In-Home Monitoring
Tracking Multi-person Activity in the Home
Funded By Oregon Partnership for Alzheimer's Research and the National Institute on Aging
One long-term objective of our research is to develop intelligent systems for assessing cognitive change over time. Towards this end, we have developed a system for unobtrusive, continuous, in-home assessment of motor activity and walking speed which is based on wireless motion sensor technology [1,2]. This system has thus far been deployed in the homes of 61 elderly subjects living alone in the community. However, our current system can be used only in single-person homes. The objective of this study is to extend our methods to monitor multiple individuals residing in the same home.
The Specific Aims of this study are:
- To determine the optimal placement and parameters of location tracking devices
for use in a continuous in-home assessment system. Due to the nature of the
unobtrusive sensors used in our monitoring system, frequent movement by two
individuals in the same room results in activity counts that are similar to those
registered by frequent movements of a single person in that room. Therefore, a key
issue in monitoring multiple individuals is determining their location at any given
time. There are a number of emerging technologies that may be used to identify a
individual's location within a home (e.g. RFID, 802.11b/g).
However, these systems were not designed for
use in a continuous in-home assessment system. In Specific Aim 1 we will
characterize the performance of these technologies in order to optimize their
configuration and deployment for use in our in-home assessment system.
- To develop novel algorithms for separating the activity data of two individuals in the same home, through fusion of data from multiple sensor types. Current technologies for tracking location information require an individual to wear a tracking device such as an RFID badge. It is well-established that most individuals will reliably wear such a device only some of the time [3-5]. We propose to develop a model-based algorithm to track the continuous location of individuals over time using the data from our core system, by training the system using information from body-worn location devices collected over a short period of time (2 weeks).
Point of Care Lab ready for location testing.
1) Hayes, T.L., M. Pavel, and J.A. Kaye.
An Unobtrusive In-home Monitoring System for Detection of Key Motor Changes Preceding Cognitive Decline.
in 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2003. San Francisco, CA: IEEE.
2) Hayes, T., et al. Unobtrusive Monitoring of Health Status in an Aging Population. in 5th International Conference on Ubiquitous Computing. 2003. Seattle, Washington.
3) Warms, C.A. and B.L. Belza, Actigraphy as a measure of physical activity for wheelchair users with spinal cord injury. Nurs Res, 2004. 53(2): p. 136-43.
4) Mathie, M.J., et al., A pilot study of long-term monitoring of human movements in the home using accelerometry. J Telemed Telecare, 2004. 10(3): p. 144-51.
5) Kochersberger, G., et al., The reliability, validity, and stability of a measure of physical activity in the elderly. Arch Phys Med Rehabil, 1996. 77(8): p. 793-5.
2) Hayes, T., et al. Unobtrusive Monitoring of Health Status in an Aging Population. in 5th International Conference on Ubiquitous Computing. 2003. Seattle, Washington.
3) Warms, C.A. and B.L. Belza, Actigraphy as a measure of physical activity for wheelchair users with spinal cord injury. Nurs Res, 2004. 53(2): p. 136-43.
4) Mathie, M.J., et al., A pilot study of long-term monitoring of human movements in the home using accelerometry. J Telemed Telecare, 2004. 10(3): p. 144-51.
5) Kochersberger, G., et al., The reliability, validity, and stability of a measure of physical activity in the elderly. Arch Phys Med Rehabil, 1996. 77(8): p. 793-5.