Identification of legacy radios in a cognitive radio network using a radio frequency fingerprinting based method

Nansai Hu, Yu Dong Yao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

22 Scopus citations

Abstract

Cognitive radio (CR) networks provide an open architecture for effectively utilizing communication resources through flexible opportunistic spectrum access methods. To successfully realize its benefits and minimize the misuses of a CR network, distinguishing radio/user classes (legacy radios/users versus secondary radios/users) and individual radio/user terminals (within one class/type) is a critical and challenging task in CR network operation. In this paper, we propose a radio frequency fingerprinting (RFF) based approach combined with machine learning algorithms to differentiate radio/user classes and terminals. In our experiments, the proposed method is implemented for distinguishing radio class (MOTOROLA walkie talkies (as legacy radios) versus Universal Software Radio Peripheral (USRP) (as secondary radios)) and distinguishing individual radio terminals within one radio class. The experimental results demonstrate that the proposed method is very effective in differentiating radio types and radio terminals.

Original languageEnglish
Title of host publication2012 IEEE International Conference on Communications, ICC 2012
Pages1597-1602
Number of pages6
DOIs
StatePublished - 2012
Event2012 IEEE International Conference on Communications, ICC 2012 - Ottawa, ON, Canada
Duration: 10 Jun 201215 Jun 2012

Publication series

NameIEEE International Conference on Communications
ISSN (Print)1550-3607

Conference

Conference2012 IEEE International Conference on Communications, ICC 2012
Country/TerritoryCanada
CityOttawa, ON
Period10/06/1215/06/12

Keywords

  • Cognitive radio
  • machine learning
  • radio frequency fingerprinting

Fingerprint

Dive into the research topics of 'Identification of legacy radios in a cognitive radio network using a radio frequency fingerprinting based method'. Together they form a unique fingerprint.

Cite this