About the series
Bio: Professor John A. Stankovic is the BP America Professor in the Computer Science Department at the University of Virginia and Director of the Link Lab. He is a Fellow of both the IEEE and the ACM. He has been awarded an Honorary Doctorate from the University of York, U.K., for his work on real-time systems. He won the IEEE Real-Time Systems Technical Committee's Award for Outstanding Technical Contributions and Leadership. He also received the IEEE Technical Committee on Distributed Processing's Distinguished Achievement Award (inaugural winner). He has a Test of Time paper award, 8 Best Paper awards. Stankovic has an h-index of 121 and over 68,000 citations. In 2015 he was awarded the Univ. of Virginia Distinguished Scientist Award, in 2010 the School of Engineering’s Distinguished Faculty Award, and in 2020 the UVA Faculty Mentor Award. He also received a Distinguished Faculty Award from the University of Massachusetts. He has given more than 40 Keynote talks at conferences and many Distinguished Lectures at major Universities. His research interests are in real-time systems, wireless sensor networks, smart and connected health, smart cities, cyber-physical systems, and the Internet of Things. Prof. Stankovic received his Ph.D. from Brown University.
Talk Abstract: Is the Internet of Healthcare Things (IOHT) hype or on the cusp of a healthcare revolution? We believe that wearables, in-situ sensors, machine learning, natural language processing, and the Internet are providing the technological backbone to achieve a true revolution in healthcare. Many challenges remain due to numerous factors including the complexities of human health and the realism of deployment of the technology especially for the elderly. This talk describes our progress towards establishing an ambient intelligence for healthcare. Descriptions of several wearables and conversational-based solutions that support taking medications, exercising, and quality of handwashing will be presented. Voice will be a major modality for this coming revolution. We present a solution for detecting emotion via speech even at significant distances from a microphone and in realistic settings. We also present a novel bi-directional LSTM with Multiple Instance Learning (MIL) for detecting anxiety from speech. We conclude with several observations concerning multi-disciplinary research that requires in-home deployments.
Register in advance for this webinar:
Or an H.323/SIP room system:
H.323: 126.96.36.199 (US West) or 188.8.131.52 (US East)
Meeting ID: 160 881 6944
After registering, you will receive a confirmation email containing information about joining the webinar.