Efficient Open-Set Recognition for Interference Signals Based on Convolutional Prototype Learning
Interference classification plays an important role in anti-jamming communication. Although the existing interference signal recognition methods based on deep learning have a higher accuracy than traditional methods, these have poor robustness while rejecting interference signals of unknown classes...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/9/4380 |
| _version_ | 1797505642093608960 |
|---|---|
| author | Xiangwei Chen Zhijin Zhao Xueyi Ye Shilian Zheng Caiyi Lou Xiaoniu Yang |
| author_facet | Xiangwei Chen Zhijin Zhao Xueyi Ye Shilian Zheng Caiyi Lou Xiaoniu Yang |
| author_sort | Xiangwei Chen |
| collection | DOAJ |
| description | Interference classification plays an important role in anti-jamming communication. Although the existing interference signal recognition methods based on deep learning have a higher accuracy than traditional methods, these have poor robustness while rejecting interference signals of unknown classes in interference open-set recognition (OSR). To ensure the classification accuracy of the known classes and the rejection rate of the unknown classes in interference OSR, we propose a new hollow convolution prototype learning (HCPL) in which the inner-dot-based cross-entropy loss (ICE) and the center loss are used to update prototypes to the periphery of the feature space so that the internal space is left for the unknown class samples, and the radius loss is used to reduce the impact of the prototype norm on the rejection rate of unknown classes. Then, a hybrid attention and feature reuse net (HAFRNet) for interference signal classification was designed, which contains a feature reuse structure and hybrid domain attention module (HDAM). A feature reuse structure is a simple DenseNet structure without a transition layer. An HDAM can recalibrate both time-wise and channel-wise feature responses by constructing a global attention matrix automatically. We also carried out simulation experiments on nine interference types, which include single-tone jamming, multitone jamming, periodic Gaussian pulse jamming, frequency hopping jamming, linear sweeping frequency jamming, second sweeping frequency jamming, BPSK modulation jamming, noise frequency modulation jamming and QPSK modulation jamming. The simulation results show that the proposed method has considerable classification accuracy of the known classes and rejection performance of the unknown classes. When the JNR is −10 dB, the classification accuracy of the known classes of the proposed method is 2–7% higher than other algorithms under different openness. When the openness is 0.030, the unknown class rejection performance plateau of the proposed method reaches 0.9883, while GCPL is 0.9403 and CG-Encoder is 0.9869; when the openness is 0.397, the proposed method is more than 0.89, while GCPL is 0.8102 and CG-Encoder is 0.9088. However, the rejection performance of unknown classes of CG-Encoder is much worse than that of the proposed method under low JNR. In addition, the proposed method requires less storage resources and has a lower computational complexity than CG-Encoder. |
| first_indexed | 2024-03-10T04:21:32Z |
| format | Article |
| id | doaj.art-08b0910186554cef91c57ae407afbec0 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:21:32Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-08b0910186554cef91c57ae407afbec02023-11-23T07:48:13ZengMDPI AGApplied Sciences2076-34172022-04-01129438010.3390/app12094380Efficient Open-Set Recognition for Interference Signals Based on Convolutional Prototype LearningXiangwei Chen0Zhijin Zhao1Xueyi Ye2Shilian Zheng3Caiyi Lou4Xiaoniu Yang5School of Communication Engineering, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Communication Engineering, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Communication Engineering, Hangzhou Dianzi University, Hangzhou 310018, ChinaScience and Technology on Communication Information Security Control Laboratory, Jiaxing 314001, ChinaScience and Technology on Communication Information Security Control Laboratory, Jiaxing 314001, ChinaScience and Technology on Communication Information Security Control Laboratory, Jiaxing 314001, ChinaInterference classification plays an important role in anti-jamming communication. Although the existing interference signal recognition methods based on deep learning have a higher accuracy than traditional methods, these have poor robustness while rejecting interference signals of unknown classes in interference open-set recognition (OSR). To ensure the classification accuracy of the known classes and the rejection rate of the unknown classes in interference OSR, we propose a new hollow convolution prototype learning (HCPL) in which the inner-dot-based cross-entropy loss (ICE) and the center loss are used to update prototypes to the periphery of the feature space so that the internal space is left for the unknown class samples, and the radius loss is used to reduce the impact of the prototype norm on the rejection rate of unknown classes. Then, a hybrid attention and feature reuse net (HAFRNet) for interference signal classification was designed, which contains a feature reuse structure and hybrid domain attention module (HDAM). A feature reuse structure is a simple DenseNet structure without a transition layer. An HDAM can recalibrate both time-wise and channel-wise feature responses by constructing a global attention matrix automatically. We also carried out simulation experiments on nine interference types, which include single-tone jamming, multitone jamming, periodic Gaussian pulse jamming, frequency hopping jamming, linear sweeping frequency jamming, second sweeping frequency jamming, BPSK modulation jamming, noise frequency modulation jamming and QPSK modulation jamming. The simulation results show that the proposed method has considerable classification accuracy of the known classes and rejection performance of the unknown classes. When the JNR is −10 dB, the classification accuracy of the known classes of the proposed method is 2–7% higher than other algorithms under different openness. When the openness is 0.030, the unknown class rejection performance plateau of the proposed method reaches 0.9883, while GCPL is 0.9403 and CG-Encoder is 0.9869; when the openness is 0.397, the proposed method is more than 0.89, while GCPL is 0.8102 and CG-Encoder is 0.9088. However, the rejection performance of unknown classes of CG-Encoder is much worse than that of the proposed method under low JNR. In addition, the proposed method requires less storage resources and has a lower computational complexity than CG-Encoder.https://www.mdpi.com/2076-3417/12/9/4380open-set recognitioninterference signalprototype learningconvolutional neural networkattention |
| spellingShingle | Xiangwei Chen Zhijin Zhao Xueyi Ye Shilian Zheng Caiyi Lou Xiaoniu Yang Efficient Open-Set Recognition for Interference Signals Based on Convolutional Prototype Learning Applied Sciences open-set recognition interference signal prototype learning convolutional neural network attention |
| title | Efficient Open-Set Recognition for Interference Signals Based on Convolutional Prototype Learning |
| title_full | Efficient Open-Set Recognition for Interference Signals Based on Convolutional Prototype Learning |
| title_fullStr | Efficient Open-Set Recognition for Interference Signals Based on Convolutional Prototype Learning |
| title_full_unstemmed | Efficient Open-Set Recognition for Interference Signals Based on Convolutional Prototype Learning |
| title_short | Efficient Open-Set Recognition for Interference Signals Based on Convolutional Prototype Learning |
| title_sort | efficient open set recognition for interference signals based on convolutional prototype learning |
| topic | open-set recognition interference signal prototype learning convolutional neural network attention |
| url | https://www.mdpi.com/2076-3417/12/9/4380 |
| work_keys_str_mv | AT xiangweichen efficientopensetrecognitionforinterferencesignalsbasedonconvolutionalprototypelearning AT zhijinzhao efficientopensetrecognitionforinterferencesignalsbasedonconvolutionalprototypelearning AT xueyiye efficientopensetrecognitionforinterferencesignalsbasedonconvolutionalprototypelearning AT shilianzheng efficientopensetrecognitionforinterferencesignalsbasedonconvolutionalprototypelearning AT caiyilou efficientopensetrecognitionforinterferencesignalsbasedonconvolutionalprototypelearning AT xiaoniuyang efficientopensetrecognitionforinterferencesignalsbasedonconvolutionalprototypelearning |