Prof. Dr. Kay Römer

TU Graz, Austria 

Talk Title: Towards Indoor GPS

Biography: Kay Römer is professor at and director of the Institute for Technical Informatics and head of the Field of Expertise "Information, Communication & Computing" at TU Graz. He obtained his doctorate in computer science from ETH Zurich in 2005 with a thesis on wireless sensor networks. Kay Römer is an internationally recognized expert on networked embedded systems, with research focus on dependable wireless networking, localization, and testbeds. He has co-chaired the program committees of all leading conferences in his field such as SenSys, IPSN, or SECON, he is also chairing the steering committee of the EWSN conference series. He is coordinator of the TU Graz Research Center "Dependable Internet of Things" and leads the research area "Cognitive Products" in the research center Pro2Future - Products and Production of the Future.

Abstract: While we had outdoor localization systems with global coverage such as GPS for decades, these satellite-based systems do not work well indoors and there is to date no indoor equivalent to GPS. That may change with the recent availability of low-cost and low-power Ultra Wide Band (UWB) radio transceivers produced by Dacawave (now Qorvo) or NxP and their ongoing ubiquitous deployment in the latest smartphone and tablet generations. While these UWB radios enable accurate distance measurements, also new algorithms and system architectures are needed for scalable, robust, secure, and low-cost indoor localization to pave the way towards an indoor GPS equivalent. This talk will give an overview of our recent research towards this goal, with focus on reducing the infrastructure overhead, enabling highly-scalable localization systems, dealing with line of sight obstructions, and securing localization systems.

Prof. Shiwen Mao

Auburn University

Talk Title: On Pre-trained Models for Non-intrusive Load Monitoring

Biography: SHIWEN MAO is a professor and Earle C. Williams Eminent Scholar Chair, and Director of the Wireless Engineering Research and Education Center (WEREC) at Auburn University. His research interest includes wireless networks, multimedia communications, and smart grid. He is a Distinguished Lecturer of IEEE Communications Society and the IEEE Council of RFID, and is on the Editorial Board of IEEE TWC, IEEE TNSE, IEEE TMC, IEEE IoT, IEEE TCCN, IEEE OJ-ComSoc, IEEE/CIC China Communications, IEEE Multimedia, IEEE Network, IEEE Networking Letters, and ACM GetMobile. He received the IEEE ComSoc TC-CSR Distinguished Technical Achievement Award in 2019 and NSF CAREER Award in 2010. He is a co-recipient of the 2021 Best Paper Award of Elsevier/KeAi Digital Communications and Networks Journal, the 2021 IEEE Communications Society Outstanding Paper Award, the IEEE Vehicular Technology Society 2020 Jack Neubauer Memorial Award, the 2004 IEEE Communications Society Leonard G. Abraham Prize in the Field of Communications Systems, and several conference best paper awards. He is a Fellow of the IEEE. 

Abstract: Non-intrusive load monitoring (NILM) is to estimate individual appliance's power consumption from aggregated smart meter data, which is useful for optimized energy management and provisioning of customized services. While deep learning (DL) has achieved state-of-the-art NILM performance, it is still constrained by the dependency on large amounts of data and intensive computations on training. In this talk, we present a pre-training approach to address the generalization of DL models for NILM. We develop a meta-learning based approach and an ensemble learning based approach, which pre-train a base model and then fine-tune it with few-short learning when applied to an unknown dataset. In the second part of this talk, we present a Middle Window Transformer model, termed Midformer, for NILM. Existing models are limited by high computational complexity, dependency on data, and poor transferability. In Midformer, we first exploit patch-wise embedding to shorten the input length, and then reduce the size of queries in the attention layer by only using global attention on a few selected input locations at the center of the window to capture the global context. The cyclically shifted window technique is used to preserve connection across patches. We also follow the pre-training and fine-tuning paradigm to relieve the dependency on data, reduce the computation in modeling training, and enhance transferability of the model to unknown tasks and domains. The models are validated with two real-world datasets and shown to achieve a superior transferability performance compared with traditional DL and transfer learning methods. 

Prof. Hussein T. Mouftah

University of Ottawa

Talk Title: AI-enabled Connected Autonomous Electric Vehicles in Smart City based Smart Grids

Biography: Hussein T. MOUFTAH received the BSc in Electrical Engineering and MSc in Computer Science from the University of Alexandria, Egypt, in 1969 and 1972, respectively, and the Ph.D. degree in Electrical Engineering from Laval University, Canada, in 1975. He joined the School of Electrical Engineering and Computer Science (was School of Information Technology and Engineering) of the University of Ottawa in 2002 as a Tier 1 Canada Research Chair Professor, where he became a Distinguished University Professor in 2006. He was with the ECE Department, Queen’s University (1979–2002), where he was prior to his departure a Full Professor and the Department Associate Head. He has six years of industrial experience mainly at Bell Northern Research of Ottawa (Nortel Networks). He is the author or coauthor of 13 books, 78 book chapters and more than 1800 technical papers, 17 patents, 5 invention disclosures, and 148 industrial reports. Dr. Mouftah served as the Editor-in-Chief of the IEEE Communications Magazine (1995–1997) and IEEE ComSoc Director of Magazines (1998–1999), Chair of the Awards Committee (2002–2003), Director of Education (2006–2007), and a Member of the Board of Governors (1997–1999 and 2006–2007). He was a Distinguished Speaker of the IEEE Communications Society (2000–2007). He is a Fellow of the IEEE (1990), the Canadian Academy of Engineering (2003), the Engineering Institute of Canada (2005), and the Royal Society of Canada RSC Academy of Science (2008). He is the joint holder of 26 Best/Outstanding Paper Awards. He has received numerous prestigious awards, such as the 2017 Gotlieb Medal in Computer Engineering and Science, the 2016 R.A. Fessenden Medal in Telecommunications Engineering of IEEE Canada, the 2016 Distinguished Technical Achievement Award in Communications Switching and Routing of IEEE ComSoc Communications Switching and Routing Technical Committee, the 2015 IEEE Ottawa Section Outstanding Educator Award, the 2014 Engineering Institute of Canada K. Y. Lo Medal, the 2014 Technical Achievement Award of the IEEE Communications Society Technical Committee on Wireless Ad Hoc and Sensor Networks, the 2007 Royal Society of Canada Thomas W. Eadie Medal, the 2007–2008 University of Ottawa Award for Excellence in Research, the 2008 ORION Leadership Award of Merit, the 2006 IEEE Canada McNaughton Gold Medal, the 2006 EIC Julian Smith Medal, the 2004 IEEE ComSoc Edwin Howard Armstrong Achievement Award, the 2004 George S. Glinski Award for Excellence in Research of the University of Ottawa Faculty of Engineering, the 1989 Engineering Medal for Research and Development of the Association of Professional Engineers of Ontario, and the Ontario Distinguished Researcher Award of the Ontario Innovation Trust. 

Abstract: The transformation of our current cities into smarter cities will bring challenges in diverse areas such as the transportation system, the electricity system, and wearable systems, just to name a few. In smart cities, Information and Communication Technologies (ICT) will play a vital role for providing services in the urban environment. These services include real time monitoring and reaction in time through wireless sensor and actuator networks. Smart Grids (SGs), Intelligent Transportation Systems (ITS), Internet of Things (IoT), Electric Vehicles (EVs), and Wireless Sensor Networks (WSNs), supported by the advances in Artificial Intelligence (AI) and Machine Learning (ML), will be the building blocks of futuristic smart cities. In this presentation we will address ML techniques with a focus on autonomous vehicles and in particular on Connected and Autonomous Electric Vehicles (CAEVs) in smart cities. Current capabilities as well as limitations and opportunities of key AI enabling technologies will be reviewed, along with a discussion on the impact of such advances on society and the environment. All these technologies will help to build a smart city. A use case on evaluating traffic signs detection using deep convolutional neural networks (CNNs) such as Faster R-CNN for autonomous driving, will be provided. 

CPSIOT Past Speaker

Prof. Yonghui Li

School of Electrical and Information Engineering

The University of Sydney