.org/10.1109/WF-IoT51360.2021.9594927","url":null,"abstract":"Vehicle object detection is a fundamental task in computer vision. Most modern classifiers and trackers are built upon the object detectors. For example, self-driving cars use object detection on low-power devices to capture the information from the surrounding environment. Currently, object detection uses a huge amount of labelled data to train the detector. Moreover, these detectors are designed for high-end hardware (i.e., GPUs) and cannot be used on low-power devices. In this paper, we propose DETECTren, a novel object detector that uses self-supervised learning to leverage both the limited labelled data and the huge amount of unlabelled data. DETECTren learns to accurately detect the vehicle and its bounding box. DETECTren is divided into two tasks, (1) The pretext task and (2) The downstream task. In the pretext task, DETECTren uses an autoencoder with ResNet50 as a backbone sub-network to learn rotation-invariant features. The input image is rotated three times; a 90 degree rotation of the original, a 180 degree rotation of the original, and a 270 degree rotation of the original. These three images along with the original image are fed into the pretext sub-network to output a rotation invariant image. In the downstream task, a detector sub-network is used to detect and regress the bounding boxes coordinates. To match the output of the pretext task and the input of the downstream task, matching convolutional layers layers are used with trainable parameters. DETECTren is implemented using mixed-precision to be compatible with low-power devices. Experiments on the Kitti dataset show that DETECTren achieves high Average Precision (AP).","PeriodicalId":184138,"journal":{"name":"2021 IEEE 7th World Forum on Internet of Things (WF-IoT)","volume":"232 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129031574","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: 2

Exploiting Bluetooth Low Energy smart tags for virtual coaching 利用低功耗蓝牙智能标签进行虚拟教练

2021 IEEE 7th World Forum on Internet of Things (WF-IoT) Pub Date : 2021-06-14 DOI: 10.1109/WF-IoT51360.2021.9595350

Florenc Demrozi, Nicola Serlonghi, Cristian Turetta, Cristiano Pravadelli, G. Pravadelli

引用次数: 3

Performance Analysis of Ring Oscillator PUF for Robust Security in Smart Transportation 面向智能交通鲁棒安全性的环振PUF性能分析

2021 IEEE 7th World Forum on Internet of Things (WF-IoT) Pub Date : 2021-06-14 DOI: 10.1109/WF-IoT51360.2021.9596038

Pintu Kumar Sadhu, V. P. Yanambaka, A. Abdelgawad, K. Yelamarthi

引用次数: 7

Joint Sparse Recovery in Precision Agriculture WSN and IoT Applications 精准农业WSN和物联网应用中的联合稀疏恢复

2021 IEEE 7th World Forum on Internet of Things (WF-IoT) Pub Date : 2021-06-14 DOI: 10.1109/WF-IoT51360.2021.9595086

Michael Melek, Ahmed K. F. Khattab

引用次数: 3

Smart and Secure Blockchain-based Healthcare System Using Deep Q-Learning 使用深度q -学习的基于区块链的智能安全医疗系统

2021 IEEE 7th World Forum on Internet of Things (WF-IoT) Pub Date : 2021-06-14 DOI: 10.1109/WF-IoT51360.2021.9595416

Abeer Z. Al-Marridi, Amr Mohamed, A. Erbad, M. Guizani

{"title":"Smart and Secure Blockchain-based Healthcare System Using Deep Q-Learning","authors":"Abeer Z. Al-Marridi, Amr Mohamed, A. Erbad, M. Guizani","doi":"10.1109/WF-IoT51360.2021.9595416","DOIUrl":"https://doi.org/10.1109/WF-IoT51360.2021.9595416","url":null,"abstract":"Healthcare is one of the top priorities in modern society to provide better health facilities. Therefore, investments in health care systems increased rapidly, aligned with the population growth rate. Besides, the data generated from the health sectors is incomparable with the amount of data generated in other industries. Therefore, managing data processing and sharing between various healthcare stakeholders is essential. Blockchain is an emerging technology used heavily in various domains, including the healthcare sector, to facilitate secure data sharing. However, mapping the content requirements with the blockchain’s configuration was not addressed, especially when addressing security, delays, and cost in healthcare systems. This paper proposes a blockchain-based intelligent Healthcare system (BC-iHealth) to address the mapping between the blockchain entities’ needs with the blockchain’s configuration while maximizing the security and minimizing the overall delay and cost. The optimization model is formulated as a Markov Decision Process (MDP) and solved intelligently using a Deep Q-Learning approach. Simulation results confirm that the Deep Q-Learning optimizes the BC-iHealth system and outperforms two benchmark strategies: random selection and exhaustive search.","PeriodicalId":184138,"journal":{"name":"2021 IEEE 7th World Forum on Internet of Things (WF-IoT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122846253","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: 2

Smart Musical Instruments preset sharing: an ontology-based data access approach 智能乐器预设共享:基于本体的数据访问方法

2021 IEEE 7th World Forum on Internet of Things (WF-IoT) Pub Date : 2021-06-14 DOI: 10.1109/WF-IoT51360.2021.9595417

L. Turchet, P. Bouquet

{"title":"Smart Musical Instruments preset sharing: an ontology-based data access approach","authors":"L. Turchet, P. Bouquet","doi":"10.1109/WF-IoT51360.2021.9595417","DOIUrl":"https://doi.org/10.1109/WF-IoT51360.2021.9595417","url":null,"abstract":"Interoperability represents an important aspect in research dealing with the emerging class of smart musical instruments (SMIs). To date, no interoperable file format for the exchange of content produced by heterogeneous SMIs has been defined yet. This paper proposes a solution to the issue of sharing presets among heterogeneous SMIs, which are used to conFigure an SMI. The heterogeneity of SMIs may come from the type, structure and implementation of the SMI’s embedded system, its sound engine and sensor interface. The presented solution is based on the “ontology-based data access” paradigm and leverages the existing Smart Musical Instruments Ontology. This approach allows one to share presets between heterogeneous SMIs by mapping information about the configuration of an instrument to the concepts of the ontology. Thanks to this approach, SMIs developers can implement programs that convert proprietary formats for the configuration of the instrument into a common format for SMIs, and vice versa. We present the general architecture and workflow of this approach, and we describe an implementation for it which involves the sharing of presets among two heterogeneous smart guitars.","PeriodicalId":184138,"journal":{"name":"2021 IEEE 7th World Forum on Internet of Things (WF-IoT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115066805","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: 3

Addressing Uncertainties within Active Learning for Industrial IoT 解决工业物联网主动学习中的不确定性

2021 IEEE 7th World Forum on Internet of Things (WF-IoT) Pub Date : 2021-06-14 DOI: 10.1109/WF-IoT51360.2021.9595397

D. Agarwal, Pravesh Srivastava, Sergio Martin del Campo, Balasubramaniam Natarajan, Babji Srinivasan

{"title":"Addressing Uncertainties within Active Learning for Industrial IoT","authors":"D. Agarwal, Pravesh Srivastava, Sergio Martin del Campo, Balasubramaniam Natarajan, Babji Srinivasan","doi":"10.1109/WF-IoT51360.2021.9595397","DOIUrl":"https://doi.org/10.1109/WF-IoT51360.2021.9595397","url":null,"abstract":"Internet of Things (IoT) is a key enabler of Industry 4.0 with networked devices providing sensor data to help manage, automate, streamline and optimize assets, operations and processes. In such industrial IoT settings, reliability and process experts spend a considerable amount of time in creating accurate ground-truth data to assist with the inferencing capabilities of Artificial Intelligence (AI) engines. This process can be time-consuming and sometimes inaccurate, depending on the complexity of data. Accurate expert annotated data is the foundation for many AI applications because data needs to be classified on several bases, for instance into ‘normal’, ‘abnormal’ or ‘pre-abnormal’ states. Such problem formulations can be appropriately addressed using Active Learning (AL) techniques. We propose an AL framework capable of handling two practical challenges: oracle uncertainty and quantification of model performance in the absence of ground truth. Consequently, the proposed approach addresses uncertainties within AL techniques by fusing information pertaining to expertise levels of the human annotators and their confidence levels corresponding to the annotation provided.","PeriodicalId":184138,"journal":{"name":"2021 IEEE 7th World Forum on Internet of Things (WF-IoT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116764717","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: 5

Green IoT System Architecture for Applied Autonomous Network Cybersecurity Monitoring 应用自主网络安全监控的绿色物联网系统架构

2021 IEEE 7th World Forum on Internet of Things (WF-IoT) Pub Date : 2021-06-14 DOI: 10.1109/WF-IoT51360.2021.9595142

Zaghloul Saad Zaghloul, Nelly Elsayed, Chengcheng Li, M. Bayoumi

{"title":"Green IoT System Architecture for Applied Autonomous Network Cybersecurity Monitoring","authors":"Zaghloul Saad Zaghloul, Nelly Elsayed, Chengcheng Li, M. Bayoumi","doi":"10.1109/WF-IoT51360.2021.9595142","DOIUrl":"https://doi.org/10.1109/WF-IoT51360.2021.9595142","url":null,"abstract":"Network security morning (NSM) is essential for any cybersecurity system, where the average cost of a cyberattack is ${$}1.1$ million. No matter how much a system is secure, it will eventually fail without proper and continuous monitoring. No wonder that the cybersecurity market is expected to grow up to ${$} 170.4$ billion in 2022. However, the majority of legacy industries do not invest in NSM implementation until it is too late due to the initial and operation cost and static unutilized resources. Thus, this paper proposes a novel dynamic Internet of things (IoT) architecture for an industrial NSM that features a low installation and operation cost, low power consumption, intelligent organization behavior, and environmentally friendly operation. As a case study, the system is implemented in a midrange oil a gas manufacture facility in the southern states with more than 300 machines and servers over three remote locations and a production plant that features a challenging atmosphere condition. The proposed system successfully shows a significant saving $(gt 65$%) in power consumption, acquires one-tenth the installation cost, develops an intelligent operation expert system tools as well as saves the environment from more than 500 mg of CO2 pollution per hour, promoting green IoT systems.","PeriodicalId":184138,"journal":{"name":"2021 IEEE 7th World Forum on Internet of Things (WF-IoT)","volume":"6 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123686632","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: 4

Application case of IoT, Cloud and DLT technologies to enhance particulate matter air sampling 物联网、云和DLT技术应用案例，增强空气颗粒物采样

2021 IEEE 7th World Forum on Internet of Things (WF-IoT) Pub Date : 2021-06-14 DOI: 10.1109/WF-IoT51360.2021.9595556

D. Suarez-Bagnasco

{"title":"Application case of IoT, Cloud and DLT technologies to enhance particulate matter air sampling","authors":"D. Suarez-Bagnasco","doi":"10.1109/WF-IoT51360.2021.9595556","DOIUrl":"https://doi.org/10.1109/WF-IoT51360.2021.9595556","url":null,"abstract":"Aerosols are fine solid particles (particulate matter: PM) or liquid droplets in gas (usually air). Its origin can be natural or anthropogenic. Air PM pollution exposure is linked to diverse human health problems and to many environmental effects. Air samplers are used to study particles in air. Systematic periodic air sampling is needed to have confident air quality assessment. In this work we present a device (named RDMA) and a software application (named Enviro-Air Sampling) we have developed to enable access to environmental data, flow data, geolocation, and meteorological conditions from high volume air samplers (HVAS) with no data acquisition capabilities. One of the objectives of the RDMA (designed ab-initio to be an easy add-on to Tisch HVAS) is to enable a more precise determination (compared to Tisch Dickinson chart recorder) of the mass concentration of particles (MC) and of the standard mass concentration (SMC). In this paper we present some aspects of the work done that involved the use of IoT, Cloud, and DLT (Distributed Ledger Technology) technologies, that are enabling and driving Digital Transformation.","PeriodicalId":184138,"journal":{"name":"2021 IEEE 7th World Forum on Internet of Things (WF-IoT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122755881","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

Physical Layer Security for IoT Communications - A Survey 物联网通信的物理层安全-调查

2021 IEEE 7th World Forum on Internet of Things (WF-IoT) Pub Date : 2021-06-14 DOI: 10.1109/WF-IoT51360.2021.9595025

P. Rojas, Sara Alahmadi, M. Bayoumi

引用次数: 4