OFDM Emitter Identification Method Based on Data Augmentation and Contrastive Learning
Deep learning technology has been widely applied in emitter identification. With the deepening research, the problem of emitter identification under the few-shots condition has become a frontier research direction. As a special communication signal, OFDM (Orthogonal Frequency Division Multiplexing)...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/1/91 |
| _version_ | 1797626330770046976 |
|---|---|
| author | Jiaqi Yu Ye Yuan Qian Zhang Wei Zhang Ziyu Fan Fusheng Jin |
| author_facet | Jiaqi Yu Ye Yuan Qian Zhang Wei Zhang Ziyu Fan Fusheng Jin |
| author_sort | Jiaqi Yu |
| collection | DOAJ |
| description | Deep learning technology has been widely applied in emitter identification. With the deepening research, the problem of emitter identification under the few-shots condition has become a frontier research direction. As a special communication signal, OFDM (Orthogonal Frequency Division Multiplexing) signal is of high complexity so emitter identification technology under OFDM is extremely challenging. In this paper, an emitter identification method based on contrastive learning and residual network is proposed. First, according to the particularity of OFDM, we adjust the structure of ResNet and propose a targeted data preprocessing method. Then, some data augmentation strategies are designed to construct positive samples. We conduct self-supervised pretraining to distinguish features of positive and negative samples in hidden space. Based on the pretrained feature extractor, the classifier is no longer trained from scratch. Extensive experiments have validated the effectiveness of our proposed methods. |
| first_indexed | 2024-03-11T10:08:53Z |
| format | Article |
| id | doaj.art-6cc10c9982c3402f9eb3769387e350e2 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T10:08:53Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-6cc10c9982c3402f9eb3769387e350e22023-11-16T14:50:33ZengMDPI AGApplied Sciences2076-34172022-12-011319110.3390/app13010091OFDM Emitter Identification Method Based on Data Augmentation and Contrastive LearningJiaqi Yu0Ye Yuan1Qian Zhang2Wei Zhang3Ziyu Fan4Fusheng Jin5School of Computer Science, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Computer Science, Beijing Institute of Technology, Beijing 100081, ChinaScience and Technology on Electronic Information Control Laboratory, Chengdu 610036, ChinaScience and Technology on Electronic Information Control Laboratory, Chengdu 610036, ChinaSchool of Computer Science, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Computer Science, Beijing Institute of Technology, Beijing 100081, ChinaDeep learning technology has been widely applied in emitter identification. With the deepening research, the problem of emitter identification under the few-shots condition has become a frontier research direction. As a special communication signal, OFDM (Orthogonal Frequency Division Multiplexing) signal is of high complexity so emitter identification technology under OFDM is extremely challenging. In this paper, an emitter identification method based on contrastive learning and residual network is proposed. First, according to the particularity of OFDM, we adjust the structure of ResNet and propose a targeted data preprocessing method. Then, some data augmentation strategies are designed to construct positive samples. We conduct self-supervised pretraining to distinguish features of positive and negative samples in hidden space. Based on the pretrained feature extractor, the classifier is no longer trained from scratch. Extensive experiments have validated the effectiveness of our proposed methods.https://www.mdpi.com/2076-3417/13/1/91orthogonal frequency division multiplexing (OFDM)emitter identificationcontrastive learningdata augmentationResNet |
| spellingShingle | Jiaqi Yu Ye Yuan Qian Zhang Wei Zhang Ziyu Fan Fusheng Jin OFDM Emitter Identification Method Based on Data Augmentation and Contrastive Learning Applied Sciences orthogonal frequency division multiplexing (OFDM) emitter identification contrastive learning data augmentation ResNet |
| title | OFDM Emitter Identification Method Based on Data Augmentation and Contrastive Learning |
| title_full | OFDM Emitter Identification Method Based on Data Augmentation and Contrastive Learning |
| title_fullStr | OFDM Emitter Identification Method Based on Data Augmentation and Contrastive Learning |
| title_full_unstemmed | OFDM Emitter Identification Method Based on Data Augmentation and Contrastive Learning |
| title_short | OFDM Emitter Identification Method Based on Data Augmentation and Contrastive Learning |
| title_sort | ofdm emitter identification method based on data augmentation and contrastive learning |
| topic | orthogonal frequency division multiplexing (OFDM) emitter identification contrastive learning data augmentation ResNet |
| url | https://www.mdpi.com/2076-3417/13/1/91 |
| work_keys_str_mv | AT jiaqiyu ofdmemitteridentificationmethodbasedondataaugmentationandcontrastivelearning AT yeyuan ofdmemitteridentificationmethodbasedondataaugmentationandcontrastivelearning AT qianzhang ofdmemitteridentificationmethodbasedondataaugmentationandcontrastivelearning AT weizhang ofdmemitteridentificationmethodbasedondataaugmentationandcontrastivelearning AT ziyufan ofdmemitteridentificationmethodbasedondataaugmentationandcontrastivelearning AT fushengjin ofdmemitteridentificationmethodbasedondataaugmentationandcontrastivelearning |