Editor-In-Chief of Elsevier Smart Health Journal
Short Bio: Weisong Shi (Fellow, IEEE) is a Professor and the Chair of the Department of Computer and Information Sciences, University of Delaware (UD), where he leads the Connected and Autonomous Research (CAR) Laboratory. He is an internationally renowned expert in edge computing, autonomous driving, and connected health. His pioneer paper titled “Edge Computing: Vision and Challenges” has been cited more than 5700 times. Before he joins UD, he was a Professor with Wayne State University from 2002 to 2022 and served in multiple administrative roles, including an Associate Dean for Research and Graduate Studies with the College of Engineering and an Interim Chair of the Computer Science Department. He also served as a National Science Foundation (NSF) Program Director from 2013 to 2015 and the Chair of two technical committees of the Institute of Electrical and Electronics Engineers (IEEE) Computer Society. He has published more than 270 articles in peer-reviewed journals and conferences and served in editorial roles for more than ten academic journals and publications, including EIC of Smart Health, AEIC of IEEE Internet Computing Magazine. He is a Distinguished Member of ACM. He is the Founding Steering Committee Chair of several conferences, including ACM/IEEE Symposium on Edge Computing (SEC), IEEE/ACM International Conference on Connected Health (CHASE), and IEEE International Conference on Mobility (MOST).
Date: December 16, 2023
Topic: Federated Learning for Wearable Healthcare Devices
Editor-in-Chief of IEEE TNSE, Associate Editor for IEEE TCSVT, IEEE TWC, and IEEE TVT
Dapeng Oliver Wu received Ph.D. in Electrical and Computer Engineering from Carnegie Mellon University, Pittsburgh, PA, in 2003. Currently, he is Yeung Kin Man Chair Professor of Network Science, at the Department of Computer Science, City University of Hong Kong. His research interests are in the areas of artificial intelligence, communications, image processing, computer vision, signal processing, and biomedical engineering.
He received University of Florida Term Professorship Award in 2017, University of Florida Research Foundation Professorship Award in 2009, AFOSR Young Investigator Program (YIP) Award in 2009, ONR Young Investigator Program (YIP) Award in 2008, NSF CAREER award in 2007, the IEEE Circuits and Systems for Video Technology (CSVT) Transactions Best Paper Award for Year 2001, the Best Paper Award in GLOBECOM 2011, and the Best Paper Award in QShine 2006. He has served as Editor-in-Chief of IEEE Transactions on Network Science and Engineering, and Associate Editor of IEEE Transactions on Communications, IEEE Transactions on Signal and Information Processing over Networks, and IEEE Signal Processing Magazine. He was the founding Editor-in-Chief of Journal of Advances in Multimedia between 2006 and 2008, and an Associate Editor for IEEE Transactions on Circuits and Systems for Video Technology, IEEE Transactions on Wireless Communications and IEEE Transactions on Vehicular Technology. He has served as Technical Program Committee (TPC) Chair for IEEE INFOCOM 2012. He was elected as a Distinguished Lecturer by IEEE Vehicular Technology Society in 2016. He is an IEEE Fellow.
Abstract: Federated learning enables multiple distributed devices to collaboratively learn a shared prediction model without centralizing their on-device data. Most of the current algorithms require comparable individual efforts for local training with the same structure and size of on-device models, which, however, impedes participation from resource-constrained devices such as wearable healthcare devices. To cope with heterogeneous devices, we propose a new federated learning framework with heterogeneous on-device models through Zero-shot Knowledge Transfer, called FedZKT. Specifically, FedZKT allows devices to independently determine their on-device models according to their own local resources. This talk presents the design of FedZKT, the effectiveness and robustness of FedZKT towards on-device knowledge agnostic, on-device model heterogeneity, and other challenging federated learning scenarios, such as heterogeneous on-device data and straggler effects.
Topic: Wearable Computing for Healthcare and Motion Analysis
Editor-In-Chief of ACM Transactions on Computing for Healthcare
Short Bio: Dr. Gang Zhou is a professor of computer science at William & Mary, where he previously served as the Graduate Program Director from 2015 to 2017. He is an IEEE Fellow, a co-Editor-In-Chief of ACM Transactions on Computing for Healthcare, and a co-Area-Editor of IEEE Internet of Things Journal. He earned his Ph.D. degree from the University of Virginia in 2007. His research interests encompass a range of cutting-edge topics, including wearables & sensor systems, smart health, internet of things, wireless, ubiquitous & mobile computing. Dr. Zhou has served as a Steering Committee member (2018-present), General Chair (2019), and TPC Chair (2018 and 2023) of CHASE---ACM/IEEE’s premier conference on Connected Health: Applications, Systems and Engineering Technologies. He has also been recognized with several prestigious awards, including the NSF CAREER Award in 2013, the Best Paper Award from IEEE Internet Computing in 2020, and the Best Paper Award from IEEE ICNP in 2010.
Abstract: Healthcare is a fundamental human need that has been revolutionized by computing in the past century. Technology has transformed the way we approach healthcare from paper and pencil to individual computers, to connected devices via the internet, and now to wireless and mobile smartphones and wearables. In recent years, sensors have been integrated into these mobile and wearable devices, making healthcare a potential killer application for wearables. Additionally, non-contact sensing based on radio technologies is emerging as a promising new approach. As mobile and wearable computing can potentially dominate the healthcare landscape, I am excited to introduce three wearable computing platforms that my research group has been developing for Parkinson's Disease patients and other subjects for gait and motion analysis and real-time intervention. These platforms include IMU, magnet, and textile sensors. Using these sensors, we can provide personalized and targeted interventions to improve patient outcomes and well-being.