Radar signal recognition based on triplet convolutional neural network

Abstract Recently, due to the wide application of low probability of intercept (LPI) radar, lots of recognition approaches about LPI radar signal modulations have been proposed. However, facing the increasingly complex electromagnetic environment, most existing methods have poor performance to ident...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Lutao Liu, Xinyu Li
Formato: article
Lenguaje:EN
Publicado: SpringerOpen 2021
Materias:
Acceso en línea:https://doaj.org/article/08fe32933c9840a08fb85473ce86cd80
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:08fe32933c9840a08fb85473ce86cd80
record_format dspace
spelling oai:doaj.org-article:08fe32933c9840a08fb85473ce86cd802021-11-14T12:15:47ZRadar signal recognition based on triplet convolutional neural network10.1186/s13634-021-00821-81687-6180https://doaj.org/article/08fe32933c9840a08fb85473ce86cd802021-11-01T00:00:00Zhttps://doi.org/10.1186/s13634-021-00821-8https://doaj.org/toc/1687-6180Abstract Recently, due to the wide application of low probability of intercept (LPI) radar, lots of recognition approaches about LPI radar signal modulations have been proposed. However, facing the increasingly complex electromagnetic environment, most existing methods have poor performance to identify different modulation types in low signal-to-noise ratio (SNR). This paper proposes an automatic recognition method for different LPI radar signal modulations. Firstly, time-domain signals are converted to time-frequency images (TFIs) by smooth pseudo-Wigner–Ville distribution. Then, these TFIs are fed into a designed triplet convolutional neural network (TCNN) to obtain high-dimensional feature vectors. In essence, TCNN is a CNN network that triplet loss is adopted to optimize parameters of the network in the training process. The participation of triplet loss can ensure that the distance between samples in different classes is greater than that between samples with the same label, improving the discriminability of TCNN. Eventually, a fully connected neural network is employed as the classifier to recognize different modulation types. Simulation shows that the overall recognition success rate can achieve 94% at − 10 dB, which proves the proposed method has a strong discriminating capability for the recognition of different LPI radar signal modulations, even under low SNR.Lutao LiuXinyu LiSpringerOpenarticleLPI radar signal recognitionTriplet lossConvolutional neural networkDeep learningSmooth pseudo-Wigner–Ville distributionTelecommunicationTK5101-6720ElectronicsTK7800-8360ENEURASIP Journal on Advances in Signal Processing, Vol 2021, Iss 1, Pp 1-16 (2021)
institution DOAJ
collection DOAJ
language EN
topic LPI radar signal recognition
Triplet loss
Convolutional neural network
Deep learning
Smooth pseudo-Wigner–Ville distribution
Telecommunication
TK5101-6720
Electronics
TK7800-8360
spellingShingle LPI radar signal recognition
Triplet loss
Convolutional neural network
Deep learning
Smooth pseudo-Wigner–Ville distribution
Telecommunication
TK5101-6720
Electronics
TK7800-8360
Lutao Liu
Xinyu Li
Radar signal recognition based on triplet convolutional neural network
description Abstract Recently, due to the wide application of low probability of intercept (LPI) radar, lots of recognition approaches about LPI radar signal modulations have been proposed. However, facing the increasingly complex electromagnetic environment, most existing methods have poor performance to identify different modulation types in low signal-to-noise ratio (SNR). This paper proposes an automatic recognition method for different LPI radar signal modulations. Firstly, time-domain signals are converted to time-frequency images (TFIs) by smooth pseudo-Wigner–Ville distribution. Then, these TFIs are fed into a designed triplet convolutional neural network (TCNN) to obtain high-dimensional feature vectors. In essence, TCNN is a CNN network that triplet loss is adopted to optimize parameters of the network in the training process. The participation of triplet loss can ensure that the distance between samples in different classes is greater than that between samples with the same label, improving the discriminability of TCNN. Eventually, a fully connected neural network is employed as the classifier to recognize different modulation types. Simulation shows that the overall recognition success rate can achieve 94% at − 10 dB, which proves the proposed method has a strong discriminating capability for the recognition of different LPI radar signal modulations, even under low SNR.
format article
author Lutao Liu
Xinyu Li
author_facet Lutao Liu
Xinyu Li
author_sort Lutao Liu
title Radar signal recognition based on triplet convolutional neural network
title_short Radar signal recognition based on triplet convolutional neural network
title_full Radar signal recognition based on triplet convolutional neural network
title_fullStr Radar signal recognition based on triplet convolutional neural network
title_full_unstemmed Radar signal recognition based on triplet convolutional neural network
title_sort radar signal recognition based on triplet convolutional neural network
publisher SpringerOpen
publishDate 2021
url https://doaj.org/article/08fe32933c9840a08fb85473ce86cd80
work_keys_str_mv AT lutaoliu radarsignalrecognitionbasedontripletconvolutionalneuralnetwork
AT xinyuli radarsignalrecognitionbasedontripletconvolutionalneuralnetwork
_version_ 1718429329037197312