DocumentCode :
1447185
Title :
Principal Component Localization in Indoor WLAN Environments
Author :
Fang, Shih-Hau ; Lin, Tsung-Nan
Author_Institution :
Dept. of Electr. Eng., Yuan Ze Univ., Taoyuan, Taiwan
Volume :
11
Issue :
1
fYear :
2012
Firstpage :
100
Lastpage :
110
Abstract :
This paper presents a novel approach to building a WLAN-based location fingerprinting system. Our algorithm intelligently transforms received signal strength (RSS) into principal components (PCs) such that the information of all access points (APs) is more efficiently utilized. Instead of selecting APs, the proposed technique replaces the elements with a subset of PCs to simultaneously improve the accuracy and reduce the online computation. Our experiments are conducted in a realistic WLAN environment. The results show that the mean error is reduced by 33.75 percent, and the complexity by 40 percent, as compared to the existing methods. Moreover, several benefits of our algorithm are demonstrated, such as requiring fewer training samples and enhancing the robustness to RSS anomalies.
Keywords :
indoor communication; wireless LAN; RSS anomaly; WLAN-based location fingerprinting system; indoor WLAN environment; online computation; principal component localization; realistic WLAN environment; received signal strength; Computer architecture; Fingerprint recognition; IEEE 802.11 Standards; Indoor radio communication; Principal component analysis; Probabilistic logic; Wireless LAN; WLAN; fingerprinting; indoor localization; principal component.; transformation;
fLanguage :
English
Journal_Title :
Mobile Computing, IEEE Transactions on
Publisher :
ieee
ISSN :
1536-1233
Type :
jour
DOI :
10.1109/TMC.2011.30
Filename :
5710948
Link To Document :
بازگشت