Automatic modulation recognition of dual-component radar signals using ResSwinT-SwinT network
Automatic modulation recognition plays an important role in military and civilian applications, identifying the modulation format of received signals before signal demodulation. With the increasing complexity and density of the electromagnetic environment, the multi-component modulation radar signal...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/170687 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-170687 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1706872023-09-26T06:18:30Z Automatic modulation recognition of dual-component radar signals using ResSwinT-SwinT network Ren, Bing Teh, Kah Chan An, Hongyang Gunawan, Erry School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Automatic Modulation Recognition Dual-Component Radar Signals Automatic modulation recognition plays an important role in military and civilian applications, identifying the modulation format of received signals before signal demodulation. With the increasing complexity and density of the electromagnetic environment, the multi-component modulation radar signal recognition against various signal-to-noise ratio (SNR) conditions has become a practical and urgent problem. In this paper, we propose a dual-component modulation recognition framework, which incorporates the residual Swin transformer denoise network (ResSwinT), Swin transformer feature extraction network (SwinT), residual-attention (RA) modulation recognition head, and SNR level classifier and achieves robust recognition performance against various SNR conditions with tolerable complexity and accuracy trade-off. Firstly, the time-frequency analysis is employed to transform dual-component radar signals into time-frequency images (TFIs). Then, the TFIs at various SNR levels are applied to the SwinT, which generates shallow and deep feature representations for the SNR classifier and RA-modulation recognition head, respectively. The ResSwinT is initiated to reconstruct low SNR TFIs only, which are again processed by the SwinT. Finally, the RA-modulation recognition head provides modulation format predictions. The proposed framework can identify randomly combined dual-component radar signals from 12 modulation formats, meanwhile, improving the utilization of the SwinT feature and reducing unnecessary computation of the ResSwinT. Simulation results show that the proposed scheme can obtain an exact match ratio (EMR) of larger than 97% at SNR > −6dB. At low SNR condition (−12dB), the ResSwinT can obtain about EMR gain of 20% and the overall framework can achieve EMR of more than 80%, which outperforms other state-of-the-art methods and obtains better generalization capability. Nanyang Technological University This work was supported in part by the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, in part by the National Natural Science Foundation of China under Grant 62101096, and in part by the Postdoctoral Innovation Talent Support Program under Grant BX2021058. 2023-09-26T01:48:39Z 2023-09-26T01:48:39Z 2023 Journal Article Ren, B., Teh, K. C., An, H. & Gunawan, E. (2023). Automatic modulation recognition of dual-component radar signals using ResSwinT-SwinT network. IEEE Transactions On Aerospace and Electronic Systems, 1-13. https://dx.doi.org/10.1109/TAES.2023.3277430 0018-9251 https://hdl.handle.net/10356/170687 10.1109/TAES.2023.3277430 2-s2.0-85160241900 1 13 en IEEE Transactions on Aerospace and Electronic Systems © 2023 IEEE. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering Automatic Modulation Recognition Dual-Component Radar Signals |
spellingShingle |
Engineering::Electrical and electronic engineering Automatic Modulation Recognition Dual-Component Radar Signals Ren, Bing Teh, Kah Chan An, Hongyang Gunawan, Erry Automatic modulation recognition of dual-component radar signals using ResSwinT-SwinT network |
description |
Automatic modulation recognition plays an important role in military and civilian applications, identifying the modulation format of received signals before signal demodulation. With the increasing complexity and density of the electromagnetic environment, the multi-component modulation radar signal recognition against various signal-to-noise ratio (SNR) conditions has become a practical and urgent problem. In this paper, we propose a dual-component modulation recognition framework, which incorporates the residual Swin transformer denoise network (ResSwinT), Swin transformer feature extraction network (SwinT), residual-attention (RA) modulation recognition head, and SNR level classifier and achieves robust recognition performance against various SNR conditions with tolerable complexity and accuracy trade-off. Firstly, the time-frequency analysis is employed to transform dual-component radar signals into time-frequency images (TFIs). Then, the TFIs at various SNR levels are applied to the SwinT, which generates shallow and deep feature representations for the SNR classifier and RA-modulation recognition head, respectively. The ResSwinT is initiated to reconstruct low SNR TFIs only, which are again processed by the SwinT. Finally, the RA-modulation recognition head provides modulation format predictions. The proposed framework can identify randomly combined dual-component radar signals from 12 modulation formats, meanwhile, improving the utilization of the SwinT feature and reducing unnecessary computation of the ResSwinT.
Simulation results show that the proposed scheme can obtain an exact match ratio (EMR) of larger than 97% at SNR > −6dB. At low SNR condition (−12dB), the ResSwinT can obtain about EMR gain of 20% and the overall framework can achieve EMR of more than 80%, which outperforms other state-of-the-art methods and obtains better generalization capability. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Ren, Bing Teh, Kah Chan An, Hongyang Gunawan, Erry |
format |
Article |
author |
Ren, Bing Teh, Kah Chan An, Hongyang Gunawan, Erry |
author_sort |
Ren, Bing |
title |
Automatic modulation recognition of dual-component radar signals using ResSwinT-SwinT network |
title_short |
Automatic modulation recognition of dual-component radar signals using ResSwinT-SwinT network |
title_full |
Automatic modulation recognition of dual-component radar signals using ResSwinT-SwinT network |
title_fullStr |
Automatic modulation recognition of dual-component radar signals using ResSwinT-SwinT network |
title_full_unstemmed |
Automatic modulation recognition of dual-component radar signals using ResSwinT-SwinT network |
title_sort |
automatic modulation recognition of dual-component radar signals using resswint-swint network |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/170687 |
_version_ |
1779156308994293760 |