A semi-supervised transfer learning recognition method for radar compound jamming under small samples
Aiming at the problem that more and more kinds of radar compound jamming signals and too few training samples were difficult to make the deep learning model reach the optimal state, a semi-supervised transfer learning recognition method for radar compound jamming under small samples was proposed, wh...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2023-10-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023182/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530886215958528 |
|---|---|
| author | Jinqiang WANG Minhong SUN Xianghong TANG Zhaoyang QIU Deguo ZENG |
| author_facet | Jinqiang WANG Minhong SUN Xianghong TANG Zhaoyang QIU Deguo ZENG |
| author_sort | Jinqiang WANG |
| collection | DOAJ |
| description | Aiming at the problem that more and more kinds of radar compound jamming signals and too few training samples were difficult to make the deep learning model reach the optimal state, a semi-supervised transfer learning recognition method for radar compound jamming under small samples was proposed, which solved the problem of low network training accuracy caused by the difficulty in obtaining labeled samples through unlabeled samples.The feature extractor and classifier obtained after pre-training of single jamming data set were transferred to small-scale compound jamming data set, and the model was fine-tuning by using weight imprinting and semi-supervised learning.The model parameters were optimized by the proposed nearest neighbor correlation loss nearest neighbor correlation loss (NNCL).The experimental results show that the recognition accuracy of the model can reach 93.20% when the jamming-to-noise ratio is 10 dB and there are only 5 labeled samples of the new class of compound jamming signals. |
| format | Article |
| id | doaj-art-0e3775f2aa5b41b48ccf4de500499c89 |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2023-10-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-0e3775f2aa5b41b48ccf4de500499c892025-01-15T02:58:01ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012023-10-0139152859559852A semi-supervised transfer learning recognition method for radar compound jamming under small samplesJinqiang WANGMinhong SUNXianghong TANGZhaoyang QIUDeguo ZENGAiming at the problem that more and more kinds of radar compound jamming signals and too few training samples were difficult to make the deep learning model reach the optimal state, a semi-supervised transfer learning recognition method for radar compound jamming under small samples was proposed, which solved the problem of low network training accuracy caused by the difficulty in obtaining labeled samples through unlabeled samples.The feature extractor and classifier obtained after pre-training of single jamming data set were transferred to small-scale compound jamming data set, and the model was fine-tuning by using weight imprinting and semi-supervised learning.The model parameters were optimized by the proposed nearest neighbor correlation loss nearest neighbor correlation loss (NNCL).The experimental results show that the recognition accuracy of the model can reach 93.20% when the jamming-to-noise ratio is 10 dB and there are only 5 labeled samples of the new class of compound jamming signals.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023182/radar anti-jammingcompound jamming recognitiontransfer learningweight imprintingsemi-supervised learning |
| spellingShingle | Jinqiang WANG Minhong SUN Xianghong TANG Zhaoyang QIU Deguo ZENG A semi-supervised transfer learning recognition method for radar compound jamming under small samples Dianxin kexue radar anti-jamming compound jamming recognition transfer learning weight imprinting semi-supervised learning |
| title | A semi-supervised transfer learning recognition method for radar compound jamming under small samples |
| title_full | A semi-supervised transfer learning recognition method for radar compound jamming under small samples |
| title_fullStr | A semi-supervised transfer learning recognition method for radar compound jamming under small samples |
| title_full_unstemmed | A semi-supervised transfer learning recognition method for radar compound jamming under small samples |
| title_short | A semi-supervised transfer learning recognition method for radar compound jamming under small samples |
| title_sort | semi supervised transfer learning recognition method for radar compound jamming under small samples |
| topic | radar anti-jamming compound jamming recognition transfer learning weight imprinting semi-supervised learning |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023182/ |
| work_keys_str_mv | AT jinqiangwang asemisupervisedtransferlearningrecognitionmethodforradarcompoundjammingundersmallsamples AT minhongsun asemisupervisedtransferlearningrecognitionmethodforradarcompoundjammingundersmallsamples AT xianghongtang asemisupervisedtransferlearningrecognitionmethodforradarcompoundjammingundersmallsamples AT zhaoyangqiu asemisupervisedtransferlearningrecognitionmethodforradarcompoundjammingundersmallsamples AT deguozeng asemisupervisedtransferlearningrecognitionmethodforradarcompoundjammingundersmallsamples AT jinqiangwang semisupervisedtransferlearningrecognitionmethodforradarcompoundjammingundersmallsamples AT minhongsun semisupervisedtransferlearningrecognitionmethodforradarcompoundjammingundersmallsamples AT xianghongtang semisupervisedtransferlearningrecognitionmethodforradarcompoundjammingundersmallsamples AT zhaoyangqiu semisupervisedtransferlearningrecognitionmethodforradarcompoundjammingundersmallsamples AT deguozeng semisupervisedtransferlearningrecognitionmethodforradarcompoundjammingundersmallsamples |