Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/69936
Title: Featured-based room-level localization of unmodified smartphones
Authors: Shen, J
Cao, J 
Liu, X
Wen, J
Chen, Y
Keywords: Room-level localization
RSS
Fingerprinting
Issue Date: 2016
Publisher: springer
Source: Lecture notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, 2016, v. 166, p. 125-136 How to cite?
Journal: Lecture notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering 
Abstract: Locating smartphone users will enable numerous potential applications such as monitoring customers in shopping malls. However, conventional received signal strength (RSS)-based room-level localization methods are not likely to distinguish neighboring zones accurately due to similar RSS fingerprints. We solve this problem by proposing a system called feature-based room-level localization (FRL). FRL is based on an observation that different rooms vary in internal structures and human activities which can be reflected by RSS fluctuation ranges and user dwell time respectively. These two features combing with RSS can be exploited to improve the localization accuracy. To enable localization of unmodified smartphones, FRL utilizes probe requests, which are periodically broadcast by smartphones to discover nearby access points (APs). Experiments indicate that FRL can reliably locate users in neighboring zones and achieve a 10 % accuracy gain, compared with conventional methods like the histogram method.
Description: 1st EAI International Summit, Smart City 360°, Slovakia and Toronto, Canada, October 13-16, 2015
URI: http://hdl.handle.net/10397/69936
ISBN: 978-3-319-33680-0
978-3-319-33681-7
ISSN: 1867-8211
DOI: 10.1007/978-3-319-33681-7_11
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

2
Citations as of Nov 19, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.