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.
Collections
Show Collections