ADDRESSING DEPLOYMENT ISSUES IN WI-FI FINGERPRINT-BASED INDOOR LOCALIZATION

MPhil Thesis Defence


Title: "ADDRESSING DEPLOYMENT ISSUES IN WI-FI FINGERPRINT-BASED INDOOR 
LOCALIZATION"

By

Mr. Tianyang HU


Abstract

Wi-Fi fingerprint-based techniques for indoor localization have attracted 
extensive research interest in recent years. Various localization schemes 
have been proposed which produce decent accuracy. However, besides 
localization accuracy, several other issues need to be considered when 
deploying the system. In this thesis, we address three deployment issues 
in Wi-Fi fingerprint-based indoor localization: virtual access point 
(VAP), device calibration and localization error estimation. We propose a 
graph-based algorithm to identify and merge VAPs so as to remove redundant 
data and speed up localization. To make the system adapt to heterogeneous 
devices, we dynamically calibrate user-measured fingerprints through 
linear transformation in the online phase. We also estimate the 
localization error and provide a confidence range where the user is likely 
to be. We implement these functions as individual modules and integrate 
them into our existing system. Extensive experimental trials in Hong Kong 
International Airport and Hong Kong Olympian City show that our solutions 
to the three issues are satisfactory and they make the system more 
applicable and computationally- efficient.


Date:			Monday, 20 July 2015

Time:			2:00pm - 4:00pm

Venue:			Room 3494
 			Lifts 25/26

Committee Members:	Prof. Gary Chan (Supervisor)
 			Dr. Brahim Bensaou (Chairperson)
 			Dr. Raymond Wong


**** ALL are Welcome ****