Detecting human behavior from longitudinal data streams

Speaker Name: 
Afsaneh Doryab
Speaker Title: 
Computer Scientist and Systems Faculty
Speaker Organization: 
Carnegie Mellon University
Start Time: 
Friday, March 8, 2019 - 11:15am
End Time: 
Friday, March 8, 2019 - 12:15pm
Katherine Isbister

Abstract: Humans today interact frequently and intensively with a wide range of computing devices. These interactions generate data streams that can, in some cases, be analyzed to extract clues about the physical and mental states of users. Such latent information can be used to help create more intelligent systems that anticipate users’ needs and provide personalized services and interventions. This capability, however, introduces new technical and social challenges. In this talk, I will describe methods to computationally model human behavior from diverse data streams to assess the state of individuals' health and wellbeing. I will also describe how models of human behavior can help integrate technology into people’s lives and connect community members for opportunistic social and economic exchange.


Bio: Afsaneh Doryab, Ph.D. (IT University of Copenhagen, 2011), is a Computer Scientist and a Systems Faculty in the School of Computer Science at Carnegie Mellon University. She conducts research in the area of Intelligent Human-Centered Computing. She works on computational modeling of human behavior from data streams collected from ubiquitous and mobile devices in the wild. Dr. Doryab has more than 10 years of research experience in ubiquitous and mobile computing, machine learning, computational modeling of human behavior, context-aware computing, and human-computer interaction. Her research has been supported by the National Science Foundation and the National Institutes of Health.