Please use this identifier to cite or link to this item:
|Title:||Transient-based Internet of Things emitter identification using Deep Convolutional Neural Networks and General linear chirplet transform|
|Authors:||BALDINI GIANMARCO; GENTILE CLAUDIO|
|Citation:||IEEE COMMUNICATIONS LETTERS vol. 24 no. 7 p. 1482-1486|
|Publisher:||IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC|
|Type:||Articles in periodicals and books|
|Abstract:||This letter investigates the application of the General Linear Chirplet Transform (GLCT), a time frequency representation recently proposed in the literature, in combination with Convolutional Neural Network (CNN) for the identification of Internet of Things Internet of Things (IOT) wireless devices. The identification is performed by analyzing the radio frequency emissions from the IOT devices during transmission. We apply the novel combination of CNN and GLCT (CNN-GLCT) to the transient portions of the radio frequency emissions by proposing an optimization procedure for GLCT which is specifically designed for emitter identification. Our empirical results show that this combination provides a superior identification performance as compared to other Deep CNN approaches available in the literature, as well as to approaches based on shallow machine learning methods, like SVM and KNN, especially under low Signal Noise Ratio (SNR) and fading conditions.|
|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.