Transfer Learning Strategy in Neural Network Application for Underwater Visible Light Communication System
Post-equalization using neural network (NN) is a promising technique that models and offsets the nonlinear distortion in visible light communication (VLC) channels, which is recognized as an essential component in the incoming 6G era. NN post-equalizer is good at modeling complex channel effects wit...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/24/9969 |
| _version_ | 1827636861935288320 |
|---|---|
| author | Zengyi Xu Jianyang Shi Wenqing Niu Guojin Qin Ruizhe Jin Zhixue He Nan Chi |
| author_facet | Zengyi Xu Jianyang Shi Wenqing Niu Guojin Qin Ruizhe Jin Zhixue He Nan Chi |
| author_sort | Zengyi Xu |
| collection | DOAJ |
| description | Post-equalization using neural network (NN) is a promising technique that models and offsets the nonlinear distortion in visible light communication (VLC) channels, which is recognized as an essential component in the incoming 6G era. NN post-equalizer is good at modeling complex channel effects without previously knowing the law of physics during the transmission. However, the trained NN might be weak in generalization, and thus consumes considerable computation in retraining new models for different channel conditions. In this paper, we studied transfer learning strategy, growing DNN models from a well-trained ‘stem model’ instead of exhaustively training multiple models from randomly initialized states. It extracts the main feature of the channel first whose signal power balances the signal-to-noise ratio and the nonlinearity, and later focuses on the detailed difference in other channel conditions. Compared with the exhaustive training strategy, stem-originated DNN models achieve 64% of the working range with five times the training efficiency at most or more than 95% of the working range with 150% higher efficiency. This finding is beneficial to improving the feasibility of DNN application in real-world UVLC systems. |
| first_indexed | 2024-03-09T15:51:27Z |
| format | Article |
| id | doaj.art-4522314671234ff1bbf7da44e05eb979 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T15:51:27Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4522314671234ff1bbf7da44e05eb9792023-11-24T17:58:21ZengMDPI AGSensors1424-82202022-12-012224996910.3390/s22249969Transfer Learning Strategy in Neural Network Application for Underwater Visible Light Communication SystemZengyi Xu0Jianyang Shi1Wenqing Niu2Guojin Qin3Ruizhe Jin4Zhixue He5Nan Chi6Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaPengcheng Laboratory, Shenzhen 518055, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaPost-equalization using neural network (NN) is a promising technique that models and offsets the nonlinear distortion in visible light communication (VLC) channels, which is recognized as an essential component in the incoming 6G era. NN post-equalizer is good at modeling complex channel effects without previously knowing the law of physics during the transmission. However, the trained NN might be weak in generalization, and thus consumes considerable computation in retraining new models for different channel conditions. In this paper, we studied transfer learning strategy, growing DNN models from a well-trained ‘stem model’ instead of exhaustively training multiple models from randomly initialized states. It extracts the main feature of the channel first whose signal power balances the signal-to-noise ratio and the nonlinearity, and later focuses on the detailed difference in other channel conditions. Compared with the exhaustive training strategy, stem-originated DNN models achieve 64% of the working range with five times the training efficiency at most or more than 95% of the working range with 150% higher efficiency. This finding is beneficial to improving the feasibility of DNN application in real-world UVLC systems.https://www.mdpi.com/1424-8220/22/24/9969UVLCnonlinearityDNNcomputational complexitygeneralization |
| spellingShingle | Zengyi Xu Jianyang Shi Wenqing Niu Guojin Qin Ruizhe Jin Zhixue He Nan Chi Transfer Learning Strategy in Neural Network Application for Underwater Visible Light Communication System Sensors UVLC nonlinearity DNN computational complexity generalization |
| title | Transfer Learning Strategy in Neural Network Application for Underwater Visible Light Communication System |
| title_full | Transfer Learning Strategy in Neural Network Application for Underwater Visible Light Communication System |
| title_fullStr | Transfer Learning Strategy in Neural Network Application for Underwater Visible Light Communication System |
| title_full_unstemmed | Transfer Learning Strategy in Neural Network Application for Underwater Visible Light Communication System |
| title_short | Transfer Learning Strategy in Neural Network Application for Underwater Visible Light Communication System |
| title_sort | transfer learning strategy in neural network application for underwater visible light communication system |
| topic | UVLC nonlinearity DNN computational complexity generalization |
| url | https://www.mdpi.com/1424-8220/22/24/9969 |
| work_keys_str_mv | AT zengyixu transferlearningstrategyinneuralnetworkapplicationforunderwatervisiblelightcommunicationsystem AT jianyangshi transferlearningstrategyinneuralnetworkapplicationforunderwatervisiblelightcommunicationsystem AT wenqingniu transferlearningstrategyinneuralnetworkapplicationforunderwatervisiblelightcommunicationsystem AT guojinqin transferlearningstrategyinneuralnetworkapplicationforunderwatervisiblelightcommunicationsystem AT ruizhejin transferlearningstrategyinneuralnetworkapplicationforunderwatervisiblelightcommunicationsystem AT zhixuehe transferlearningstrategyinneuralnetworkapplicationforunderwatervisiblelightcommunicationsystem AT nanchi transferlearningstrategyinneuralnetworkapplicationforunderwatervisiblelightcommunicationsystem |