Cargando…
A Complex-Valued Self-Supervised Learning-Based Method for Specific Emitter Identification
Specific emitter identification (SEI) refers to distinguishing emitters using individual features extracted from wireless signals. The current SEI methods have proven to be accurate in tackling large labeled data sets at a high signal-to-noise ratio (SNR). However, their performance declines dramati...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9318124/ https://www.ncbi.nlm.nih.gov/pubmed/35885074 http://dx.doi.org/10.3390/e24070851 |
_version_ | 1784755214454095872 |
---|---|
author | Zhao, Dongxing Yang, Junan Liu, Hui Huang, Keju |
author_facet | Zhao, Dongxing Yang, Junan Liu, Hui Huang, Keju |
author_sort | Zhao, Dongxing |
collection | PubMed |
description | Specific emitter identification (SEI) refers to distinguishing emitters using individual features extracted from wireless signals. The current SEI methods have proven to be accurate in tackling large labeled data sets at a high signal-to-noise ratio (SNR). However, their performance declines dramatically in the presence of small samples and a significant noise environment. To address this issue, we propose a complex self-supervised learning scheme to fully exploit the unlabeled samples, comprised of a pretext task adopting the contrastive learning concept and a downstream task. In the former task, we design an optimized data augmentation method based on communication signals to serve the contrastive conception. Then, we embed a complex-valued network in the learning to improve the robustness to noise. The proposed scheme demonstrates the generality of handling the small and sufficient samples cases across a wide range from 10 to 400 being labeled in each group. The experiment also shows a promising accuracy and robustness where the recognition results increase at 10–16% from 10–15 SNR. |
format | Online Article Text |
id | pubmed-9318124 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-93181242022-07-27 A Complex-Valued Self-Supervised Learning-Based Method for Specific Emitter Identification Zhao, Dongxing Yang, Junan Liu, Hui Huang, Keju Entropy (Basel) Article Specific emitter identification (SEI) refers to distinguishing emitters using individual features extracted from wireless signals. The current SEI methods have proven to be accurate in tackling large labeled data sets at a high signal-to-noise ratio (SNR). However, their performance declines dramatically in the presence of small samples and a significant noise environment. To address this issue, we propose a complex self-supervised learning scheme to fully exploit the unlabeled samples, comprised of a pretext task adopting the contrastive learning concept and a downstream task. In the former task, we design an optimized data augmentation method based on communication signals to serve the contrastive conception. Then, we embed a complex-valued network in the learning to improve the robustness to noise. The proposed scheme demonstrates the generality of handling the small and sufficient samples cases across a wide range from 10 to 400 being labeled in each group. The experiment also shows a promising accuracy and robustness where the recognition results increase at 10–16% from 10–15 SNR. MDPI 2022-06-21 /pmc/articles/PMC9318124/ /pubmed/35885074 http://dx.doi.org/10.3390/e24070851 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Zhao, Dongxing Yang, Junan Liu, Hui Huang, Keju A Complex-Valued Self-Supervised Learning-Based Method for Specific Emitter Identification |
title | A Complex-Valued Self-Supervised Learning-Based Method for Specific Emitter Identification |
title_full | A Complex-Valued Self-Supervised Learning-Based Method for Specific Emitter Identification |
title_fullStr | A Complex-Valued Self-Supervised Learning-Based Method for Specific Emitter Identification |
title_full_unstemmed | A Complex-Valued Self-Supervised Learning-Based Method for Specific Emitter Identification |
title_short | A Complex-Valued Self-Supervised Learning-Based Method for Specific Emitter Identification |
title_sort | complex-valued self-supervised learning-based method for specific emitter identification |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9318124/ https://www.ncbi.nlm.nih.gov/pubmed/35885074 http://dx.doi.org/10.3390/e24070851 |
work_keys_str_mv | AT zhaodongxing acomplexvaluedselfsupervisedlearningbasedmethodforspecificemitteridentification AT yangjunan acomplexvaluedselfsupervisedlearningbasedmethodforspecificemitteridentification AT liuhui acomplexvaluedselfsupervisedlearningbasedmethodforspecificemitteridentification AT huangkeju acomplexvaluedselfsupervisedlearningbasedmethodforspecificemitteridentification AT zhaodongxing complexvaluedselfsupervisedlearningbasedmethodforspecificemitteridentification AT yangjunan complexvaluedselfsupervisedlearningbasedmethodforspecificemitteridentification AT liuhui complexvaluedselfsupervisedlearningbasedmethodforspecificemitteridentification AT huangkeju complexvaluedselfsupervisedlearningbasedmethodforspecificemitteridentification |