{"title":"Multi-Task Gaussian Process Learning for Energy Forecasting in IoT-Enabled Electric Vehicle Charging Infrastructure","authors":"Mostafa Gilanifar, M. Parvania, M. E. Hariri","doi":"10.1109/WF-IoT48130.2020.9221159","DOIUrl":"https://doi.org/10.1109/WF-IoT48130.2020.9221159","url":null,"abstract":"Modern electric vehicle (EV) charging infrastructure represents an application of an Internet of Things (IoT) framework in power systems where communication networks are the basis to transmit, monitor, and control a network of EV charging stations. This paper takes advantage of the high-resolution EV charging data made available by IoT-enabled charging stations for developing models that would forecast the energy demand of EV charging stations. More superficially, this paper proposes a Multi-Task Learning (MTL) method that enhances the estimation and forecast accuracy by fusing data from multiple charging stations via a Gaussian Process (GP) model in order to extract common features of the charging data. The proposed GP model learns a shared covariance function over all data sources, and transfers the meaningful knowledge of one charging station to other stations, which helps improve the forecasting accuracy. Data from multiple EVs charging stations in Utah is used in a case study to implement and validate the proposed forecasting model. The implementation results show that the proposed method significantly outperforms the state-of-the-art forecasting methods.","PeriodicalId":397397,"journal":{"name":"2020 IEEE 6th World Forum on Internet of Things (WF-IoT)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134577397","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}
P. Manandhar, Keran Rong, Katherine Carroll, Roland de Filippi, Ira Winder, J. Dieffenbach, B. Moser
{"title":"Sensing systemic awareness and performance of teams during model-based site design","authors":"P. Manandhar, Keran Rong, Katherine Carroll, Roland de Filippi, Ira Winder, J. Dieffenbach, B. Moser","doi":"10.1109/WF-IoT48130.2020.9221406","DOIUrl":"https://doi.org/10.1109/WF-IoT48130.2020.9221406","url":null,"abstract":"Operating with systemic awareness is a known factor in the success of large organizations. A similar dynamic could be in effect at the level of teams and teams of teams within organizations. Engineering teams are tasked with solving problems of multidisciplinary nature with multiple stakeholder constraints. To perform at a higher level, teams need to be aware of multiple constraints simultaneously. This paper proposes the design of sensors to measure team awareness using team attention in the problem and solution spaces. A model problem of designing an innovation campus is chosen. Data from 50 teams spending one hour with a model exploration interface are analyzed. Results suggest that strategy discussions help to arrive at more effective problem-solving. These results are not statistically significant but provide direction for further work.","PeriodicalId":397397,"journal":{"name":"2020 IEEE 6th World Forum on Internet of Things (WF-IoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130859187","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}
{"title":"Decentralized IoT with Wattsworth","authors":"J. Donnal, Ryan S. McDowell, M. Kutzer","doi":"10.1109/WF-IoT48130.2020.9221350","DOIUrl":"https://doi.org/10.1109/WF-IoT48130.2020.9221350","url":null,"abstract":"Low cost sensors, powerful single board computers, and high bandwidth wireless networks have encouraged the proliferation of IoT systems to both measure and control our environment. Unfortunately those eager to realize the benefits of IoT are generally forced to choose between centralized commercial offerings or developing their own system from scratch. The former is cost effective but brittle, while the later is flexible but often impractical. Wattsworth is an open source platform for decentralized IoT providing users with the best of both worlds. Users can leverage a turn-key software stack while still retaining total control of their systems with no dependency on third party infrastructure. This paper presents three case studies showing how Wattsworth solves traditionally challenging IoT scenarios. In particular, these case studies illustrate how to collect data from proprietary sensors, design complex user interfaces, and coordinate diverse geographically distributed devices. Source code, full documentation, and installation media for Wattsworth are available at https://wattsworth.net.","PeriodicalId":397397,"journal":{"name":"2020 IEEE 6th World Forum on Internet of Things (WF-IoT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133094129","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}
{"title":"Evaluating Distinct Sensations by Modulating High-Frequency Electrotactile Pulses for Unobtrusive Communication with IoT Devices","authors":"Sina Parsnejad, Sylmarie Dávila-Montero, A. Mason","doi":"10.1109/WF-IoT48130.2020.9221040","DOIUrl":"https://doi.org/10.1109/WF-IoT48130.2020.9221040","url":null,"abstract":"IoT devices that report information to a user, such as fitness trackers, exhibit a need for user feedback capable of communicating a wide range of messages in an unobtrusive manner. This paper describes the use of high-frequency electrotactile stimulation pulses for producing multiple distinct sensations within a limited messaging window of 0.5s that serve as unobtrusive and discreet feedback messages. Two experiments were conducted on willing participants using a custom electrotactile stimulator. Experiment 1 investigated the effectiveness of producing unique sensations by varying a compound electrotactile stimulation where a 1kHz pulse train is modulated by a frequency between 10Hz and 100Hz (mid-range frequencies). Results indicate that participants can discriminate midrange frequencies utilizing compound electrotactile stimulus composed of 1kHz pulses. Experiment 2 investigated the effectiveness of creating new sensations by modulating high-frequency pulse trains with a mid-range \"Bundle\" frequency of varying duty cycle. Results show that variations in Bundle frequency duty-cycle produced at least three distinct sensations that may be employed to produce distinct sensations. Such distinct electrotactile sensations permit unobtrusive communication between individuals and wearable IoT device.","PeriodicalId":397397,"journal":{"name":"2020 IEEE 6th World Forum on Internet of Things (WF-IoT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114233776","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}
{"title":"Deep Learning for Optimal Resource Allocation in IoT-enabled Additive Manufacturing","authors":"Farshad Mashhadi, Sergio A. Salinas Monroy","doi":"10.1109/WF-IoT48130.2020.9221038","DOIUrl":"https://doi.org/10.1109/WF-IoT48130.2020.9221038","url":null,"abstract":"Additive manufacturing is revolutionizing the way that we produce, deliver, and consume objects in many industries. Compared to traditional manufacturing, where large factories mass produce objects far away from consumers, additive manufacturing can build customized objects in many small factories closer to where they are needed. Building these simplified supply chains requires manufacturers to employ IoT technologies that can provide real-time monitoring of the 3D-printers, and automatically adjust their operation to meet a highly-dynamic object demand. To this end, researchers have proposed the Additive Manufacturing (AM) cloud that can automatically manage the manufacturing resources based on real-time data collected from IoT-enabled equipment. However, most existing works on the AM Cloud only focus on finding production decisions that minimize the operating costs of the AM Cloud, and disregard setting prices for their services, which limits the profits of the manufacturers. To bridge this gap, we design a deep-learning auction that maximizes the utility of the AM Cloud by assigning 3D-printers to the buyers who are willing to pay the highest prices for their objects, and by assigning production orders to the manufacturers that can build the objects at the lowest cost. The auction prevents buyers from unfairly affecting the results, and its assignments satisfy production capacity and raw material constraints. We conduct extensive simulations, and see that our proposed auction mechanism can both find production control decisions and improve the utility of the AM Cloud by up to 50% compared to existing approaches.","PeriodicalId":397397,"journal":{"name":"2020 IEEE 6th World Forum on Internet of Things (WF-IoT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128276908","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}
João Marcos do Valle, Gabriel Souza, N. Cacho, Iaslan Silva, Jaine Budke, Henrique Sales, Frederico Lopes, D. Araújo, R. Silva
{"title":"Using Traces from IoT Devices to Solve Criminal Cases","authors":"João Marcos do Valle, Gabriel Souza, N. Cacho, Iaslan Silva, Jaine Budke, Henrique Sales, Frederico Lopes, D. Araújo, R. Silva","doi":"10.1109/WF-IoT48130.2020.9221265","DOIUrl":"https://doi.org/10.1109/WF-IoT48130.2020.9221265","url":null,"abstract":"During a criminal investigation, the evidence collection process produces an enormous amount of data. These data are present in many medias and IoT devices that are extracted as crime evidences (USB flash drives, smartphones, hard drives, computers, drones, smartwatches, AI speakers, sensors etc). Due to this data volume, the manual analysis is slow and costly. This work fulfills this gap by presenting a data extraction and processing platform for crime evidence analysis. Our proposed platform leverages a lambda architecture and uses a set of tools and frameworks such as Hadoop HDFS, Kafka, Spark and Docker to analyze a big volume of data at an acceptable time. We also present an example of the proposed platform in use by the State Attorney Office of Rio Grande do Norte (Brazil), where some evaluative tests have been carried out.","PeriodicalId":397397,"journal":{"name":"2020 IEEE 6th World Forum on Internet of Things (WF-IoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129732071","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}
Omar Eldash, Adam Frost, Kasem Khalil, Ashok Kumar, M. Bayoumi
{"title":"Dynamically Reconfigurable Deep Learning for Efficient Video Processing in Smart IoT Systems","authors":"Omar Eldash, Adam Frost, Kasem Khalil, Ashok Kumar, M. Bayoumi","doi":"10.1109/WF-IoT48130.2020.9221101","DOIUrl":"https://doi.org/10.1109/WF-IoT48130.2020.9221101","url":null,"abstract":"Video systems are the core of many IoT systems, and efficient processing is crucial for their operation. There is little work focusing on the flexibility of current hardware systems when used for long term deployment, particularly for constrained devices such as those used in IoT. This paper shows a unique case study for Video Processing Nodes that adopt deep learning algorithms and dynamically switch the models within a streaming path to investigate the flexibility that can be offered and the limitations within different applications. The video processing node utilizes a framework called FINN that generates FPGA compatible models. The proposed system can switch between different configurations according to their quantization, showing how accuracy and confidence can vary with each option. Inference per second is one of the major benefits when switching between different configurations, where a 1-bit weight and 1-bit activation achieves the highest inference rate for convolutional neural networks and greatly reduces energy consumption.","PeriodicalId":397397,"journal":{"name":"2020 IEEE 6th World Forum on Internet of Things (WF-IoT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129444701","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}
Monette H. Khadr, Haythem A. Bany Salameh, M. Ayyash, Sufyan Almajali, H. Elgala
{"title":"Testbed Validation of Security-Aware Channel Assignment in Cognitive Radio IoT Networks","authors":"Monette H. Khadr, Haythem A. Bany Salameh, M. Ayyash, Sufyan Almajali, H. Elgala","doi":"10.1109/WF-IoT48130.2020.9221302","DOIUrl":"https://doi.org/10.1109/WF-IoT48130.2020.9221302","url":null,"abstract":"Cognitive radio networks (CRNs) are a propitious realization for Internet-of-Things (IoT) applications due to their superior utilization of spectrum and time-critical data delivery. With the expected widespread of IoT devices, security concerns are escalating; forcing additional challenges on network designers. Jamming attacks are one of the most common kind of attacks. Various solutions in literature were proposed to address these attacks, however, the analysis in most of the proposed methods relied on simulation and emulation tools which fail to accurately capture realistic environmental conditions, specifically radio propagation. In this paper, a thorough experimental performance evaluation of our spectrum assignment scheme for CR-IoT applications under jamming attacks is orchestrated over the large scale and open Future Internet-of-Things (FIT) IoT-LAB testbed. The proposed algorithm exploits statistical information of both the licensed primary user and the jammer to provide CR-IoT devices with the most secure idle channel which has the least invalidity ratio. Experimental results show that the proposed algorithm can significantly improve the reliability and overall performance of the network in terms of throughput and packet loss.","PeriodicalId":397397,"journal":{"name":"2020 IEEE 6th World Forum on Internet of Things (WF-IoT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117088737","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}
S. Kakakhel, Aron Kondoro, Tomi Westerlund, I. Dhaou, J. Plosila
{"title":"Enhancing Smart Grids via Advanced Metering Infrastructure and Fog Computing Fusion","authors":"S. Kakakhel, Aron Kondoro, Tomi Westerlund, I. Dhaou, J. Plosila","doi":"10.1109/WF-IoT48130.2020.9221172","DOIUrl":"https://doi.org/10.1109/WF-IoT48130.2020.9221172","url":null,"abstract":"The smart grid is a new generation of the power grid that incorporates advanced features such as distributed energy resources, two-way communication and situation awareness. It is not just energy that is exchanged between consumers and producers but information. An efficient and robust smart grid requires efficient and robust communication and computation infrastructure to carry and process the associated data. We provide an overview of the possibilities that fog computing offer for smart grids. In our investigation, the pillars of fog computing, such as decentralization, resiliency, scalability and mobility, offer a perfect match for the decentralized smart grid. Fog computing nodes, capable of communication and coordination, incorporated in smart meters, will provide distributed control, communication and computation. Thus, enhancing reliability, resiliency and scalability of the smart grid as more and more distributed energy resources (DERs) are added to the grid.","PeriodicalId":397397,"journal":{"name":"2020 IEEE 6th World Forum on Internet of Things (WF-IoT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115652558","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}
Christos Chatzigeorgiou, M. Feidakis, Dimitrios G. Kogias, C. Patrikakis
{"title":"Increasing safety and security in public places using IoT devices","authors":"Christos Chatzigeorgiou, M. Feidakis, Dimitrios G. Kogias, C. Patrikakis","doi":"10.1109/WF-IoT48130.2020.9221458","DOIUrl":"https://doi.org/10.1109/WF-IoT48130.2020.9221458","url":null,"abstract":"The demo presented here covers three use cases that are part of \"DESMOS\" (Smart Interconnected Infrastructures for Security and Protection) project which aims to develop a novel framework for the intelligent interconnection of smart infrastructures, mobile and wearable devices and apps for the provision of a secure environment for citizens. The implemented platform promotes the collaboration between people and devices to increase citizens’ protection by supporting timely reporting of incidents, adaptation of the interconnected environments in case of emergency and the provision of assistance by empowering local authorities and volunteers. The project is funded by the European Union and Greek national funds under the call RESEARCH-CREATE-INNOVATE, and is implemented by a consortium of Academic/Research Institutes, companies, while the pilot trials are taking place in the city of Trikala, Greece.","PeriodicalId":397397,"journal":{"name":"2020 IEEE 6th World Forum on Internet of Things (WF-IoT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131431301","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}