Title: A Comparison of Techniques for Radiometric Identification based on Deep Convolutional Neural Networks
Authors: BALDINI GIANMARCOGENTILE CLAUDIOGIULIANI RAIMONDOSTERI GARY
Citation: ELECTRONICS LETTERS vol. 55 no. 2 p. 90
Publisher: INST ENGINEERING TECHNOLOGY-IET
Publication Year: 2019
JRC N°: JRC113770
ISSN: 0013-5194 (online)
URI: https://digital-library.theiet.org/content/journals/10.1049/el.2018.6229
http://publications.jrc.ec.europa.eu/repository/handle/JRC113770
DOI: 10.1049/el.2018.6229
Type: Articles in periodicals and books
Abstract: We investigate the application of deep Convolutional Neural Networks (CNN) to the problem of Radiometric Identification (RAI), i.e., the task of authenticating wireless devices on the basis of their RF emissions, which contain features directly related to the physical properties of the wireless devices. We collected digitized Radio Frequency (RF) from 12 wireless devices, and used various techniques to transform the time series derived from the RF to images. A deep CNN is then applied to the images. Our results show that the identification performance of the combination of deep CNN with image representation significantly outperforms conventional methods based on dissimilarity on the original time series. Moreover, a specific comparison among RF-to-image techniques show that on our datasets the wavelet-based approach outperforms other approaches, also in the presence of white gaussian noise.
JRC Directorate:Space, Security and Migration

Files in This Item:
There are no files associated with this item.


Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.