Deep adversarial neural network for specific emitter identification under varying frequency
Specific emitter identification (SEI) is the process of identifying individual emitters by analyzing the radio frequency emissions, based on the fact that each device contains unique hardware imperfections. While the majority of previous research focuses on obtaining features that are discriminative...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Polish Academy of Sciences
2021-03-01
|
| Series: | Bulletin of the Polish Academy of Sciences: Technical Sciences |
| Subjects: | |
| Online Access: | https://journals.pan.pl/Content/119421/PDF/32_01952_Bpast.No.69(2)_23.04.21_K1_G_TeX_OK.pdf |
| _version_ | 1811344018121949184 |
|---|---|
| author | Keju Huang Junan Yang Hui Liu Pengjiang Hu |
| author_facet | Keju Huang Junan Yang Hui Liu Pengjiang Hu |
| author_sort | Keju Huang |
| collection | DOAJ |
| description | Specific emitter identification (SEI) is the process of identifying individual emitters by analyzing the radio frequency emissions, based on the fact that each device contains unique hardware imperfections. While the majority of previous research focuses on obtaining features that are discriminative, the reliability of the features is rarely considered. For example, since device characteristics of the same emitter vary when it is operating at different carrier frequencies, the performance of SEI approaches may degrade when the training data and the test data are collected from the same emitters with different frequencies. To improve performance of SEI under varying frequency, we propose an approach based on continuous wavelet transform (CWT) and domain adversarial neural network (DANN). The proposed approach exploits unlabeled test data in addition to labeled training data, in order to learn representations that are discriminative for individual emitters and invariant for varying frequencies. Experiments are conducted on received signals of five emitters under three carrier frequencies. The results demonstrate the superior performance of the proposed approach when the carrier frequencies of the training data and the test data differ. |
| first_indexed | 2024-04-13T19:40:15Z |
| format | Article |
| id | doaj.art-998ab3fa0178484da67c0ca31be15d5a |
| institution | Directory Open Access Journal |
| issn | 2300-1917 |
| language | English |
| last_indexed | 2024-04-13T19:40:15Z |
| publishDate | 2021-03-01 |
| publisher | Polish Academy of Sciences |
| record_format | Article |
| series | Bulletin of the Polish Academy of Sciences: Technical Sciences |
| spelling | doaj.art-998ab3fa0178484da67c0ca31be15d5a2022-12-22T02:32:55ZengPolish Academy of SciencesBulletin of the Polish Academy of Sciences: Technical Sciences2300-19172021-03-01692https://doi.org/10.24425/bpasts.2021.136737Deep adversarial neural network for specific emitter identification under varying frequencyKeju Huang0Junan Yang1Hui Liu2Pengjiang Hu3College of Electronic Engineering, National University of Defense Technology, Hefei, Anhui 230037, ChinaCollege of Electronic Engineering, National University of Defense Technology, Hefei, Anhui 230037, ChinaCollege of Electronic Engineering, National University of Defense Technology, Hefei, Anhui 230037, ChinaCollege of Electronic Engineering, National University of Defense Technology, Hefei, Anhui 230037, ChinaSpecific emitter identification (SEI) is the process of identifying individual emitters by analyzing the radio frequency emissions, based on the fact that each device contains unique hardware imperfections. While the majority of previous research focuses on obtaining features that are discriminative, the reliability of the features is rarely considered. For example, since device characteristics of the same emitter vary when it is operating at different carrier frequencies, the performance of SEI approaches may degrade when the training data and the test data are collected from the same emitters with different frequencies. To improve performance of SEI under varying frequency, we propose an approach based on continuous wavelet transform (CWT) and domain adversarial neural network (DANN). The proposed approach exploits unlabeled test data in addition to labeled training data, in order to learn representations that are discriminative for individual emitters and invariant for varying frequencies. Experiments are conducted on received signals of five emitters under three carrier frequencies. The results demonstrate the superior performance of the proposed approach when the carrier frequencies of the training data and the test data differ.https://journals.pan.pl/Content/119421/PDF/32_01952_Bpast.No.69(2)_23.04.21_K1_G_TeX_OK.pdfspecific emitter identificationunsupervised domain adaptationtransfer learningdeep learning |
| spellingShingle | Keju Huang Junan Yang Hui Liu Pengjiang Hu Deep adversarial neural network for specific emitter identification under varying frequency Bulletin of the Polish Academy of Sciences: Technical Sciences specific emitter identification unsupervised domain adaptation transfer learning deep learning |
| title | Deep adversarial neural network for specific emitter identification under varying frequency |
| title_full | Deep adversarial neural network for specific emitter identification under varying frequency |
| title_fullStr | Deep adversarial neural network for specific emitter identification under varying frequency |
| title_full_unstemmed | Deep adversarial neural network for specific emitter identification under varying frequency |
| title_short | Deep adversarial neural network for specific emitter identification under varying frequency |
| title_sort | deep adversarial neural network for specific emitter identification under varying frequency |
| topic | specific emitter identification unsupervised domain adaptation transfer learning deep learning |
| url | https://journals.pan.pl/Content/119421/PDF/32_01952_Bpast.No.69(2)_23.04.21_K1_G_TeX_OK.pdf |
| work_keys_str_mv | AT kejuhuang deepadversarialneuralnetworkforspecificemitteridentificationundervaryingfrequency AT junanyang deepadversarialneuralnetworkforspecificemitteridentificationundervaryingfrequency AT huiliu deepadversarialneuralnetworkforspecificemitteridentificationundervaryingfrequency AT pengjianghu deepadversarialneuralnetworkforspecificemitteridentificationundervaryingfrequency |