A Sorting Method of SAR Emitter Signal Sorting Based on Self-Supervised Clustering
Most existing methods for sorting synthetic aperture radar (SAR) emitter signals rely on either unsupervised clustering or supervised classification methods. However, unsupervised clustering can consume a significant amount of computational and storage space and is sensitive to the setting of hyperp...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/7/1867 |
| _version_ | 1797607149533134848 |
|---|---|
| author | Dahai Dai Guanyu Qiao Caikun Zhang Runkun Tian Shunjie Zhang |
| author_facet | Dahai Dai Guanyu Qiao Caikun Zhang Runkun Tian Shunjie Zhang |
| author_sort | Dahai Dai |
| collection | DOAJ |
| description | Most existing methods for sorting synthetic aperture radar (SAR) emitter signals rely on either unsupervised clustering or supervised classification methods. However, unsupervised clustering can consume a significant amount of computational and storage space and is sensitive to the setting of hyperparameters, while supervised classification requires a considerable number of labeled samples. To address these limitations, we propose a self-supervised clustering-based method for sorting SAR radiation source signals. The method uses a constructed affinity propagation-convolutional neural network (AP-CNN) to perform self-supervised clustering of a large number of unlabeled signal time-frequency images into multiple clusters in the first stage. Subsequently, it uses a self-organizing map (SOM) network combined with inter-pulse parameters for further sorting in the second stage. The simulation results demonstrate that the proposed method outperforms other depth models and conventional methods in the environment where Gaussian white noise affects the signal. The experiments conducted using measured data also show the superiority of the proposed method in this paper. |
| first_indexed | 2024-03-11T05:26:10Z |
| format | Article |
| id | doaj.art-c8f61583d99e4fb4a486320d82e61f4d |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T05:26:10Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c8f61583d99e4fb4a486320d82e61f4d2023-11-17T17:30:07ZengMDPI AGRemote Sensing2072-42922023-03-01157186710.3390/rs15071867A Sorting Method of SAR Emitter Signal Sorting Based on Self-Supervised ClusteringDahai Dai0Guanyu Qiao1Caikun Zhang2Runkun Tian3Shunjie Zhang4College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of Complex Electromagnetic Environmental Effects on Electronics and Information Systems, Luoyang 471003, ChinaState Key Laboratory of Complex Electromagnetic Environmental Effects on Electronics and Information Systems, Luoyang 471003, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaMost existing methods for sorting synthetic aperture radar (SAR) emitter signals rely on either unsupervised clustering or supervised classification methods. However, unsupervised clustering can consume a significant amount of computational and storage space and is sensitive to the setting of hyperparameters, while supervised classification requires a considerable number of labeled samples. To address these limitations, we propose a self-supervised clustering-based method for sorting SAR radiation source signals. The method uses a constructed affinity propagation-convolutional neural network (AP-CNN) to perform self-supervised clustering of a large number of unlabeled signal time-frequency images into multiple clusters in the first stage. Subsequently, it uses a self-organizing map (SOM) network combined with inter-pulse parameters for further sorting in the second stage. The simulation results demonstrate that the proposed method outperforms other depth models and conventional methods in the environment where Gaussian white noise affects the signal. The experiments conducted using measured data also show the superiority of the proposed method in this paper.https://www.mdpi.com/2072-4292/15/7/1867synthetic aperture radar (SAR)radar signal sortingself-supervised clusteringself-organizing map (SOM) |
| spellingShingle | Dahai Dai Guanyu Qiao Caikun Zhang Runkun Tian Shunjie Zhang A Sorting Method of SAR Emitter Signal Sorting Based on Self-Supervised Clustering Remote Sensing synthetic aperture radar (SAR) radar signal sorting self-supervised clustering self-organizing map (SOM) |
| title | A Sorting Method of SAR Emitter Signal Sorting Based on Self-Supervised Clustering |
| title_full | A Sorting Method of SAR Emitter Signal Sorting Based on Self-Supervised Clustering |
| title_fullStr | A Sorting Method of SAR Emitter Signal Sorting Based on Self-Supervised Clustering |
| title_full_unstemmed | A Sorting Method of SAR Emitter Signal Sorting Based on Self-Supervised Clustering |
| title_short | A Sorting Method of SAR Emitter Signal Sorting Based on Self-Supervised Clustering |
| title_sort | sorting method of sar emitter signal sorting based on self supervised clustering |
| topic | synthetic aperture radar (SAR) radar signal sorting self-supervised clustering self-organizing map (SOM) |
| url | https://www.mdpi.com/2072-4292/15/7/1867 |
| work_keys_str_mv | AT dahaidai asortingmethodofsaremittersignalsortingbasedonselfsupervisedclustering AT guanyuqiao asortingmethodofsaremittersignalsortingbasedonselfsupervisedclustering AT caikunzhang asortingmethodofsaremittersignalsortingbasedonselfsupervisedclustering AT runkuntian asortingmethodofsaremittersignalsortingbasedonselfsupervisedclustering AT shunjiezhang asortingmethodofsaremittersignalsortingbasedonselfsupervisedclustering AT dahaidai sortingmethodofsaremittersignalsortingbasedonselfsupervisedclustering AT guanyuqiao sortingmethodofsaremittersignalsortingbasedonselfsupervisedclustering AT caikunzhang sortingmethodofsaremittersignalsortingbasedonselfsupervisedclustering AT runkuntian sortingmethodofsaremittersignalsortingbasedonselfsupervisedclustering AT shunjiezhang sortingmethodofsaremittersignalsortingbasedonselfsupervisedclustering |