Investigation of Security and Spectrum Management Issues in Cognitive Radio Aided by Machine Learning

Slehat, Shaher Suleman Mousa

Investigation of Security and Spectrum Management Issues in Cognitive Radio Aided by Machine Learning

Slehat, Shaher Suleman Mousa

Permalink

Publication Type:: Thesis
Issue Date:: 2020

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download contents and abstractAdobe PDF (425.48 kB)

Adobe PDF

Download thesisAdobe PDF (20.76 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Slehat, Shaher Suleman Mousa
dc.date.accessioned	2020-04-24T00:50:36Z
dc.date.available	2020-04-24T00:50:36Z
dc.date.issued	2020
dc.identifier.uri	http://hdl.handle.net/10453/140244
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_AU
dc.description.abstract	Cognitive Radio (CR) is an intelligent and adaptive radio and network technology that allows transceivers to sense available frequency spectrum and change its parameters, to switch to available channels (frequency bands) without interruption to other connected transceivers. It is primarily a technology to resolve spectrum scarcity problems using Dynamic Spectrum Access (DSA). The potential aspects and applications of Cognitive radio are far superior to DSA alone. CR abilities and CR reconfiguration abilities are essential components for electronic warfare (communications). It provides capabilities for developing and deploying advanced anti-jamming methods, by assisting in the development of advanced intelligent, self-reconfiguration methods to alleviate the effects of jamming. This thesis examines the effects of jamming and other attacks on Cognitive Radio Networks and provides methods and processes to overcome those effects. Cognitive Radio architecture simulation was applied so that policies and their application correlate to Cognitive Radio jamming and anti-jamming issues. Simulation is employed for testing Multi-Armed Bandit and machine learning strategies/solutions as shown by this thesis. The central part of the thesis is the mitigation of jamming outcomes on Cognitive Radio Networks by using proactive steps to increase communication robustness and contentiousness. The thesis utilizes game theory (i.e. the Multi-Armed Bandit problem) and protection using Machine Learning (ProML) design for analysing jamming behavior on Cognitive Radio systems. MAB experiment show MAB approach is effective giants random attack, whereas, the proposed machine learning has its own merits to overcome constant and reactive jamming.	en_AU
dc.format	Thesis (PhD)
dc.language.iso	en_AU	en_AU
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/140244/2/02whole.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	au.edu.uts.lib/ppc
dc.title	Investigation of Security and Spectrum Management Issues in Cognitive Radio Aided by Machine Learning	en_AU
dc.type	Thesis	en_AU
utslib.copyright.status	open_access

Abstract:

Cognitive Radio (CR) is an intelligent and adaptive radio and network technology that allows transceivers to sense available frequency spectrum and change its parameters, to switch to available channels (frequency bands) without interruption to other connected transceivers. It is primarily a technology to resolve spectrum scarcity problems using Dynamic Spectrum Access (DSA). The potential aspects and applications of Cognitive radio are far superior to DSA alone. CR abilities and CR reconfiguration abilities are essential components for electronic warfare (communications). It provides capabilities for developing and deploying advanced anti-jamming methods, by assisting in the development of advanced intelligent, self-reconfiguration methods to alleviate the effects of jamming. This thesis examines the effects of jamming and other attacks on Cognitive Radio Networks and provides methods and processes to overcome those effects. Cognitive Radio architecture simulation was applied so that policies and their application correlate to Cognitive Radio jamming and anti-jamming issues. Simulation is employed for testing Multi-Armed Bandit and machine learning strategies/solutions as shown by this thesis. The central part of the thesis is the mitigation of jamming outcomes on Cognitive Radio Networks by using proactive steps to increase communication robustness and contentiousness. The thesis utilizes game theory (i.e. the Multi-Armed Bandit problem) and protection using Machine Learning (ProML) design for analysing jamming behavior on Cognitive Radio systems. MAB experiment show MAB approach is effective giants random attack, whereas, the proposed machine learning has its own merits to overcome constant and reactive jamming.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/140244