Personalized Behavior-Powered Systems
I will present work that leverages user behavioral data to build personalized applications, which I call “behavior-powered systems”. I will present 3 projects from our group. 1) WebGazer uses interaction data made on any website to continuously calibrate a webcam-based eye tracker, so that users can manipulate any web page solely by looking. 2) Portal-ble is an augmented reality device for smartphones that accommodates for imprecise hand manipulation and noisy hand tracking. 3) SleepCoacher uses smartphone sensors to capture noise and movement data while people sleep to automatically generate recommendations about how to sleep better through a continuous cycle of mini-experiments. Together, these systems show how subtle footprints of user behavior collected remotely can reimagine the way we gaze at websites, interact with virtual objects, and understand our sleep.
Jeff Huang is an Assistant Professor in Computer Science at Brown University. His research in human-computer interaction focuses on behavior-powered systems, spanning the domains of mobile devices, personal informatics, and web search. Jeff’s Ph.D. is in Information Science from the University of Washington in Seattle, and his masters and undergraduate degrees are in Computer Science from the University of Illinois at Urbana-Champaign. Before joining Brown, he analyzed search behavior at Microsoft Research, Google, Yahoo, and Bing, and co-founded World Blender, a Techstars-backed company that made geolocation mobile games. Jeff has been a Facebook Fellow and has received an NSF CAREER Award, Google Research Award, and Army Research Office Young Investigator Award.