Transfer-learning-adapted CNN-BiLSTM nonlinear equalizer for DSCM-enabled microwave-band fiber-wireless integration transmission
Optics Express · 13.07.2026 · 34 (14) · 26583
DOI: 10.1364/oe.606313 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 09.07.2026. Verfasst von Chengang Fu und 12 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Fund for Excellent Young Scientists Fund Program (Overseas), Beijing Institute of Technology Research Fund Program for Young Scholars.
Abstract (Originalsprache)
Fiber-wireless integration (FWI) provides a promising architecture for flexible and high-capacity fronthaul transmission, while digital subcarrier multiplexing (DSCM) enables subchannel-wise resource allocation with different modulation formats. However, in practical DSCM-enabled FWI systems, cascaded wireless and optical impairments lead to subchannel-dependent residual distortions after classical linear equalization, thereby limiting the uniform recovery of all transmitted subchannels. In this paper, we propose a DSCM-enabled microwave-band FWI transmission scheme integrated with a transfer learning (TL)-adapted convolutional neural network-bidirectional long short-term memory (CNN-BiLSTM) nonlinear equalizer. The proposed equalizer operates on the linear-equalized symbol sequence of each subchannel after classical digital signal processing (DSP) and predicts a residual correction for the target center symbol. A progressive TL adaptation strategy is further developed to reduce the training overhead of subchannel-specific equalization, in which a source model trained on a selected subchannel is adapted to impaired target subchannels via fully connected (FC) warm-up and full-network fine-tuning. The proposed scheme is experimentally validated in a 17.5-GHz microwave-band FWI system over a 2-m wireless link and a 25-km single-mode fiber-28 (SMF-28) link. Experimental results show that the CNN-BiLSTM nonlinear equalizer consistently reduces the average error vector magnitude (EVM) from 34.1% to 6.3% for quadrature phase shift keying (QPSK), from 21.7% to 8.7% for 8-ary quadrature amplitude modulation (8QAM), and from 19.6% to 15.1% for 16-ary quadrature amplitude modulation (16QAM). Moreover, with only 10% target-domain data, the TL-adapted equalizer reduces the EVM of QPSK-modulated target subchannel from about 41% to approximately 22%, approaching the full-training result of about 20%. These results verify the effectiveness and data efficiency of the proposed TL-adapted CNN-BiLSTM nonlinear equalizer for DSCM-enabled FWI transmission.
Förderung
- National Key Research and Development Program of China
- National Natural Science Fund for Excellent Young Scientists Fund Program (Overseas)
- Beijing Institute of Technology Research Fund Program for Young Scholars
Zitieren
APA
Fu, C., Bi, J., Li, X., Li, X., Xie, T., Hong, Z., Chen, C., Zhang, Y., Fu, Y., Liu, Y., Liu, H., Zhang, Q., & Xin, X. (2026). Transfer-learning-adapted CNN-BiLSTM nonlinear equalizer for DSCM-enabled microwave-band fiber-wireless integration transmission. Optics Express, 34(14), 26583. https://doi.org/10.1364/oe.606313
Vancouver
Fu C, Bi J, Li X, Li X, Xie T, Hong Z, et al. Transfer-learning-adapted CNN-BiLSTM nonlinear equalizer for DSCM-enabled microwave-band fiber-wireless integration transmission. Optics Express. 2026;34(14):26583. doi:10.1364/oe.606313
BibTeX
@article{Fu2026,
author = {Fu, Chengang and Bi, Jiahao and Li, Xianshuang and Li, Xinying and Xie, Tangyao and Hong, Zhixin and Chen, Chen and Zhang, Yujie and Fu, Yukai and Liu, Yang and Liu, Haonan and Zhang, Qi and Xin, Xiangjun},
title = {Transfer-learning-adapted CNN-BiLSTM nonlinear equalizer for DSCM-enabled microwave-band fiber-wireless integration transmission},
journal = {Optics Express},
year = {2026},
volume = {34},
number = {14},
pages = {26583},
doi = {10.1364/oe.606313}
}
EUVIMED