A Knowledge Graph-Driven CNN for Radar Emitter Identification
In recent years, the rapid development of deep learning technology has brought new opportunities for specific emitter identification and has greatly improved the performance of radar emitter identification. The most specific emitter identification methods, based on deep learning, have focused more o...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/13/3289 |
| _version_ | 1797590920921612288 |
|---|---|
| author | Yingchao Chen Peng Li Erxing Yan Zehuan Jing Gaogao Liu Zhao Wang |
| author_facet | Yingchao Chen Peng Li Erxing Yan Zehuan Jing Gaogao Liu Zhao Wang |
| author_sort | Yingchao Chen |
| collection | DOAJ |
| description | In recent years, the rapid development of deep learning technology has brought new opportunities for specific emitter identification and has greatly improved the performance of radar emitter identification. The most specific emitter identification methods, based on deep learning, have focused more on studying network structures and data preprocessing. However, the data selection and utilization have a significant impact on the emitter recognition efficiency, and the method to adaptively determine the two parameters by a specific recognition model has yet to be studied. This paper proposes a knowledge graph-driven convolutional neural network (KG-1D-CNN) to solve this problem. The relationship network between radar data is modeled via the knowledge graph and uses 1D-CNN as the metric kernel to measure these relationships in the knowledge graph construction process. In the recognition process, a precise dataset is constructed based on the knowledge graph according to the task requirement. The network is designed to recognize target emitter individuals from easy to difficult by the precise dataset. In the experiments, most algorithms achieved good recognition results in the high SNR case (10–15 dB), while only the proposed method could achieve more than a 90% recognition rate in the low SNR case (0–5 dB). The experimental results demonstrate the efficacy of the proposed method. |
| first_indexed | 2024-03-11T01:30:38Z |
| format | Article |
| id | doaj.art-b7df79c407194fa38767446cac7ede51 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T01:30:38Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b7df79c407194fa38767446cac7ede512023-11-18T17:24:05ZengMDPI AGRemote Sensing2072-42922023-06-011513328910.3390/rs15133289A Knowledge Graph-Driven CNN for Radar Emitter IdentificationYingchao Chen0Peng Li1Erxing Yan2Zehuan Jing3Gaogao Liu4Zhao Wang5School 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, ChinaSchool of Electronic Engineering, Xidian University, Xi’an 710071, ChinaSchool of Electronic Engineering, Xidian University, Xi’an 710071, ChinaIn recent years, the rapid development of deep learning technology has brought new opportunities for specific emitter identification and has greatly improved the performance of radar emitter identification. The most specific emitter identification methods, based on deep learning, have focused more on studying network structures and data preprocessing. However, the data selection and utilization have a significant impact on the emitter recognition efficiency, and the method to adaptively determine the two parameters by a specific recognition model has yet to be studied. This paper proposes a knowledge graph-driven convolutional neural network (KG-1D-CNN) to solve this problem. The relationship network between radar data is modeled via the knowledge graph and uses 1D-CNN as the metric kernel to measure these relationships in the knowledge graph construction process. In the recognition process, a precise dataset is constructed based on the knowledge graph according to the task requirement. The network is designed to recognize target emitter individuals from easy to difficult by the precise dataset. In the experiments, most algorithms achieved good recognition results in the high SNR case (10–15 dB), while only the proposed method could achieve more than a 90% recognition rate in the low SNR case (0–5 dB). The experimental results demonstrate the efficacy of the proposed method.https://www.mdpi.com/2072-4292/15/13/3289radar emitterspecific emitter identificationknowledge graphconvolutional neural network |
| spellingShingle | Yingchao Chen Peng Li Erxing Yan Zehuan Jing Gaogao Liu Zhao Wang A Knowledge Graph-Driven CNN for Radar Emitter Identification Remote Sensing radar emitter specific emitter identification knowledge graph convolutional neural network |
| title | A Knowledge Graph-Driven CNN for Radar Emitter Identification |
| title_full | A Knowledge Graph-Driven CNN for Radar Emitter Identification |
| title_fullStr | A Knowledge Graph-Driven CNN for Radar Emitter Identification |
| title_full_unstemmed | A Knowledge Graph-Driven CNN for Radar Emitter Identification |
| title_short | A Knowledge Graph-Driven CNN for Radar Emitter Identification |
| title_sort | knowledge graph driven cnn for radar emitter identification |
| topic | radar emitter specific emitter identification knowledge graph convolutional neural network |
| url | https://www.mdpi.com/2072-4292/15/13/3289 |
| work_keys_str_mv | AT yingchaochen aknowledgegraphdrivencnnforradaremitteridentification AT pengli aknowledgegraphdrivencnnforradaremitteridentification AT erxingyan aknowledgegraphdrivencnnforradaremitteridentification AT zehuanjing aknowledgegraphdrivencnnforradaremitteridentification AT gaogaoliu aknowledgegraphdrivencnnforradaremitteridentification AT zhaowang aknowledgegraphdrivencnnforradaremitteridentification AT yingchaochen knowledgegraphdrivencnnforradaremitteridentification AT pengli knowledgegraphdrivencnnforradaremitteridentification AT erxingyan knowledgegraphdrivencnnforradaremitteridentification AT zehuanjing knowledgegraphdrivencnnforradaremitteridentification AT gaogaoliu knowledgegraphdrivencnnforradaremitteridentification AT zhaowang knowledgegraphdrivencnnforradaremitteridentification |