My research explores autism through computational tools & methods 

I am a Senior Research Scientist in the School of Interactive Computing at Georgia Tech. By training, I am a developmental psychologist interested in early trajectories and predictors of social-communicative development in autism. Most recently, I have been collaborating with computer scientists to develop novel computational tools and methods to objectively measure such behaviors in natural settings. The goal is to develop tools that can help us better detect, understand, and ultimately treat autism.

Together, my collaborators and I are forging a new multidisciplinary research area, which we call computational behavioral science. Our research vision is that we can transform how we measure, analyze, and understand behavior by leveraging advances in sensing and wearable technologies and computational modeling and analysis methods.

A few recent publications

Recent talks & activities
* denotes student co-authors
  • *Edmunds, S.R., Rozga, A., *Li, Y., Karp, E.A., Ibanez, L.V., Rehg, J.M., Stone, W.L., (2017). Using a point-of-view camera to measure eye gaze in young children with autism spectrum disorder during naturalistic social interactions: A pilot study. Journal of Autism and Developmental Disorders.
  • Jones, R.M., *Southerland, A., *Hamo, A., *Carberry, C., *Bridges, C., *Nay, S., *Stubbs, E., Komarow, E., *Washington, C., Rehg, J.M., Lord, C., & Rozga, A., (2016). Increased eye contact during conversation compared to play in children with autism. Journal of Autism and Developmental Disorders. 
  • *Tsatsoulis, D.P., *Kordas, P., Marshall, M., Forsyth, D., & Rozga, A. (2016). The Static Multimodal Dyadic Behavior Dataset for Engagement Prediction. Proceedings of the European Conference on Computer Vision (ECCV 2016), pp.386-399. 
  • Kunda, M., Soulieres, I., Rozga, A., & Goel, A. (2016). Error Patterns on the Raven's Standard Progressive Matrices Test. Intelligence, 59, 181-198. 
  • Smith, C., Rozga, A., Matthews, N., Oberleitner, R., Nazneen, N., & Abowd, G. (2016). Investigating the accuracy of novel telehealth diagnostic approach for Autism Spectrum Disorder. Psychological Assessment. 
-
  • Looking forward to presenting my work as part of the Society for Research in Child Development Paper Symposium "A closer look at infant eye gaze: exploring ecological influences on attention dynamics in typical and atypical development." See you in Austin in April of 2017!
  • Work on "Using objective measurements of movement and vocalization data to predict attachment behavior," in collaboration with the University of Miami, will be presented in a poster at the SRCD Biennial Meeting in April 2017.
  • Dec 2016: Along with colleagues Nathan Call & Thomas Ploetz, I was awarded an NIH grant titled Objective Measurement of Challenging Behaviors in Individuals with ASD. This is a true computational behavioral science endeavor, combining on-body sensing and computational analysis with a clinically-grounded conceptual framework.
  • Poster presented at the 2016 International Congress on Infant Studies on predicting expert ratings of attachment from automated acoustic analysis of infant vocalizations:
    • Prince, E., Warlaumont, A., Oller, D.K., Chow, S., Rozga, A., Ciptadi, C., Rehg, J.M, & Messinger, D. “Strange Situation Vocalizations Differ Between Secure and Insecure-Resistant Infants.”  

Get in touch with me

agata at gatech dot edu

Georgia Institute of Technology
School of Interactive Computing
85 5th Street NW
Atlanta, GA 30308

My office: Technology Square Research Building Rm.219
Office Phone # 404-894-2304