Monitoring Health by Detecting Drifts and Outliers for a Smart Environment Inhabitant 1

To many people, home is a sanctuary. For those people who need sp cial medical care, they may need to be pulled out of their home to meet th ir medical needs. As the population ages, the percentage of people in th is group is increasing and the effects are expensive as well as unsatisfying. We hyp ot esize that many people with disabilities can lead independent lives in thei r own homes with the aid of at-home automated assistance and health monitoring. In o rder to accomplish this, robust methods must be developed to collect relevant dat a and process it to detect and/or predict threatening long-term trends or immedi at crises. The main objective of this work is to design techniques for usi ng agent-based smart home technologies to provide this at-home health monitori g and assistance. Specifically, we address the following technologica l ch llenges: 1) identifying lifestyle trends, 2) detecting anomalies in current da ta, nd 3) designing a reminder assistance system. We discuss one such smart environme nt implementation in the MavHome project and present results from testing t hese techniques in simulation and with a volunteer in an apartment setting.