Emitter identification based on improved Variational modal decomposition at low SNR

Individual identification of radiation source is a technique based on extracting RF signal features. A new RF fingerprint extraction method is proposed for low SNR environment and low individual identification rate of radiation sources. The VMD algorithm is used to decompose the signal, and the auto...

Full description

Saved in:
Bibliographic Details
Published in2021 International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) pp. 152 - 156
Main Authors Li, QiuXue, Jin, YanHua, Yan, SongTao, Han, ShaoKang
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2021
Subjects
Automation
component
Feature extraction
Fingerprint recognition
Radio frequency
RF signals
RFF
Simulation
Source identification
Support vector machines
SVM
VMD
Online AccessGet full text

Cover

More Information
Summary:Individual identification of radiation source is a technique based on extracting RF signal features. A new RF fingerprint extraction method is proposed for low SNR environment and low individual identification rate of radiation sources. The VMD algorithm is used to decompose the signal, and the autocorrelation function is used to optimize it to strengthen the suppression of the modal aliasing phenomenon after the signal decomposition. The decomposed modes were analyzed by the Teager energy operator, and the energy and box dimension were extracted as fingerprint features, which were input into the support vector machine (SVM) for classification and recognition. The simulation results show the effectiveness of using VMD to extract fingerprint features under low SNR environment. And the proposed emitter identification scheme can improve the recognition rate of emitter in the environment with low signal-tonoise ratio (SNR) -5~0dB.
DOI:10.1109/AIEA53260.2021.00040