Automatic collection, analysis, access, and archiving of individual and group psycho-social behavior

ABSTRACT

CareMedia is a collaborative effort that to date has captured more than 13,000 hours of video and audio recordings of life in the shared spaces of a nursing home dementia unit, by using 23 ceiling-mounted cameras, 24 hours a day for 25 days, ensuring an un-occluded view of every point in the recorded space. Computer machine learning techniques are being applied to the resulting 25 Terabytes of data, automatically processing the record for efficient use by analytical observers (e.g., social and behavioral scientists, geriatricians, and healthcare policy makers) to monitor and understand residents' well-being, and enhance their quality of life. This truly interdisciplinary effort bridges the psychological, social and behavioral sciences, and clinical medicine with multiple engineering and computer science disciplines to establish a clinical evidence base to guide rational therapeutics, an elusive goal ardently articulated by the Institute of Medicine. This paper discusses early foundation work being conducted with the data.

References

1. Moak, G., and Borson, S. Mental Health Services in Long-Term Care. American Journal of Geriatric Psychiatry, 8, 2000, 96--101.
2. Bharucha, A., Wactlar, H., Stevens, S., Chen, D., Atkeson, C., Dew, M., Pollock, B., and Reynolds, C. Preliminary Evaluation of Automatically Analyzed Video and Sensor Data for Geriatric Care, Annual Meeting of the American Medical Directors Association, Dallas, TX, March 17, 2006, http://www.informedia.cs.cmu.edu/pubs/abstract.asp?id=282.
3. Informedia Digital Video Understanding Research Group web site at Carnegie Mellon University (accessed Aug. 2006), http://www.informedia.cs.cmu.edu.
4. Christel, M. Accessing News Libraries through Dynamic Information Extraction, Summarization and Visualization. In LNCS 2539: Visual Interfaces to Digital Libraries, K. Börner and C. Chen, eds. Berlin: Springer-Verlag, January 2002, 98--115.
5. Chen, D., Yang, J., and Wactlar, H. A Study of Detecting Social Interaction with Sensors in a Nursing Home Environment. In LNCS 3766: Computer Vision in Human-Computer Interaction (ICCV 2005 Workshop on HCI), N. Sebe, M.S. Lew, and T.S. Huang, eds. Berlin: Springer-Verlag, October 2005, 199--210.
6. Chang, Y., Yan, R., Chen, D., and Yang, J. People Identification with Limited Labels in Privacy-Protected Video. In Proc. IEEE Intl. Conf. on Multimedia and Expo (ICME) (Toronto, Canada, July 2006), 1005--1008.
7. Bharucha, A., London, A., Barnard, D., Wactlar, H., Dew, M., and Reynolds III, C. Ethical Considerations in the Conduct of Electronic Surveillance Research. Journal of Law, Medicine & Ethics, in press.
8. U.S. General Accounting Office. Nursing Homes: Prevalence of Serious Quality Problems Remains Unacceptably High, Despite Some Decline (Washington, D.C.: U.S. General Accounting Office, 2003).

Index Terms

• Applied computing

  • Law, social and behavioral sciences

  • Life and medical sciences

• Information systems

  • Information retrieval

  • Information storage systems