The continued integration of Internet of Things (IoT) applications have become more prevalent, due to the improved development in hardware, software, and communication technologies. This year’s World Forum topical track will discuss how Artificial Intelligence and Machine Learning (AI/ML) can be employed as an enabler for many different IoT applications to advance the society. The emergence of connected devices that provide observations and data measurements from the physical world have facilitated the increase in volume of collected data. AI/ML can provide insights from the data to further enhance the intelligence and the capabilities of IoT applications.
AI/ML approaches are revolutionizing the exploitation of data in products, processes, and services to make it possible to find important patterns and perform complex analysis. Within the session we will discuss technologies and applications of how AI/ML techniques can be applied to further enhance the intelligence and the capabilities of IoT applications.
Some particular areas of interest include, but are not limited to:
- AI for Edge Computing
- AI and IoT in a 5G context
- AI based Recommender Systems
- Distributed Machine Learning
- Interpretable Machine Learning
- Deep Learning for IoT applications
- Reinforcement Learning for IoT applications
- Optimization Methods for Machine Learning
Anthony Smith, Florida Institute of Technology (FIT), Melbourne, Florida, USA
Dr. Anthony Smith holds a MS in Computer Science, a MS in Engineering, and graduated with his PhD from the University of Florida in Computer Engineering. He is currently a practicing professional Data Scientist and an Assistant Professor of Computer Engineering and Sciences at Florida Institute of Technology (FIT). Dr. Smith has over 19 years of system/software engineering, and research experience, where he has served as a Principal Investigator and Research Scientist on various industry projects at Harris Corporation, as well as other DoD and government contract organizations. He has an extensive background in the design and development of complex algorithms for various data types (e.g. time-series, video, LiDAR, electro-optical). Dr. Smith currently holds 16 patents in the areas of advance image and signal processing, and high performance computing. His professional affiliations include The National Academy of Inventors, SPIE, and IEEE. Dr. Smith is a Co-director of the Information Characterization ad Exploitation (ICE) Lab at FIT. He has established research in the areas of data science, machine learning, computer vision, and high performance computing.
Mingming Liu, Dublin City University, Ireland
Dr. Mingming Liu is currently an Assistant Professor in the School of Electronic Engineering. He received his B.Eng. degree with first class honours from the Department of Electronic Engineering at the National University of Ireland Maynooth in 2011, and then the PhD degree from the Hamilton Institute from the same university in 2015 with his thesis entitled “Topics in Electromobility and Related Applications”. After that, he joined University College Dublin as a postdoctoral researcher then a senior postdoctoral researcher with the Control Engineering and Decision Science Research Group within the School of Electrical and Electronic Engineering, where he spent almost three years working on both EU and SFI funded projects, including Green Transportation and Networks (SFI) and Enable-S3 (H2020), with strong collaborations with both academia and industry. Before joining DCU, he worked at IBM Ireland lab as a data scientist, applied researcher, and H2020 project lead (5G Solutions), where his main focus was to leverage the state-of-the-art machine learning and applied optimisation techniques for practical and challenging problems arising in the industry. His current research interests include machine/deep learning, data science, centralised & distributed control and optimisation theories with links to electric, hybrid vehicles and IoT in the context of smart grids, intelligent transportation systems and smart cities.
Ziran Wang, InfoTech Labs
Ziran Wang is a research scientist at InfoTech Labs, Toyota Motor North America R&D, Mountain View, CA. Dr. Wang received Ph.D. in mechanical engineering from University of California, Riverside. His research interests include cooperative automation and digital twin of intelligent vehicles.
Takl Title: Artificial Intelligence of Things (AIoT) in Intelligent Vehicles
Abstract: AIoT, a combination of artificial intelligence (AI) and Internet of Things (IoT), has recently become a new trend in the industry. In this talk, an application of AIoT in the automotive industry is presented as an advanced driver assistance system (ADAS) on intelligent vehicles. Drivers of intelligent vehicles are characterized and modelled using a learning approach to enable personalized advisory feature. Meanwhile, all related models in this ADAS are computed on the cloud server, and executed through vehicle-to-cloud communication. Results of human-in-the-loop simulation in Unity game engine, and field implementation on real passenger vehicles are shown.
Yingqi Gu, Dublin City University, Ireland
Yingqi Gu is currently a postdoc research fellow with the Insight Centre for Data Analytics at Dublin City University, and an adjunct lecturer at National University of Ireland Maynooth. Dr. Gu received her Master of Science from School of Engineering, the University of Edinburgh and the Ph.D. in Control Engineering and Decision Science from School of Electrical and Electronic Engineering, University College Dublin. Her current research interests include AI & machine learning, control and optimisation theories with applications to electric vehicles, smart intelligent systems, and healthcare systems.
Talk Title: Leveraging Machine Learning Technologies for Improved Healthcare Systems
Abstract: Medication non-adherence is a widespread problem affecting over 50% of people who have chronic illness and need chronic treatment. Non-adherence exacerbates health risks and drives significant increases in treatment costs. In order to address these challenges, the importance of predicting patients’ adherence has been recognised. In this talk, an approach to predict the injectable medication adherence by using a digital IoT device and machine learning models will be presented. The newly invented ‘smart sharps bin’ and the end-to-end machine learning pipeline will be discussed in great details. Promising predictive performance on patients’ adherence will be demonstrated in this talk.
Mohammad Asad Rehman Chaudhry, Texas A&M University, USA
Mohammad Asad Rehman Chaudhry (PhD Electrical & Computer Engineering, Texas A&M University; MBA University of Toronto-Rotman School of Management) is a seasoned professional and thought-leader spearheading multi-disciplinary projects in Digital Disruption and Future-Tech.
He Chairs IEEE Working Group for the Standards for Software-Defined and Virtualized Ecosystems Performance. He is a cofounder of two companies Soptimizer, and Karbonbloc. He also serves on the Advisory Board of FBIT at Ontario Tech. He previously held industrial and faculty positions at IBM Research, the Hamilton Institute, University of Toronto, DARPA System F6, and the University of Calgary. He received several honors and accolades including a Fulbright Fellowship, and Peter. F Drucker Effective Executive Scholarship.
Talk Title: Blockchain, AI, 5G, IoT: A Marriage Made in Heaven
Abstract: IDC forecasts that there would be more than 41.6 billion connected IoT devices, generating 79.4 zettabytes of data in 2025. On one hand these devices are expected to bring revolutionary comfort to our lives, but on the other hand there would be enormous challenges faced in terms of storage, transmission, privacy, security, authenticity, and meaning of the data generated by these devices. This talk will discuss how Blockchain, AI, and 5G can work together with IoT to tackle these challenges.