University of Birmingham
A fuzzy logic approach to localisation in wireless local area networks
Abstract
dc:description.abstractThis thesis examines the use and value of fuzzy sets, fuzzy logic and fuzzy inference in wireless positioning systems and solutions. Various fuzzy-related techniques and methodologies are reviewed and investigated, including a comprehensive review of fuzzy-based positioning and localisation systems. The thesis is aimed at the development of a novel positioning technique which enhances well-known multi-nearest-neighbour (kNN) and fingerprinting algorithms with received signal strength (RSS) measurements. A fuzzy inference system is put forward for the generation of weightings for selected nearest-neighbours and the elimination of outliers. In this study, Monte Carlo simulations of a proposed multivariable fuzzy localisation (MVFL) system showed a significant improvement in the root mean square error (RMSE) in position estimation, compared with well-known localisation algorithms. The simulation outcomes were confirmed empirically in laboratory tests under various scenarios. The proposed technique uses available indoor wireless local area network (WLAN) infrastructure and requires no additional hardware or modification to the network, nor any active user participation. The thesis aims to benefit practitioners and academic researchers of system positioning.
Degree
thesis:*- Name dc:type.qualificationname
- d_ph
- Level dc:type.qualificationlevel
- d_ph
- Grantor dc:publisher.institution
- University of Birmingham
- Year dc:date.issued
- 2020
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Alakhras, Marwan
- ORCID person:identifier.orcid
Subjects
dc:subject × 8Rights
- Language dc:language.dcterms_iso639_2
- eng