CBA Lab @Georgia Tech

logo.png

address: CODA, 756 W Peachtree St NW, Atlanta, GA 30308

The Computational Behavior Analysis (CBA) lab at Georgia Tech is a Ubiquitous Computing and Applied Artificial Intelligence research group that develops, deploys, and studies methods and systems for the assessment of human behaviors that are based on physical movements and activities, and their contexts. Our primary application domain are health assessments and situated interventions to support people in their everyday lives. We utilize wearables, smart phones, and sensors integrated into the built environment and focus on inventing robust, secure, and usable machine learning methods for the analysis of multimodal sensor data streams thereby tackling challenging real-life scenarios.

selected publications

  1. ACM
    Imugpt 2.0: Language-based cross modality transfer for sensor-based human activity recognition
    Leng, Zikang, Bhattacharjee, Amitrajit, Rajasekhar, Hrudhai, Zhang, Lizhe, Bruda, Elizabeth, Kwon, Hyeokhyen, and Plötz, Thomas
    Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2024
  2. ISWC
    Generating Virtual On-Body Accelerometer Data from Virtual Textual Descriptions for Human Activity Recognition
    Leng, Zikang, Kwon, Hyeokhyen, and Ploetz, Thomas
    In Proceedings of the 2023 ACM International Symposium on Wearable Computers 2023
  3. Percom
    If only we had more data!: Sensor-Based Human Activity Recognition in Challenging Scenarios
    Plötz, Thomas
    In 2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops) 2023
  4. IMWUT
    Bootstrapping Human Activity Recognition Systems for Smart Homes from Scratch
    Hiremath, Shruthi K., Nishimura, Yasutaka, Chernova, Sonia, and Plötz, Thomas
    Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. Sep 2022
  5. IMWUT
    Assessing the State of Self-Supervised Human Activity Recognition Using Wearables
    Haresamudram, Harish, Essa, Irfan, and Plötz, Thomas
    Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. Sep 2022
  6. ACM
    Applying machine learning for sensor data analysis in interactive systems: Common pitfalls of pragmatic use and ways to avoid them
    PlĂ–tz, Thomas
    ACM Computing Surveys (CSUR) Sep 2021
  7. ACM
    IMUTube: Automatic extraction of virtual on-body accelerometry from video for human activity recognition
    Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies Sep 2020