Indoor positioning and navigation

Updated March 2015
Interested to pursue a Master of Science by Research degree (validated by Lancaster University) or a PhD degree at Sunway University, investigating the below research topic? Email me at (replace -at- with @).

Today, indoor positioning, along with indoor navigation, is currently no longer impossible. Nevertheless, it is still an interesting and growing research area. I particularly am interested to explore various techniques that enable unsupervised approach to learn and build patterns, commonly known as fingerprints, that may lead to usable, or better still precise indoor positioning. Once we can successfully position a person in an indoor environment, more advanced services can be realised. One of them will be indoor navigation. Again, there are various techniques to enable navigation for indoor purposes too.

In the past years, together with my colleagues at University of Kassel, we explored unsupervised fingerprint building techniques based on existing WiFi access points information [1][2][3]. This approach has several advantages. Firstly, it will be an unobtrusive technique, where users are not required to actively provide information or input to help the construction of indoor position fingerprints. Secondly, by using existing WiFi access point infrastructure, which is by today's standard almost ubiquitous in many buildings, the total investment for successful indoor positioning and subsequent services can be minimized. Thirdly, we believe that unsupervised techniques may also be suitable to build incremental fingerprints that will improve as time goes.

Currently, I am interested to further improve the fingerprint construction algorithms well as to validate the positioning techniques in the wild. Once promising results can be reproduced, the techniques should be integrated into real applications where (friendly) users can use and evaluate the techniques. Beyond positioning, indoor positioning as a basic enabling technology will be used to provide further services such as navigation, crowd detection, personalized services etc.



[1]  S. L. Lau, Y. Xu, and K. David, "Novel Indoor Localisation using an Unsupervised Wi-Fi Signal Clustering Method," in Future Network and Mobile Summit 2011, Warsaw, Poland, Jun. 15-17 2011, pp. 1 - 8.

[2]  Y. Xu, S. L. Lau, R. Kusber, and K. David, "An experimental investigation of indoor localization by unsupervised Wi-Fi signal clustering," in Future Network and Mobile Summit 2012, Berlin, Germany, Jul. 4-6 2012, pp. 1 - 8.

[3]  Y. Xu, S. L. Lau, R. Kusber, and K. David, "DCCLA: Automatic Indoor Localization Using Unsupervised Wi-Fi Fingerprinting," in Modeling and Using Context, ser. Lecture Notes in Computer Science, P. Brzillon, P. Blackburn, and R. Dapoigny, Eds.    Springer Berlin Heidelberg, 2013, vol. 8175, pp. 73 - 86.

Add new comment

Filtered HTML

  • Web page addresses and e-mail addresses turn into links automatically.
  • Allowed HTML tags: <a> <em> <strong> <cite> <blockquote> <code> <ul> <ol> <li> <dl> <dt> <dd>
  • Lines and paragraphs break automatically.

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.