A Post-Equalizer Based on Dual Self-Attention Network in UVLC System
The post-equalizer in the Underwater Visible Light Communication (UVLC) system can overcome the nonlinear distortion existing in the system. The existing nonlinear post-equalizer based on deep learning still has problems such as the number of data nodes has a great influence on the effect, the equal...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Photonics Journal |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9395215/ |
| id |
doaj-1f4d51f24373401887d7f576b2fd2505 |
|---|---|
| record_format |
Article |
| spelling |
doaj-1f4d51f24373401887d7f576b2fd25052021-04-22T23:00:14ZengIEEEIEEE Photonics Journal1943-06552021-01-0113211110.1109/JPHOT.2021.30710089395215A Post-Equalizer Based on Dual Self-Attention Network in UVLC SystemFangxing Yuan0https://orcid.org/0000-0001-8497-6825Jie Wang1Weixiang Yu2https://orcid.org/0000-0003-3851-3330Jiuchun Ren3School of Information Science and Technology, Fudan University, Shanghai, ChinaSchool of Information Science and Technology, Fudan University, Shanghai, ChinaSchool of Information Science and Technology, Fudan University, Shanghai, ChinaSchool of Information Science and Technology, Fudan University, Shanghai, ChinaThe post-equalizer in the Underwater Visible Light Communication (UVLC) system can overcome the nonlinear distortion existing in the system. The existing nonlinear post-equalizer based on deep learning still has problems such as the number of data nodes has a great influence on the effect, the equalization effect decreases significantly when the data rate becomes higher and too complex a model leads to slow training time. In this paper, we propose a Dual Self-Attention Network (DSANet) as a post equalizer in the CAP modulated UVLC system. Experiments show that the DSANet-based post equalizer can achieve good equalization performance at different data rates; it shows strong robustness when the number of data nodes changes; its training speed is close to that of the plainest nonlinear post-equalizer.https://ieeexplore.ieee.org/document/9395215/Underwater visible light communicationdual self-attention networkpost equalizertime series analysisdeep learning |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Fangxing Yuan Jie Wang Weixiang Yu Jiuchun Ren |
| spellingShingle |
Fangxing Yuan Jie Wang Weixiang Yu Jiuchun Ren A Post-Equalizer Based on Dual Self-Attention Network in UVLC System IEEE Photonics Journal Underwater visible light communication dual self-attention network post equalizer time series analysis deep learning |
| author_facet |
Fangxing Yuan Jie Wang Weixiang Yu Jiuchun Ren |
| author_sort |
Fangxing Yuan |
| title |
A Post-Equalizer Based on Dual Self-Attention Network in UVLC System |
| title_short |
A Post-Equalizer Based on Dual Self-Attention Network in UVLC System |
| title_full |
A Post-Equalizer Based on Dual Self-Attention Network in UVLC System |
| title_fullStr |
A Post-Equalizer Based on Dual Self-Attention Network in UVLC System |
| title_full_unstemmed |
A Post-Equalizer Based on Dual Self-Attention Network in UVLC System |
| title_sort |
post-equalizer based on dual self-attention network in uvlc system |
| publisher |
IEEE |
| series |
IEEE Photonics Journal |
| issn |
1943-0655 |
| publishDate |
2021-01-01 |
| description |
The post-equalizer in the Underwater Visible Light Communication (UVLC) system can overcome the nonlinear distortion existing in the system. The existing nonlinear post-equalizer based on deep learning still has problems such as the number of data nodes has a great influence on the effect, the equalization effect decreases significantly when the data rate becomes higher and too complex a model leads to slow training time. In this paper, we propose a Dual Self-Attention Network (DSANet) as a post equalizer in the CAP modulated UVLC system. Experiments show that the DSANet-based post equalizer can achieve good equalization performance at different data rates; it shows strong robustness when the number of data nodes changes; its training speed is close to that of the plainest nonlinear post-equalizer. |
| topic |
Underwater visible light communication dual self-attention network post equalizer time series analysis deep learning |
| url |
https://ieeexplore.ieee.org/document/9395215/ |
| work_keys_str_mv |
AT fangxingyuan apostequalizerbasedondualselfattentionnetworkinuvlcsystem AT jiewang apostequalizerbasedondualselfattentionnetworkinuvlcsystem AT weixiangyu apostequalizerbasedondualselfattentionnetworkinuvlcsystem AT jiuchunren apostequalizerbasedondualselfattentionnetworkinuvlcsystem AT fangxingyuan postequalizerbasedondualselfattentionnetworkinuvlcsystem AT jiewang postequalizerbasedondualselfattentionnetworkinuvlcsystem AT weixiangyu postequalizerbasedondualselfattentionnetworkinuvlcsystem AT jiuchunren postequalizerbasedondualselfattentionnetworkinuvlcsystem |
| _version_ |
1721513988722786304 |