Individual Identification of Radar Emitters Based on a One-Dimensional LeNet Neural Network

Specific emitter identification involves extracting the fingerprint features that represent the individual differences of the emitter through processing the received signals. By identifying the extracted fingerprint features, one can also identify the emitter to which the received signals belong. Du...

Full description

Saved in:
Bibliographic Details
Published in:Symmetry (Basel) 2021-07, Vol.13 (7), p.1215
Main Authors: Chen, Yue, Wu, Zi-Long, Lei, Ying-Ke
Format: Article
Language:English
Subjects:
bispectral characteristics
Communications networks
Decomposition
Emitters
empirical mode decomposition
Feature extraction
Fingerprints
LeNet neural network
Methods
Military communications
Neural networks
Noise
Parameter estimation
Power
Radar
Radiation
Radio signals
Receivers & amplifiers
Reduction
Signal processing
specific emitter identification
Spectrum analysis
Theft
Transmitters
Wavelet transforms
Wireless communications
Wireless networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Specific emitter identification involves extracting the fingerprint features that represent the individual differences of the emitter through processing the received signals. By identifying the extracted fingerprint features, one can also identify the emitter to which the received signals belong. Due to differences in transmitter hardware, this fingerprint cannot be duplicated. Therefore, SEI plays an important role in the field of information security and can reduce the information leakages caused by key theft. This method can also be used in the military field to support communication countermeasures via emitter individual identification. In this paper, empirical mode decomposition is carried out for each radar pulse signal, and then the bispectral features are extracted. Dimensionality reduction is carried out according to the symmetry of the bispectral features. The features after dimensionality reduction are input into a one-dimensional LeNet neural network as the fingerprint features of the emitter, and the identification of 10 radar emitter sources is completed. Based on the verification of real signals, the SEI identification strategy in this paper achieved a recognition rate of 96.4% for 10 radar signals, 98.9% for 10 data emitter signals, and 88.93% for 5 communication radio signals.
ISSN:2073-8994
2073-8994
DOI:10.3390/sym13071215