Deep Muti-Modal Generic Representation Auxiliary Learning Networks for End-to-End Radar Emitter Classification
Radar data mining is the key module for signal analysis, where patterns hidden inside of signals are gradually available in the learning process and its superiority is significant for enhancing the security of the radar emitter classification (REC) system. Owing to the disadvantage that radio freque...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Aerospace |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2226-4310/9/11/732 |
| _version_ | 1827645274147782656 |
|---|---|
| author | Zhigang Zhu Zhijian Yi Shiyao Li Lin Li |
| author_facet | Zhigang Zhu Zhijian Yi Shiyao Li Lin Li |
| author_sort | Zhigang Zhu |
| collection | DOAJ |
| description | Radar data mining is the key module for signal analysis, where patterns hidden inside of signals are gradually available in the learning process and its superiority is significant for enhancing the security of the radar emitter classification (REC) system. Owing to the disadvantage that radio frequency fingerprinting (RFF) caused by the imperfection of emitter’s hardware is difficult to forge, current deep-learning REC methods based on deep-learning techniques, e.g., convolutional neural network (CNN) and long short term memory (LSTM) are difficult to capture the stable RFF features. In this paper, an online and non-cooperative multi-modal generic representation auxiliary learning REC model, namely muti-modal generic representation auxiliary learning networks (MGRALN), is put forward. Multi-modal means that multi-domain transformations are unified to a generic representation. After this, the representation is employed to facilitate mining the implicit information inside of the signals and to perform the better model robustness, which is achieved by using the available generic genenation to guide the network training and learning. Online means the learning process of REC is only once and the REC is end-to-end. Non-cooperative denotes no demodulation techniques are used before the REC task. Experimental results on the measured civil aviation radar data demonstrate that the proposed method enables one to achieve superior performance. |
| first_indexed | 2024-03-09T18:32:06Z |
| format | Article |
| id | doaj.art-4882cc24ec5148b58c68b6103c3020ce |
| institution | Directory Open Access Journal |
| issn | 2226-4310 |
| language | English |
| last_indexed | 2024-03-09T18:32:06Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj.art-4882cc24ec5148b58c68b6103c3020ce2023-11-24T07:24:40ZengMDPI AGAerospace2226-43102022-11-0191173210.3390/aerospace9110732Deep Muti-Modal Generic Representation Auxiliary Learning Networks for End-to-End Radar Emitter ClassificationZhigang Zhu0Zhijian Yi1Shiyao Li2Lin Li3School of Electronic Engineering, Xidian University, Xi’an 710071, ChinaSchool of Electronic Engineering, Xidian University, Xi’an 710071, ChinaSchool of Electronic Engineering, Xidian University, Xi’an 710071, ChinaSchool of Electronic Engineering, Xidian University, Xi’an 710071, ChinaRadar data mining is the key module for signal analysis, where patterns hidden inside of signals are gradually available in the learning process and its superiority is significant for enhancing the security of the radar emitter classification (REC) system. Owing to the disadvantage that radio frequency fingerprinting (RFF) caused by the imperfection of emitter’s hardware is difficult to forge, current deep-learning REC methods based on deep-learning techniques, e.g., convolutional neural network (CNN) and long short term memory (LSTM) are difficult to capture the stable RFF features. In this paper, an online and non-cooperative multi-modal generic representation auxiliary learning REC model, namely muti-modal generic representation auxiliary learning networks (MGRALN), is put forward. Multi-modal means that multi-domain transformations are unified to a generic representation. After this, the representation is employed to facilitate mining the implicit information inside of the signals and to perform the better model robustness, which is achieved by using the available generic genenation to guide the network training and learning. Online means the learning process of REC is only once and the REC is end-to-end. Non-cooperative denotes no demodulation techniques are used before the REC task. Experimental results on the measured civil aviation radar data demonstrate that the proposed method enables one to achieve superior performance.https://www.mdpi.com/2226-4310/9/11/732signal classificationconvolutional neural network (CNN)radar emitter classification (REC)signal processing |
| spellingShingle | Zhigang Zhu Zhijian Yi Shiyao Li Lin Li Deep Muti-Modal Generic Representation Auxiliary Learning Networks for End-to-End Radar Emitter Classification Aerospace signal classification convolutional neural network (CNN) radar emitter classification (REC) signal processing |
| title | Deep Muti-Modal Generic Representation Auxiliary Learning Networks for End-to-End Radar Emitter Classification |
| title_full | Deep Muti-Modal Generic Representation Auxiliary Learning Networks for End-to-End Radar Emitter Classification |
| title_fullStr | Deep Muti-Modal Generic Representation Auxiliary Learning Networks for End-to-End Radar Emitter Classification |
| title_full_unstemmed | Deep Muti-Modal Generic Representation Auxiliary Learning Networks for End-to-End Radar Emitter Classification |
| title_short | Deep Muti-Modal Generic Representation Auxiliary Learning Networks for End-to-End Radar Emitter Classification |
| title_sort | deep muti modal generic representation auxiliary learning networks for end to end radar emitter classification |
| topic | signal classification convolutional neural network (CNN) radar emitter classification (REC) signal processing |
| url | https://www.mdpi.com/2226-4310/9/11/732 |
| work_keys_str_mv | AT zhigangzhu deepmutimodalgenericrepresentationauxiliarylearningnetworksforendtoendradaremitterclassification AT zhijianyi deepmutimodalgenericrepresentationauxiliarylearningnetworksforendtoendradaremitterclassification AT shiyaoli deepmutimodalgenericrepresentationauxiliarylearningnetworksforendtoendradaremitterclassification AT linli deepmutimodalgenericrepresentationauxiliarylearningnetworksforendtoendradaremitterclassification |