Creative Commons

This dissertation was written as a part of the MSc in ICT Systems at the International Hellenic University. It is based on the concept of fingerprinting which is used for positioning in wireless networks, primarily. Fingerprints can be generated using statistical information of the collected signal-strength measurements from various landmarks (e.g. Access Points). In particular, in the context of the algorithms for location-sensing systems, we implemented two simple algorithms, the Nearest Neighbor(s) in Signal Space algorithm – as described in RADAR system [5] – and the Percentiles method [8]. In order to obtain the respective simulation results, we have been provided with two datasets (training and runtime) with signal-strength values from known positions and an unknown position, respectively, from the Telecommunications and Networks Laboratory (TNL) at FORTH. At this point, I would like to sincerely thank Prof. Maria Papadopouli and Dr. George Koutitas for their guidance, instructions during this work as well as their significant support and patience. I would like also to mention that without the support and the continuous encouragement from my family and friends, as well, this project could not be achieved.