Nonlinear Resilient Learning Method Based on Joint Time-Frequency Image Analysis in Underwater Visible Light Communication
In this paper, we propose a novel nonlinear resilient learning post equalizer named TFDNet in UVLC system. Unlike the traditional deep neural network (DNN) based post equalizers which merely consider the time domain, the proposed TFDNet exploits time-frequency image analysis which considers the time...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Photonics Journal |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9039738/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849710512206512128 |
|---|---|
| author | Hui Chen Yiheng Zhao Fangchen Hu Nan Chi |
| author_facet | Hui Chen Yiheng Zhao Fangchen Hu Nan Chi |
| author_sort | Hui Chen |
| collection | DOAJ |
| description | In this paper, we propose a novel nonlinear resilient learning post equalizer named TFDNet in UVLC system. Unlike the traditional deep neural network (DNN) based post equalizers which merely consider the time domain, the proposed TFDNet exploits time-frequency image analysis which considers the time and frequency domains simultaneously and transforms the signal into 2D time-frequency image, which is further learned by neural network. Experimental results demonstrate that TFDNet outperforms Volterra and DNN based methods for compensating nonlinear distortions through a 1.2 m underwater channel using 64 quadrature amplitude modulation-carrierless amplitude modulation (64QAM-CAP). Even under severe nonlinear distortions where Volterra and DNN cannot work, TFDNet retains valid bit error rate (BER) below the 7% forward error correction (FEC) limit of 3.8 × 10<sup>−3</sup>. The performance of TFDNet verifies the effectiveness of time-frequency image analysis which has been applied to tackle nonlinear distortions in UVLC system for the first time. |
| format | Article |
| id | doaj-art-291f419f76d44d028e0b99efdf1db183 |
| institution | DOAJ |
| issn | 1943-0655 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Photonics Journal |
| spelling | doaj-art-291f419f76d44d028e0b99efdf1db1832025-08-20T03:14:53ZengIEEEIEEE Photonics Journal1943-06552020-01-0112211010.1109/JPHOT.2020.29815169039738Nonlinear Resilient Learning Method Based on Joint Time-Frequency Image Analysis in Underwater Visible Light CommunicationHui Chen0https://orcid.org/0000-0002-7256-1865Yiheng Zhao1Fangchen Hu2https://orcid.org/0000-0003-3859-1558Nan Chi3https://orcid.org/0000-0003-4966-3844Shanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Academy for engineering and technology, Fudan University, Shanghai, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Academy for engineering and technology, Fudan University, Shanghai, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Academy for engineering and technology, Fudan University, Shanghai, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Academy for engineering and technology, Fudan University, Shanghai, ChinaIn this paper, we propose a novel nonlinear resilient learning post equalizer named TFDNet in UVLC system. Unlike the traditional deep neural network (DNN) based post equalizers which merely consider the time domain, the proposed TFDNet exploits time-frequency image analysis which considers the time and frequency domains simultaneously and transforms the signal into 2D time-frequency image, which is further learned by neural network. Experimental results demonstrate that TFDNet outperforms Volterra and DNN based methods for compensating nonlinear distortions through a 1.2 m underwater channel using 64 quadrature amplitude modulation-carrierless amplitude modulation (64QAM-CAP). Even under severe nonlinear distortions where Volterra and DNN cannot work, TFDNet retains valid bit error rate (BER) below the 7% forward error correction (FEC) limit of 3.8 × 10<sup>−3</sup>. The performance of TFDNet verifies the effectiveness of time-frequency image analysis which has been applied to tackle nonlinear distortions in UVLC system for the first time.https://ieeexplore.ieee.org/document/9039738/Underwater visible light communicationpost equalizertime-frequency image analysisnonlinear distortionsneural network |
| spellingShingle | Hui Chen Yiheng Zhao Fangchen Hu Nan Chi Nonlinear Resilient Learning Method Based on Joint Time-Frequency Image Analysis in Underwater Visible Light Communication IEEE Photonics Journal Underwater visible light communication post equalizer time-frequency image analysis nonlinear distortions neural network |
| title | Nonlinear Resilient Learning Method Based on Joint Time-Frequency Image Analysis in Underwater Visible Light Communication |
| title_full | Nonlinear Resilient Learning Method Based on Joint Time-Frequency Image Analysis in Underwater Visible Light Communication |
| title_fullStr | Nonlinear Resilient Learning Method Based on Joint Time-Frequency Image Analysis in Underwater Visible Light Communication |
| title_full_unstemmed | Nonlinear Resilient Learning Method Based on Joint Time-Frequency Image Analysis in Underwater Visible Light Communication |
| title_short | Nonlinear Resilient Learning Method Based on Joint Time-Frequency Image Analysis in Underwater Visible Light Communication |
| title_sort | nonlinear resilient learning method based on joint time frequency image analysis in underwater visible light communication |
| topic | Underwater visible light communication post equalizer time-frequency image analysis nonlinear distortions neural network |
| url | https://ieeexplore.ieee.org/document/9039738/ |
| work_keys_str_mv | AT huichen nonlinearresilientlearningmethodbasedonjointtimefrequencyimageanalysisinunderwatervisiblelightcommunication AT yihengzhao nonlinearresilientlearningmethodbasedonjointtimefrequencyimageanalysisinunderwatervisiblelightcommunication AT fangchenhu nonlinearresilientlearningmethodbasedonjointtimefrequencyimageanalysisinunderwatervisiblelightcommunication AT nanchi nonlinearresilientlearningmethodbasedonjointtimefrequencyimageanalysisinunderwatervisiblelightcommunication |