LiU > IDA > Real-Time Systems Lab
ABOUT
MEMBERS
COOPERATION
PROJECTS
PUBLICATIONS
COURSES
OPEN POSITIONS
THESES
ALUMNI

Announcements

[16 May 2017] A bachelor student at RTSLAB was awarded the best thesis award from IDA - Tim Hultman. more ...

[12 May 2016] A master student at RTSLAB was awarded the best thesis award from IDA - Alexander Alesand. more ...

[12 May 2016] A bachelor student at RTSLAB was awarded the best thesis award from IDA - Mathias Almquist and Viktor Almquist. more ...

[25 May 2015] A master student at RTSLAB was awarded the best thesis award from IDA - Klervie Toczé. more ...

[26 May 2014] A bachelor student at RTSLAB was awarded the best thesis award from IDA - Simon Andersson. more ...

[31 May 2012] A masters student at RTSLAB was awarded the best thesis award from IDA - Ulf Magnusson. more ...

[27 February 2008] A masters student at RTSLAB was awarded the best thesis award from IDA - Johan Sigholm. more ...

[03 March 2004] A masters student at RTSLAB was awarded the best thesis award from IDA - Tobias Chyssler. more ...

[01 Jul 2003] For second year in a row a masters student at RTSLAB was awarded the best thesis award from SNART - Mehdi Amirijoo. more ...

Master Thesis - Past Projects - Abstract

Adaptive Indoor Localization System for Android Smartphones

ID: LIU-IDA/ERASMUS

Wireless indoor localization systems are now a major component of ubiquitous computing and attracted many efforts and research in the last decades. Several techniques have been proposed and experimented, but Received Signal Strength (RSS) based fingerprinting prevails as the most promising one. However, most of the solutions proposed require site-survey to scan and record signal strength with its corresponding location. Site-survey has a high cost in terms of time and resources, and is affected by inadequacy to environmental changes, limiting a worldwide propagation. Moreover, radio signals strength fluctuates over time and requires map to be continuously re-calibrated. In this thesis, we investigate a novel indoor localization system that addresses the data collection problem by progressively creating a radio-map with a limited interaction cost. This would provide high adaptability to spatiotemporal variations and a limited influence to devices characteristics. In this perspective, we defined an adaptive system for Android-based smartphones, applying the fingerprinting method to respond some of the major technical issues. Our solution proposes 1) a site-survey free system with semi-autonomous data collection, 2) to allow crowd-sourced fingerprint exchange among different devices without any calibration, 3) a limited human interaction. Through experimental analysis we evaluate our novel localization system. The results show that costly site-survey could be replaced by crowd-sourced data collection and the impact of environmental and material variations on collection of representative data is limited. These also confirm that an accurate indoor localization could be achieved with a reduced amount of interactions between user and system.

Keywords:

Author(s): Brieuc Viel

Contact: Mikael Asplund

Click here to return.
Last modified February 2017. If you have questions or suggestions for the webpages, contact the webmaster