For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Multi-Floor Semantically Meaningful Localization Using IEEE 802.11 Network Beacons
Uzair AHMAD Brian J. D'AURIOL Young-Koo LEE Sungyoung LEE
IEICE TRANSACTIONS on Communications
Publication Date: 2008/11/01
Online ISSN: 1745-1345
Print ISSN: 0916-8516
Type of Manuscript: Special Section PAPER (Special Section on Emerging Technologies for Practical Ubiquitous and Sensor Networks)
positioning and ranging, pattern discovery and recognition, ubiquitous and mobile computing,
Full Text: PDF(1.5MB)>>
This paper presents a new methodology, Beacognition, for real-time discovery of the associations between a signal space and arbitrarily defined regions, termed as Semantically Meaningful Areas (SMAs), in the corresponding physical space. It lets the end users develop semantically meaningful location systems using standard 802.11 network beacons as they roam through their environment. The key idea is to discover the unique associations using a beacon popularity model. The popularity measurements are then used to localize the mobile devices. The beacon popularity is computed using an election' algorithm and a new recognition model is presented to perform the localization task. We have implemented such a location system in a five story campus building. The comparative results show significant improvement in localization by achieving on average 83% SMA and 88% Floor recognition rate in less than one minute per SMA training time.