Semi-Supervised Classification for Intra-Pulse Modulation of Radar Emitter Signals Using Convolutional Neural Network
Intra-pulse modulation classification of radar emitter signals is beneficial in analyzing radar systems. Recently, convolutional neural networks (CNNs) have been used in classification of intra-pulse modulation of radar emitter signals, and the results proved better than the traditional methods. How...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/9/2059 |
| _version_ | 1797503080443412480 |
|---|---|
| author | Shibo Yuan Peng Li Bin Wu Xiao Li Jie Wang |
| author_facet | Shibo Yuan Peng Li Bin Wu Xiao Li Jie Wang |
| author_sort | Shibo Yuan |
| collection | DOAJ |
| description | Intra-pulse modulation classification of radar emitter signals is beneficial in analyzing radar systems. Recently, convolutional neural networks (CNNs) have been used in classification of intra-pulse modulation of radar emitter signals, and the results proved better than the traditional methods. However, there is a key disadvantage in these CNN-based methods: the CNN requires enough labeled samples. Labeling the modulations of radar emitter signal samples requires a tremendous amount of prior knowledge and human resources. In many circumstances, the labeled samples are quite limited compared with the unlabeled samples, which means that the classification will be semi-supervised. In this paper, we propose a method which could adapt the CNN-based intra-pulse classification approach to the case where a very limited number of labeled samples and a large number of unlabeled samples are provided, to classify the intra-pulse modulations of radar emitter signals. The method is based on a one-dimensional CNN and uses pseudo labels and self-paced data augmentation, which could improve the accuracy of intra-pulse classification. Extensive experiments show that our proposed method can improve the intra-pulse modulation classification performance in the semi-supervised situations. |
| first_indexed | 2024-03-10T03:45:24Z |
| format | Article |
| id | doaj.art-eac40f4b0daa493d9b91131e253b0e0b |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:45:24Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-eac40f4b0daa493d9b91131e253b0e0b2023-11-23T09:09:56ZengMDPI AGRemote Sensing2072-42922022-04-01149205910.3390/rs14092059Semi-Supervised Classification for Intra-Pulse Modulation of Radar Emitter Signals Using Convolutional Neural NetworkShibo Yuan0Peng Li1Bin Wu2Xiao Li3Jie Wang4School 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, ChinaSouthwest China Research Institute of Electronic Equipment, Chengdu 610036, ChinaSouthwest China Research Institute of Electronic Equipment, Chengdu 610036, ChinaIntra-pulse modulation classification of radar emitter signals is beneficial in analyzing radar systems. Recently, convolutional neural networks (CNNs) have been used in classification of intra-pulse modulation of radar emitter signals, and the results proved better than the traditional methods. However, there is a key disadvantage in these CNN-based methods: the CNN requires enough labeled samples. Labeling the modulations of radar emitter signal samples requires a tremendous amount of prior knowledge and human resources. In many circumstances, the labeled samples are quite limited compared with the unlabeled samples, which means that the classification will be semi-supervised. In this paper, we propose a method which could adapt the CNN-based intra-pulse classification approach to the case where a very limited number of labeled samples and a large number of unlabeled samples are provided, to classify the intra-pulse modulations of radar emitter signals. The method is based on a one-dimensional CNN and uses pseudo labels and self-paced data augmentation, which could improve the accuracy of intra-pulse classification. Extensive experiments show that our proposed method can improve the intra-pulse modulation classification performance in the semi-supervised situations.https://www.mdpi.com/2072-4292/14/9/2059intra-pulse modulation classificationradar emitter signalssemi-supervised classificationconvolutional neural network |
| spellingShingle | Shibo Yuan Peng Li Bin Wu Xiao Li Jie Wang Semi-Supervised Classification for Intra-Pulse Modulation of Radar Emitter Signals Using Convolutional Neural Network Remote Sensing intra-pulse modulation classification radar emitter signals semi-supervised classification convolutional neural network |
| title | Semi-Supervised Classification for Intra-Pulse Modulation of Radar Emitter Signals Using Convolutional Neural Network |
| title_full | Semi-Supervised Classification for Intra-Pulse Modulation of Radar Emitter Signals Using Convolutional Neural Network |
| title_fullStr | Semi-Supervised Classification for Intra-Pulse Modulation of Radar Emitter Signals Using Convolutional Neural Network |
| title_full_unstemmed | Semi-Supervised Classification for Intra-Pulse Modulation of Radar Emitter Signals Using Convolutional Neural Network |
| title_short | Semi-Supervised Classification for Intra-Pulse Modulation of Radar Emitter Signals Using Convolutional Neural Network |
| title_sort | semi supervised classification for intra pulse modulation of radar emitter signals using convolutional neural network |
| topic | intra-pulse modulation classification radar emitter signals semi-supervised classification convolutional neural network |
| url | https://www.mdpi.com/2072-4292/14/9/2059 |
| work_keys_str_mv | AT shiboyuan semisupervisedclassificationforintrapulsemodulationofradaremittersignalsusingconvolutionalneuralnetwork AT pengli semisupervisedclassificationforintrapulsemodulationofradaremittersignalsusingconvolutionalneuralnetwork AT binwu semisupervisedclassificationforintrapulsemodulationofradaremittersignalsusingconvolutionalneuralnetwork AT xiaoli semisupervisedclassificationforintrapulsemodulationofradaremittersignalsusingconvolutionalneuralnetwork AT jiewang semisupervisedclassificationforintrapulsemodulationofradaremittersignalsusingconvolutionalneuralnetwork |