Radio frequency fingerprinting for outdoor user equipment localization
The recent advancements in cellular mobile technology and smart phone usage
have opened opportunities for researchers and commercial companies to
develop ubiquitous low cost localization systems. Radio frequency (RF)
fingerprinting is a popular positioning technique which uses radio signal
strength (RSS) values from already existing infrastructures to provide
satisfactory user positioning accuracy in indoor and densely built outdoor
urban areas where Global Navigation Satellite System (GNSS) signal is poor
and hard to reach. However a major requirement for the RF fingerprinting to
maintain good localization accuracy is the collection and updating of large
training database. The Minimization of Drive Tests (MDT) functionality
proposed by 3GPP LTE Release 10 & 11 has enabled cellular operators to
autonomously gather and update necessary amount of RF fingerprint samples
by utilizing their subscriber user equipments (UEs). The main objective of this
thesis is to propose a framework for RF fingerprint positioning (RFFP) of
outdoor UEs using MDT data and to further improve its performance capability
to provide better localization. In the first part only LTE base-station (BS) RSS
values were used to improve grid-based RF fingerprint positioning (G-RFFP) by
using novel approaches: using overlapped grid-cell layouts (GCL), weighting
based grid-cell unit selection and Artificial Intelligence based G-RFFP method.
In the second part real measurement RSS values from LTE BS and WLAN
access points (APs) were utilized and a generic measurement method referred
to as GMDT was proposed to correlate WLAN RSS to LTE RSS measurements
and its significance to RFFP was studied using a partial fingerprint matching
technique. To remove the computational cost associated with training data
preprocessing a new cluster-based RF fingerprint positioning (C-RFFP) method
was proposed. This thesis provides a good source of information and novel
techniques for cellular operators to build a low cost RF fingerprint positioning
system which can deliver acceptable results in emergency user localization
...


Publisher
University of JyväskyläISBN
978-951-39-7285-1ISSN Search the Publication Forum
1456-5390Keywords
Metadata
Show full item recordCollections
- Väitöskirjat [3224]
Related items
Showing items with similar title or keywords.
-
Cluster-Based RF Fingerprint Positioning Using LTE and WLAN Outdoor Signals
Mondal, Riaz; Ristaniemi, Tapani; Turkka, Jussi (IEEE, 2015)In this paper we evaluate user-equipment (UE) positioning performance of three cluster-based RF fingerprinting methods using LTE and WLAN signals. Real-life LTE and WLAN data were collected for the evaluation purpose ... -
RF fingerprinting for user locationing in LTE/WLAN networks
Khandker, Syed Ibrahim (2016)Location based applications and services have become popular in many wireless communication devices. This thesis study presents a performance evaluation of Radio Frequency (RF) fingerprinting framework in heterogeneous ... -
On data mining applications in mobile networking and network security
Zolotukhin, Mikhail (University of Jyväskylä, 2014) -
Langattomien sensoriverkkoteknologioiden soveltaminen älykodissa : muistisairaan paikantaminen
Silvennoinen, Mika (2019)Työssä esitellään älykotiratkaisuja lähinnä terveydenhuollon näkökulmasta. Lisäksi läpikäydään älykotien langattomaan tiedonsiirtoon liittyviä teknologioita. Empiirisessä osuudessa selvitetään muistisairaan vanhuksen ... -
Yleisötapahtumien tietoliikenneratkaisut
Tirronen, Roope (2023)Tässä tutkielmassa selvitetään, millaisilla ratkaisuilla saadaan langattomat verkot toimimaan paremmin yleisötapahtumissa tai ylipäätään tilanteissa, joissa usea käyttäjä pyrkii pienellä alueella käyttämään langattomia verkkoja.