Underwater Wireless Optical Communication Utilizing a Semi-Supervised Twin Neural Network-Based Post-Equalizer With Interleaved Consistency Regularization
Journal of Lightwave Technology · 15.07.2024 · 42 (14) · 4763-4773
DOI: 10.1109/jlt.2024.3379217 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Lightwave Technology, erschienen am 15.07.2024. Verfasst von Zihao Du und 8 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Key Research and Development Program of Hainan Province, Project of Sanya Yazhou Bay Science and Technology City.
Abstract (Originalsprache)
In this work, a novel semi-supervised twin neural network (semiTNN)-based post-equalizer (PE) is proposed and developed for high-speed 4-level pulse amplitude modulation (PAM4) underwater wireless optical communication (UWOC). Furthermore, semiTNN is enabled by a dual-drop strategy and interleaved consistency regularization (ICR), thereby only requiring a small amount of labeled PAM4 symbols as references to be well-trained. The experimental results over a 14-m/4-Gbps underwater link reveal that the proposed semiTNN PE paired with ICR, with only 5% labeled data, can achieve nearly the same bit error rate (BER) performance as the one trained by a fully-supervised learning process, resulting in 0.8-dB and 4.9-dB sensitivity improvements comparing with the traditional Volterra nonlinear equalizer (VNE) and linear feedforward equalizer (FFE) at a specific BER of 1 × 10−3, respectively. When the transmission distance is further extended to 56 m, the semiTNN PE with 10% labeled data can reach a data rate up to 4.26 Gbps under the hard-decision forward error correction (HD-FEC) threshold, which is 90 Mbps and 150 Mbps larger than that of VNE and FFE, respectively. Moreover, even facing bias-current fluctuations, turbulence, and bubbles, the UWOC systems supported by the semiTNN can still maintain a satisfying BER performance to some extent. This is the first time to utilize the proposed semiTNN PE combined with an ICR-based loss function for high-speed UWOC, and it can be highly beneficial to the practical deployment of NN-based PEs in the future.
Förderung
- National Key Research and Development Program of China
- Key Research and Development Program of Hainan Province
- Project of Sanya Yazhou Bay Science and Technology City
Zitieren
APA
Du, Z., Zhang, T., Wang, H., Cai, C., Ma, X., He, Y., Ding, Z., Ma, D., & Xu, J. (2024). Underwater Wireless Optical Communication Utilizing a Semi-Supervised Twin Neural Network-Based Post-Equalizer With Interleaved Consistency Regularization. Journal of Lightwave Technology, 42(14), 4763-4773. https://doi.org/10.1109/jlt.2024.3379217
Vancouver
Du Z, Zhang T, Wang H, Cai C, Ma X, He Y, et al. Underwater Wireless Optical Communication Utilizing a Semi-Supervised Twin Neural Network-Based Post-Equalizer With Interleaved Consistency Regularization. Journal of Lightwave Technology. 2024;42(14):4763-4773. doi:10.1109/jlt.2024.3379217
BibTeX
@article{Du2024,
author = {Du, Zihao and Zhang, Tianhao and Wang, Haipeng and Cai, Chengye and Ma, Xiaoxu and He, Yuxin and Ding, Zhongjun and Ma, Dongfang and Xu, Jing},
title = {Underwater Wireless Optical Communication Utilizing a Semi-Supervised Twin Neural Network-Based Post-Equalizer With Interleaved Consistency Regularization},
journal = {Journal of Lightwave Technology},
year = {2024},
volume = {42},
number = {14},
pages = {4763--4773},
doi = {10.1109/jlt.2024.3379217}
}
EUVIMED