Polarization Domain Spectrum Sensing Algorithm Based on AlexNet
In this paper, we propose a spectrum sensing algorithm based on the Jones vector covariance matrix (JCM) and AlexNet model, i.e., the JCM-AlexNet algorithm, by taking advantage of the different state characteristics of the signal and noise in the polarization domain. We use the AlexNet model, which...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/22/8946 |
| _version_ | 1797463943644446720 |
|---|---|
| author | Shiyu Ren Hailong Wu Wantong Chen Dongxia Li |
| author_facet | Shiyu Ren Hailong Wu Wantong Chen Dongxia Li |
| author_sort | Shiyu Ren |
| collection | DOAJ |
| description | In this paper, we propose a spectrum sensing algorithm based on the Jones vector covariance matrix (JCM) and AlexNet model, i.e., the JCM-AlexNet algorithm, by taking advantage of the different state characteristics of the signal and noise in the polarization domain. We use the AlexNet model, which is good at extracting matrix features, as the classification model and use the Jones vector, which characterizes the polarization state, to calculate its covariance matrix and convert it into an image and then use it as the input to the AlexNet model. Then, we calculate the likelihood ratio test statistic (AlexNet-LRT) based on the output of the model to achieve the classification of the signal and noise. The simulation analysis shows that the JCM-AlexNet algorithm performs better than the conventional polarization detection (PSD) algorithm and the other three (LeNet5, long short-term memory (LSTM), multilayer perceptron (MLP)) excellent deep-learning-based spectrum sensing algorithms for different signal-to-noise ratios and different false alarm probabilities. |
| first_indexed | 2024-03-09T17:59:54Z |
| format | Article |
| id | doaj.art-3d72fa2ea09c414d8f26f53ba0b51d8a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T17:59:54Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3d72fa2ea09c414d8f26f53ba0b51d8a2023-11-24T09:58:23ZengMDPI AGSensors1424-82202022-11-012222894610.3390/s22228946Polarization Domain Spectrum Sensing Algorithm Based on AlexNetShiyu Ren0Hailong Wu1Wantong Chen2Dongxia Li3School of Electronic Information and Automation, Civil Aviation University of China, Tianjin 300300, ChinaSchool of Electronic Information and Automation, Civil Aviation University of China, Tianjin 300300, ChinaSchool of Electronic Information and Automation, Civil Aviation University of China, Tianjin 300300, ChinaSchool of Electronic Information and Automation, Civil Aviation University of China, Tianjin 300300, ChinaIn this paper, we propose a spectrum sensing algorithm based on the Jones vector covariance matrix (JCM) and AlexNet model, i.e., the JCM-AlexNet algorithm, by taking advantage of the different state characteristics of the signal and noise in the polarization domain. We use the AlexNet model, which is good at extracting matrix features, as the classification model and use the Jones vector, which characterizes the polarization state, to calculate its covariance matrix and convert it into an image and then use it as the input to the AlexNet model. Then, we calculate the likelihood ratio test statistic (AlexNet-LRT) based on the output of the model to achieve the classification of the signal and noise. The simulation analysis shows that the JCM-AlexNet algorithm performs better than the conventional polarization detection (PSD) algorithm and the other three (LeNet5, long short-term memory (LSTM), multilayer perceptron (MLP)) excellent deep-learning-based spectrum sensing algorithms for different signal-to-noise ratios and different false alarm probabilities.https://www.mdpi.com/1424-8220/22/22/8946spectrum sensingpolarization informationdeep learningAlexNet |
| spellingShingle | Shiyu Ren Hailong Wu Wantong Chen Dongxia Li Polarization Domain Spectrum Sensing Algorithm Based on AlexNet Sensors spectrum sensing polarization information deep learning AlexNet |
| title | Polarization Domain Spectrum Sensing Algorithm Based on AlexNet |
| title_full | Polarization Domain Spectrum Sensing Algorithm Based on AlexNet |
| title_fullStr | Polarization Domain Spectrum Sensing Algorithm Based on AlexNet |
| title_full_unstemmed | Polarization Domain Spectrum Sensing Algorithm Based on AlexNet |
| title_short | Polarization Domain Spectrum Sensing Algorithm Based on AlexNet |
| title_sort | polarization domain spectrum sensing algorithm based on alexnet |
| topic | spectrum sensing polarization information deep learning AlexNet |
| url | https://www.mdpi.com/1424-8220/22/22/8946 |
| work_keys_str_mv | AT shiyuren polarizationdomainspectrumsensingalgorithmbasedonalexnet AT hailongwu polarizationdomainspectrumsensingalgorithmbasedonalexnet AT wantongchen polarizationdomainspectrumsensingalgorithmbasedonalexnet AT dongxiali polarizationdomainspectrumsensingalgorithmbasedonalexnet |