Edison Thomaz

Publications      Teaching       Vita       Prospective Students

I am an Assistant Professor in the Department of Electrical and Computer Engineering at The University of Texas at Austin, where I direct the Human Signals lab. I hold 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. I am a member of DICE, WNCG, and I am currently an Associate Editor of IMWUT. I also co-lead the Life Sensing Consortium.

My research focuses on the computational perception of human signals (e.g., behavioral, emotional, physiological) while leveraging ubiquitous and wearable sensing. A core area of interest is studying systems and methods for recognizing and modeling the entire span of people's everyday activities and context. This work is at the intersection of ubiquitous computing, hci, human-centered machine learning, and signal processing. I am particularly motivated by applications in the domain of health and personalized medicine such as building health models and tools that can characterize and forecast states of health and disease from sensor data.

Contact Info

ethomaz at utexas dot edu
Twitter: @ethomaz

EER 7.818
2501 Speedway
Austin, TX 78712

Office Hours

Fri: 1pm-2pm


Fall 2021

EE382V - Human Signals

Spring 2022

EE422C - Software Design II



Rebecca Adaimi
Keum San Chun
Dawei Liang
Priyanka Khante
Xuewen Yao


Recent News

April 2021

We are actively looking for UT master students and undergrads to join our group. If you are interested in wearable + mobile computing, and activity recognition, please visit this. Experience with iOS programming, web app development and hardware fabrication would be especially welcome.

April 2021

The new UT Austin-based Institute for Foundations of Machine Learning (IFML) has awarded us a grant to work on adaptive and continual learning for activity recognition applications. We are excited to extend our research work in this direction.

March 2021

Rebecca Adaimi's paper on acoustic activity recognition with conversational assistants has been accepted to IMWUT and will be presented at Ubicomp in September. This work shows that it is possible to leverage gaps in voice interactions to learn about a person's context and activities.

January 2021

In collaboration with colleagues at Penn State and Stanford, we are kicking off a 5-year project to explore the use of wearables to prevent kidney stones. Thanks to the National Institute of Diabetes and Digestive and Kidney Diseases for supporting this effort.


Recent Publications

Improving Prediction of Real-Time Loneliness and Companionship Type Using Geosocial Features of Personal Smartphone Data
Congyu Wu, Amanda N. Barczyk, R. Cameron Craddock, Gabriella M. Harari, Edison Thomaz, Jason D. Shumake, Christopher G. Beevers, Samuel D. Gosling, David M. Schnyer
Smart Health 2021

Eating Episode Detection with Jawbone-Mounted Inertial Sensing
Keum San Chun, Hyoyoung Jeong, Rebecca Adaimi, Edison Thomaz
EMBC 2020

Edison Thomaz © 2021