Integrated Communications and Inference Systems for Continuous Coordinated Care of Older Adults in the Home



Duration: 2011-2015
Collaborators: Misha Pavel (Northeastern University), Holly Jimison (Northeastern University), Edmund Seto (Washington University), Paul Gorman (OHSU - Oregon Health Science University)
Funding:National Science Foundation (#1111965)

Goals:

  • Model behavior change of elderly during coaching intervention
  • Development of automated coaching platform based on Microsoft Kinect camera
  • Development of cognitive and physical models to predict effects of intervention



    Methods:
    Multi-sensor data collected at homes of elderly to obtain information on sleeping, physical activity, socialization etc.



    Applications:
    Remote health care management - individual-specific models will assist in administering effective intervention to improve extend independence of elderly population.


    Description:
    Millions of elderly people live alone and do not take proper care of their physical health. Wireless and other sensors in home can be used to observe cognitive behavior and physical activity. The problem we wish to solve is how design, model and analysis an integrated system based on scientific foundations that are composed of several environmental and body sensors coupled with cognitive games to observe, guide and intervene healthy elderly people who live alone. The intervention will be provided by a combination of automated computer based feedback and by a human health coach. In designing the system, provisions will be made to respect the privacy of the elderly person.

    In particular we are interested in observing and quantifying the levels of physical activity and model the effect of physical exercise on the cognitive levels of elderly individuals. We use cameras such as Microsoft Kinect to measure the human body kinematics and derive various features that quantify and summarize the performance of various exercises, which can either assist the coach or provide online feedback during the exercise.



    Videos:


    Publications:

  • Q. Wang, G. Kurillo, F. Ofli, R. Bajcsy, "Evaluation of pose tracking accuracy in the first and second generations of Microsoft Kinect" Proceedings of IEEE International Conference on Healthcare Informatics (ICHI), 2015.
  • G. Kurillo, F. Ofli, J. Marcoe, P. Gorman, H. Jimison, M. Pavel, R. Bajcsy, "Multi-disciplinary Design and In-home Evaluation of Kinect-Based Exercise Coaching System for Elderly", Human Aspects of IT for the Aged Population. Design for Everyday Life (Proceedings of HCI International 2015 Conference), Springer International Publishing, 2015, 9194, 101-113.
  • F. Ofli, G. Kurillo, S. Obdrzalek, R. Bajcsy, H. Jimison, M.Pavel, "Design and Evaluation of an Interactive Exercise Coaching System for Older Adults: Lessons Learned", IEEE Journal of Biomedical and Health Informatics, 2015. Accepted.
  • Š. Obdržálek, G. Kurillo, E. Seto, R. Bajcsy, "Architecture of an Automated Coaching System for Elderly Population", Stud Health Technol Inform. 2013;184:309-11 (Proceedings of MMVR 2013). [Poster]
  • Š. Obdržálek, G. Kurillo, F. Ofli, R. Bajcsy, E. Seto, H. Jimison, M. Pavel, "Accuracy and Robustness of Kinect Pose Estimation in the Context of Coaching of Elderly Population", EMBC, 34th International Conference of the IEEE Engineering in Medicine and Biology Society, San Diego, California, August 2012
  • S. Obdržálek, G. Kurillo, J. Han; T. Abresch, R. Bajcsy, "Real-time human pose detection and tracking for tele-rehabilitation in virtual reality," Stud Health Technol Inform 173, 320 (2012).