Tutorials
Building on Convergent IoT: Novel Directions in the Tactile Internet
Abstract:
Recent developments in the Internet of Things (IoT) are ever more islandic, pushing the envelope in a myriad of silos. While the research community has produced significant milestones in improving the energy footprint, processing capacity, and overall resilience of IoT systems, today’s practitioner is faced with significant challenges in adopting an IoT platform/framework/standard. In this tutorial we will elaborate on the chronological and topological evolution of IoT frameworks, targeting a common understanding of the underlying reference models. We will present and contrast leading standards from industry (e.g., SymphonyLink, Thread, LoRaWAN), academia, and research communities (e.g., IEEE P2413 and ETSI), as well as growing alliances that span multiple stakeholders (e.g., AllSeen and Open Interconnect Consortium). We will present the ensuing challenge of Big Sensed Data (BSD), and the critical challenges facing IoT proliferation. This tutorial will elaborate on the role of Convergent IoT in building the next-generation of the Tactile Internet, and delve into the architectural basis of this nascent technology, and the multiplicity of factors that impact Ultra Reliable Low Latency Communication (URLLC) in a global deployment of the Tactile Internet. We will emphasize recent developments in the IEEE P1918.1 Tactile Internet standard, as the presenter is a key player in the development of the architecture, and secretary of the standard working group.
Biography:
Dr. Sharief Oteafy (S’08–M’14–SM’19) is an Assistant Professor at the School of Computing, DePaul University, USA. He received his PhD in 2013 from Queen’s University, Canada, focusing on adaptive resource management in Next Generation Sensing Networks. His current research focuses on dynamic architectures for interoperability in the Internet of Things, Information Centric Networks, and managing the proliferation of Big Sensed Data (BSD). He is currently a key player in the design of the Tactile Internet Architecture, under the development of the IEEE P1918.1 Standard Working Group, where he is now the secretary of the WG. He is actively engaged in the IEEE Communications Society (ComSoc). Dr. Oteafy co-authored a book on “Dynamic Wireless Sensor Networks”, published by Wiley, presented 50+ publications and delivered multiple IEEE tutorials on IoT and BSD. He co-chaired a number of IEEE symposia and workshops in conjunction with IEEE ICC and IEEE LCN, and served on the technical program committee of numerous IEEE and ACM symposia; recently co-chairing the AHSN track in IEEE Globecom 2018. He is currently an Associate Editor with IEEE Access, and on the editorial board of Wiley’s Internet Technology Letters. Dr. Oteafy is a Senior Member of the IEEE, and a professional member of the ACM. He also holds an Adjunct Assistant Professor position at Queen’s University.
The Future of Blockchains for the Management of Electronic Medical Records
Abstract:
Blockchains are a growing list of electronic records that are linked using cryptography and are saved in a distributed way. The key features of blockchains include decentralization, data transparency and privacy. These key features make it possible to use blockchains in several domains, the management of electronic medical records (EMR) of patients being one of the most vital domains exhibiting a lot of potential for future work. Given this, in this tutorial we aim to cover the usage of the principles of blockchain technology in the management of EMR. In this context, a framework will be discussed that maintains patient’s medical records in a blockchain and make it accessible to the concerned parties i.e., patient and doctor. Meanwhile the problem of scalability will be highlighted since with the passage of time, the data is supposed to grow exponentially and scalability will eventually become an issue. Moreover, the security aspect of the framework will also be highlighted given the sensitivity of the information that is carried by the EMRs.
Biography:
Dr. Farhan Riaz received his B.E. degree with distinction from the National University of Sciences and Technology (NUST), Islamabad, Pakistan, M.S. degree from the Technical University of Munich, Germany, and Ph.D. degree again with distinction from the University of Porto, Portugal. Since 2012, he has been serving NUST as a Faculty Member. He has about 11 years of experience in the area of computer vision, pattern recognition and signal processing, specifically applied to the Biomedical signal/imaging scenarios. He has 19 impact factor journal publications and about 40+ conference publications. His h-index is 11 and cumulative impact factor is 40+. In addition to his experience of working as a faculty member, he has also worked as a computer vision consultant with the Instituto de Telecomunicacoes, Porto, Portugal on various projects. During his Masters studies, he also worked part time with two multinational companies, Intel and NTT DoCoMo Euro labs where he worked in the RFID development team for supply chain management and design of wireless protocols respectively. Dr. Farhan has earned research funding worth 9.1 Million PKR, a project worth 47 Million PKR is almost positively negotiated. He has obtained various awards; most notably his team won Silver Medal in 2013 Asia Pacific ICT Awards and one of his research papers published in IEEE Transaction on Neural Systems and Rehabilitation Engineering won 3rd prize in the 2019 IEEE Engineering in Medicine and Biology Prize Paper Award.
Deep Learning with Tensorflow 2.0
Abstract:
In this tutorial, the participants will have hands-on experience on the newly released Tensorflow 2.0 library for deep learning applications. Deep learning has had a tangible impact on a number of fields in the recent years. Many libraries help people build deep architectures. Tensorflow is one of the most popular open source libraries out there. In this tutorial, we will go over the basics of Tensorflow 2.0. Then we will learn how to build a neural network, a deep convolutional neural network and long-short term memory networks in Tensorflow 2.0 with practical examples. If we have enough time left, in addition, we may develop a Generative Adversarial Networks as well. We will cover the structures of the different networks in brief; however, this will not be the focus of the tutorial. The focus will primarily be on the practical implementation. The participants are expected to have a working knowledge of Python and NumPy. In addition, the participants are expected to have working knowledge of machine learning and different architectures developed in the tutorial.
Biography:
Dr. Usman Tariq is a faculty member in the Electrical Engineering Department at the American University of Sharjah, Sharjah, UAE. He has over 10 years of experience in machine learning, image processing and computer vision. Before AUS, he worked as a Research Scientist in the Computer Vision group at the Xerox Research Center Europe, France. He earned his M.S. and Ph.D. degrees from the Electrical and Computer Engineering Department of University of Illinois at Urbana-Champaign (UIUC), respectively in 2009 and 2013. His research interests include computer vision, image processing, and machine learning.
On the Convergence of Internet of Things and Artificial Intelligence
Abstract:
The emergence of Internet of Things (IoT) coupled with artificial intelligence has changed the way we carry out everyday business to become smarter, productive and much safer. There have been many recent revolutions that IoT brought to a wide range of business and industrial sectors including smart cities, healthcare, emergency response, intelligent transportation, industrial automation and agriculture. Drones also have invaded our skies to provide unprecedented opportunities and see things like never before. In this tutorial, I am going to provide a quick update on the status quo of how IoT impacted our lives and what are the opportunities yet to unfold at the current progress pace. Then, I will elaborate on one application enabled by the convergence of IoT and machine learning in the agriculture domain using autonomous drones. Agriculture is ripe with opportunities to incorporate AI analytics, specifically novel and ever-growing deep learning analytics. Visual information for analysis can be collected autonomously using appropriately equipped and programmed mobile robots (drones & ground robots). The tutorial will shed the light on the technical details involving yield estimation using deep learning and Mask R-CNN for object detection and tracking, weed detection, crop disease classification, and fruit ripeness prediction. Pending resource availability, we will do some quick hands-on to better understand the processing pipeline and dataflow across the dataflow stack.
Biography:
Dr. Khalid Elgazzar, is a Canada Research Chair and assistant professor with the Faculty of Engineering and Applied Science at Ontario Tech University, Canada and an holds and adjunct assistant professor at Queen’s University where he also received his PhD degree in Computer Science from the School of Computing in 2013. He is the founder and director of the IoT Research Lab at Ontario Tech University. Prior to joining Ontario Tech, he was an assistant professor at University of Louisiana at Lafayette and an NSERC postdoctoral fellow at Carnegie Mellon School of Computer Science. Dr. Elgazzar named the recipient of the outstanding achievement in sponsored research award from UL Lafayette in 2017 and the distinguished research award from Queen’s University in 2014. He also received several recognition and best paper award at top international venues. Dr. Elgazzar is a rising world leader in the areas of Internet of Things (IoT), computer systems, real-time data analytics, and mobile computing. Dr. Elgazzar is currently an associate editor for Springer Peer-to-Peer Networking and Applications Journal and Wireless Communications and Mobile Computing. He also chaired a number of IEEE conferences and symposia on mobile computing, communications and IoT. Dr. Elgazzar is Senior IEEE Member and an active volunteer in technical program committees and organizing committees in both IEEE and ACM events.