Gå til hovedinnhold
0
Jump to main content

Machine Learning Tools for Radio Map Estimation in Fading-Impaired Channels

Yves Teganya of the Faculty of Engineering and Science at the University of Agder has submitted his thesis entitled “Machine Learning Tools for Radio Map Estimation in Fading-Impaired Channels“ and will defend the thesis for the PhD-degree Friday 13 November 2020. (Photo: Private)

Extensive experiments carried out in realistic propagation environments to validate the proposed radio map estimators reveal that the resulting algorithms markedly outperform state-of-the-art alternatives.

Yves Teganya

PhD Candidate

The disputation will be held digitally, because of the Corona covid-19-situation. Spectators may follow the disputation digitally – link is available below.

 

Yves Teganya of the Faculty of Engineering and Science at the University of Agder has submitted his thesis entitled “Machine Learning Tools for Radio Map Estimation in Fading-Impaired Channels“ and will defend the thesis for the PhD-degree Friday 13 November 2020. 

He has followed the PhD Programme at the Faculty of Engineering and Science with Specialization in Information- and Communication Technology (ICT) at the University of Agder.

The research work has been performed at the WISENET Center, Department of ICT, UiA, and was funded by the Research Council of Norway through the FRIPRO TOPPFORSK grant and the IKTPLUSS grant (LUCAT).

Summary of the thesis by Yves Teganya:

Machine Learning Tools for Radio Map Estimation in Fading-Impaired Channels

In radio map estimation, the goal is to construct maps that provide the received signal strength at every frequency and spatial location of interest.

These maps are built using sensor measurements, and find numerous applications in wireless communications such as network planning or device-to-device (D2D) communications.

Recently, radio maps have been widely recognized as a key enabler for unmanned aerial vehicle (UAV) communications, because they allow autonomous UAVs to account for communication constraints when planning a mission.

In this PhD thesis, we develop machine learning algorithms to build these maps in propagation channels impaired by fading.

Frameworks

Specifically, two frameworks are proposed:

The first one, termed "location-free radio map estimation", relies on robust features of the localization signals rather than locations of the measurement sensors, which are not available in practice and cannot be accurately estimated due to multipath.

The second one builds upon the idea of learning propagation phenomena of electromagnetic waves such as reflection using a record of past measurements. 

Extensive experiments carried out in realistic propagation environments to validate the proposed radio map estimators reveal that the resulting algorithms markedly outperform state-of-the-art alternatives.

 

Disputation facts:

The trial lecture and the public defence will take place online, via the Zoom conferencing app (link below)

Director, Centre for Artificial Intelligence Research (CAIR), Professor Ole-Christoffer Granmo, Department of Information and Communication Technology, Faculty of Engineering and Science, will chair the disputation.

The trial lecture at 10:15 hours

Public defence at 12:15 hours

 

Given topic for trial lecture«mmWave communications for immersive media delivery

Thesis Title: "Machine Learning Tools for Radio Map Estimation in Fading-Impaired Channels"

Search for the thesis in AURA - Agder University Research Archive, a digital archive of scientific papers, theses and dissertations from the academic staff and students at the University of Agder.

The thesis is available here:

https://uia.brage.unit.no/uia-xmlui/handle/11250/2687236 

 PhD Thesis Yves Teganya - print

 

The CandidateYves Teganya (1986, Nyabihu, Rwanda) Bachelor of Science (BSc) in Electronic and Telecommunication Engineering, University of Rwanda - College of Science and Technology UR-CST (former KIST), Rwanda (2012). Master of Science (MSc) in Electronics/ Telecommunications from University of Gävle, Sweden (2016). Present position: PhD Candidate.

Opponents:

First opponent: Associate Professor Olav Tirkkonen, Aalto University, Finland

Second opponent: Associate Professor Suzan Bayhan, University of Twente, Zilverling, NL

Associate Professor Lei Jiao, Department of Information and Communication Technolog, University of Agder, is appointed as the administrator for the assessment commitee.

Supervisors were Associate Professor Daniel Romero (main superviosor) and Professor Baltasar Beferull-Lozano (co-supervisor)

 

What to do as an audience member:

The disputation is open to the public, but to follow the trial lecture and the public defence, which is transmitted via the Zoom conferencing app, you have to register as an audience member.

We ask audience members to join the virtual trial lecture at 10:05 at the earliest and the public defense at 12:05 at the earliest. After these times, you can leave and rejoin the meeting at any time. Further, we ask audience members to turn off their microphone and camera and keep them turned off throughout the event. You do this at the bottom left of the image when in Zoom. We recommend you use ‘Speaker view’. You select that at the top right corner of the video window when in Zoom.

Opponent ex auditorio:

The chair invites members of the public to pose questions ex auditorio in the introduction to the public defense, with deadlines. Questions can be submitted to the chair, Professor Ole-Christoffer Granmo, on e-mail ole.granmo@uia.no