University of Cambridge > Talks.cam > Centre for Mobile, Wearable Systems and Augmented Intelligence Seminar Series > Balancing Performance and Acceptability in Real-World Automated Dietary Monitoring

Balancing Performance and Acceptability in Real-World Automated Dietary Monitoring

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Lorena Qendro.

Abstract: Over the last decade, smartphones and wearable devices have become a powerful source of sensor data driving numerous mobile health applications. An active area of research in this space has been automated dietary monitoring (ADM), which addresses the problem of tracking what a person eats using passive and continuous sensing. A significant challenge in realizing a practical ADM system, however, has been striking a balance between acceptability and performance in real-world environments. In this talk, I will present several research efforts from my group aimed at creating an eating detection system that is high-performing in naturalistic setting while also being acceptable from a human-centered perspective. The trajectory of our research is characterized by the design of increasingly smaller and more compact ADM sensing systems, combining novel sensing and computational methods. Our approach has emphasized on-body precision sensing and targeted remote sensing, allowing us to explore ADM in various form-factors and configurations, including as facial stick-on sensors and intra-orally.

Bio: Edison Thomaz is an Assistant Professor in the Department of Electrical and Computer Engineering at The University of Texas at Austin, where he directs the Human Signals Laboratory. His research focuses on human-centered machine perception, the study of how to combine sensing and computation to build systems that can reason about, and make sense of humans and the human experience. A core area of interest is studying systems and methods for recognizing and modeling health-related activities and context. This work intersects with several disciplines, from ubiquitous computing and HCI to human-centered machine learning and signal processing. At UT Austin, he is a member of the DICE and BioECE tracks and belongs to the Wireless Networking and Communications Group (WNCG), an industry affiliates program. He is an Associate Editor of the ACM Proceedings on Interactive, Mobile, Wearable and Ubiquitous Technologies (PACM IMWUT ) and has served on numerous program and organizing committees for both ACM and IEEE conferences (e.g., Pervasive Health, CHI , ISWC). He presently co-directs the Life Sensing Consortium (LSC), a multi-disciplinary, multi-university collaborative network of researchers who use sensing technologies to conduct interdisciplinary sensing research to promote positive life outcomes. Prior to his Ph.D., Edison held industry positions at Microsoft and France Telecom. He holds a bachelor’s degree in Computer Science from UT Austin, a master’s from the MIT Media Lab and a Ph.D. in Human-Centered Computing from Georgia Tech.

This talk is part of the Centre for Mobile, Wearable Systems and Augmented Intelligence Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2021 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity