Location Estimation in a Smart Home: System Implementation and Evaluation Using Experimental Data

摘要

In the context of a constantly increasing aging population withcognitive deficiencies, insuring the autonomy of the elders athome becomes a priority. The DOMUS laboratory is addressingthis issue by conceiving a smart home which can both assistpeople and preserve their quality of life. Obviously, the ability tomonitor properly the occupant’s activities and thus provide thepertinent assistance depends highly on location information insidethe smart home. This paper proposes a solution to localize theoccupant thanks to Bayesian filtering and a set of anonymoussensors disseminated throughout the house. The localizationsystem is designed for a single person inside the house. It couldhowever be used in conjunction with other localization systemsin case more people are present. Our solution is functional in realconditions. We conceived an experiment to estimate precisely itsaccuracy and evaluate its robustness. The experiment consistsof a scenario of daily routine meant to maximize the occupant’smotion in meaningful activities. It was performed by 14 subjects,one subject at a time. The results are satisfactory: the system’saccuracy exceeds 85% and is independent of the occupant’sprofile. The system works in real time and behaves well inpresence of noise.