• Two papers accepted to Ubicomp/ISWC 2020!

    read more
  • Best Student Paper Award at Learning@Scale 2020

    Congratulations to lead author Qiaosi (Chelsea) Wang and CBA co-authors Hong Li and Thomas Ploetz!

    read more
  • Daniel Scarafoni wins Outstanding Achievement in Robotic Orchestration at the UnixWorld Challenge!

    read more
  • Hyeok wins the consolation prize in the Emteq activity recognition challenge!

    read more
  • 6 papers accepted at Ubicomp/ISWC 2019!

    read more
  • CBA moves to CODA!

    Find us on the 15th floor! Plus, we have spectacular views!

    read more
  • ACII Keynote: "Quo Vadis, Computational Behavior Analysis?"

    read more

CBA Lab @GeorgiaTech

We are the Computational Behavior Analysis (CBA) research lab at Georgia Institute of Technology.

Our research agenda focuses on applied machine learning, that is developing systems and innovative sensor data analysis methods for real world applications. Primary application domain for our work is computational behavior analysis where we develop methods for automated and objective behavior assessments in naturalistic environments. Main driving functions for our work are “in the wild" deployments and as such the development of systems and methods that have a real impact on peoples’ lives.

Recent Publications:

IMUTube: Automatic Extraction of Virtual on-body Accelerometry from Video for Human Activity Recognition.

Hyeokhyen Kwon, Catherine Tong, Harish Haresamudram, Yan Gao, Gregory D. Abowd, Nicholas D. Lane, Plötz. Thomas

A Real-Time Eating Detection System for Capturing Eating Moments and Triggering Ecological Momentary Assessments to Obtain Further Context: System Development and Validation Study

Mehrab Bin Morshed, Samruddhi Shreeram Kulkarni, Richard Li, Koustuv Saha, Leah Galante Roper, Lama Nachman, Hong Lu, Lucia Mirabella, Sanjeev Srivastava, Munmun De Choudhury, Kaya de Barbaro, Thomas Ploetz, Gregory D Abowd

Masked reconstruction based self-supervision for human activity recognition

Harish Haresamudram, Apoorva Beedu, Varun Agrawal, Patrick L Grady, Irfan Essa, Judy Hoffman, Thomas Plötz

Estimation of Instantaneous Oxygen Uptake during Exercise and Daily Activities using a Wearable Cardio-Electromechanical and Environmental Sensor

Md Mobashir Hasan Shandhi, William H Bartlett, James Heller, Mozziyar Etemadi, Aaron Young, Thomas Ploetz, Omer Inan

IMUTube: Automatic extraction of virtual on-body accelerometry from video for human activity recognition

Hyeokhyen Kwon, Catherine Tong, Harish Haresamudram, Yan Gao, Gregory D Abowd, Nicholas D Lane, Thomas Ploetz

Deep learning-based automated speech detection as a marker of social functioning in late-life depression

Bethany Little, Ossama Alshabrawy, Daniel Stow, I Nicol Ferrier, Roisin McNaney, Daniel G Jackson, Karim Ladha, Cassim Ladha, Thomas Ploetz, Jaume Bacardit, Patrick Olivier, Peter Gallagher, John T O'Brien

Automated General Movement Assessment for Perinatal Stroke Screening in Infants

Yan Gao, Yang Long, Yu Guan, Anna Basu, Jessica Baggaley, Thomas Plötz

Recognition Of Atypical Behavior In Autism Diagnosis From Video Using Pose Estimation Over Time

Kathan Vyas, Rui Ma, Behnaz Rezaei, Shuangjun Liu, Michael Neubauer, Thomas Ploetz, Ronald Oberleitner, Sarah Ostadabbas

Sensing Affect to Empower Students: Learner Perspectives on Affect-Sensitive Technology in Large Educational Contexts

Q Wang, S Jing, D Joyner, L Wilcox, H Li, T Plötz, B DiSalvo


Our research is supported by grants from: