Constellation, le dépôt institutionnel de l'Université du Québec à Chicoutimi

Résumé

Bluetooth Low Energy emitters used as beacons have gained a lot of traction in the last few years. The technology is continuously improving and it is now possible for consumers to buy highly durable beacons for a reasonable price. The main use of these beacons is to be harnessed by context-aware software, as such, applications requiring localization can benefit from beacon technology. However, the reliability and accuracy of the location information is rather crucial when used for ambient intelligence in healthcare domain. Most systems currently rely only on received signal strength indication (RSSI) that may not be highly reliable in that they are highly susceptible to diffraction, multipath propagation, angle-of-arrival, lack of line-of-sight and absorption by human body. In this paper, we propose to investigate the use of two features in addition to mean RSSI. The new algorithm presented in the paper improve the localization accuracy from 6.2% to 9.14% over simple proximity localization.