Blind Modulation Format Identification Based on Principal Component Analysis and Singular Value Decomposition
As optical networks evolve towards flexibility and heterogeneity, various modulation formats are used to match different bandwidth requirements and channel conditions. For correct reception and efficient compensation, modulation format identification (MFI) becomes a critical issue. Thus, a novel bli...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/4/612 |
| _version_ | 1797480889736757248 |
|---|---|
| author | Jinkun Jiang Qi Zhang Xiangjun Xin Ran Gao Xishuo Wang Feng Tian Qinghua Tian Bingchun Liu Yongjun Wang |
| author_facet | Jinkun Jiang Qi Zhang Xiangjun Xin Ran Gao Xishuo Wang Feng Tian Qinghua Tian Bingchun Liu Yongjun Wang |
| author_sort | Jinkun Jiang |
| collection | DOAJ |
| description | As optical networks evolve towards flexibility and heterogeneity, various modulation formats are used to match different bandwidth requirements and channel conditions. For correct reception and efficient compensation, modulation format identification (MFI) becomes a critical issue. Thus, a novel blind MFI method based on principal component analysis (PCA) and singular value decomposition (SVD) is proposed. Based on square operation and PCA, the influence of phase rotation is removed, which avoids phase rotation-related discussions and training. By performing SVD on the density matrix about constellation, a denoise method is implemented and the quality of the constellation is improved. In the subsequent processing, the denoised density matrix is used as the feature of the support vector machine (SVM), and the identification of seven modulation formats such as BPSK, QPSK, 8PSK, 8QAM, 16QAM, 32QAM and 64QAM is realized. The results show that lower OSNR values are required for the 100% accurate identification of all modulation formats to be achieved, which are 5 dB, 7 dB, 8 dB, 11 dB, 14 dB, 14 dB and 15 dB. Moreover, the proposed method still retains the advantage, even when the number of samples decrease, which is beneficial for low-complexity implementation. |
| first_indexed | 2024-03-09T22:06:41Z |
| format | Article |
| id | doaj.art-866b9b24ee7942908bc85ea27ed39e98 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T22:06:41Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-866b9b24ee7942908bc85ea27ed39e982023-11-23T19:40:10ZengMDPI AGElectronics2079-92922022-02-0111461210.3390/electronics11040612Blind Modulation Format Identification Based on Principal Component Analysis and Singular Value DecompositionJinkun Jiang0Qi Zhang1Xiangjun Xin2Ran Gao3Xishuo Wang4Feng Tian5Qinghua Tian6Bingchun Liu7Yongjun Wang8School of Electronic Engineering, State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Electronic Engineering, State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Electronic Engineering, State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Electronic Engineering, State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Electronic Engineering, State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Electronic Engineering, State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Management, Tianjin University of Technology, Tianjin 300384, ChinaSchool of Electronic Engineering, State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaAs optical networks evolve towards flexibility and heterogeneity, various modulation formats are used to match different bandwidth requirements and channel conditions. For correct reception and efficient compensation, modulation format identification (MFI) becomes a critical issue. Thus, a novel blind MFI method based on principal component analysis (PCA) and singular value decomposition (SVD) is proposed. Based on square operation and PCA, the influence of phase rotation is removed, which avoids phase rotation-related discussions and training. By performing SVD on the density matrix about constellation, a denoise method is implemented and the quality of the constellation is improved. In the subsequent processing, the denoised density matrix is used as the feature of the support vector machine (SVM), and the identification of seven modulation formats such as BPSK, QPSK, 8PSK, 8QAM, 16QAM, 32QAM and 64QAM is realized. The results show that lower OSNR values are required for the 100% accurate identification of all modulation formats to be achieved, which are 5 dB, 7 dB, 8 dB, 11 dB, 14 dB, 14 dB and 15 dB. Moreover, the proposed method still retains the advantage, even when the number of samples decrease, which is beneficial for low-complexity implementation.https://www.mdpi.com/2079-9292/11/4/612optical communicationdigital signal processingmodulation format identificationprincipal component analysissingular value decompositionsupport vector machine |
| spellingShingle | Jinkun Jiang Qi Zhang Xiangjun Xin Ran Gao Xishuo Wang Feng Tian Qinghua Tian Bingchun Liu Yongjun Wang Blind Modulation Format Identification Based on Principal Component Analysis and Singular Value Decomposition Electronics optical communication digital signal processing modulation format identification principal component analysis singular value decomposition support vector machine |
| title | Blind Modulation Format Identification Based on Principal Component Analysis and Singular Value Decomposition |
| title_full | Blind Modulation Format Identification Based on Principal Component Analysis and Singular Value Decomposition |
| title_fullStr | Blind Modulation Format Identification Based on Principal Component Analysis and Singular Value Decomposition |
| title_full_unstemmed | Blind Modulation Format Identification Based on Principal Component Analysis and Singular Value Decomposition |
| title_short | Blind Modulation Format Identification Based on Principal Component Analysis and Singular Value Decomposition |
| title_sort | blind modulation format identification based on principal component analysis and singular value decomposition |
| topic | optical communication digital signal processing modulation format identification principal component analysis singular value decomposition support vector machine |
| url | https://www.mdpi.com/2079-9292/11/4/612 |
| work_keys_str_mv | AT jinkunjiang blindmodulationformatidentificationbasedonprincipalcomponentanalysisandsingularvaluedecomposition AT qizhang blindmodulationformatidentificationbasedonprincipalcomponentanalysisandsingularvaluedecomposition AT xiangjunxin blindmodulationformatidentificationbasedonprincipalcomponentanalysisandsingularvaluedecomposition AT rangao blindmodulationformatidentificationbasedonprincipalcomponentanalysisandsingularvaluedecomposition AT xishuowang blindmodulationformatidentificationbasedonprincipalcomponentanalysisandsingularvaluedecomposition AT fengtian blindmodulationformatidentificationbasedonprincipalcomponentanalysisandsingularvaluedecomposition AT qinghuatian blindmodulationformatidentificationbasedonprincipalcomponentanalysisandsingularvaluedecomposition AT bingchunliu blindmodulationformatidentificationbasedonprincipalcomponentanalysisandsingularvaluedecomposition AT yongjunwang blindmodulationformatidentificationbasedonprincipalcomponentanalysisandsingularvaluedecomposition |