Strong generalizability neural network for modulation format recognition in multi-scenario visible light communications
Chinese Optics Letters · 2026 · 24 (4) · 040601
DOI: 10.3788/col202624.040601 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chinese Optics Letters, 2026. Verfasst von Yufeng Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 15 Literaturangaben.
Abstract (Originalsprache)
Visible light communication suffers from signal-to-noise ratio (SNR) loss and blurred modulation features due to ambient light, underwater scattering and absorption, and device nonlinearity, degrading modulation-format recognition (MFR). We propose TF-former, a lightweight time – frequency Transformer that jointly models time-and frequency-domain features to enhance robustness to complex impairments. To improve computational efficiency, we introduce linear attention to MFR, reducing attention complexity from quadratic to linear. On four real-link datasets covering 19 modulation formats, TF-former achieves average accuracies of 97.25%, 98.11%, 98.68%, and 66.94%. It notably retains 62.74% under extremely low SNR conditions (corridor link, transmission distance 26 m, arbitrary wave generator peak-to-peak voltage 0.05 V, and corresponding bit error rate of all modulation formats between 0.34 and 0.49), gains up to 47.85% over the baseline method TLDNN, and outperforms on RML2016.10a.
Zitieren
APA
Zhang, Y., Zhu, X., Zhou, H., Zhang, H., Liu, X., & Zhang, M. (2026). Strong generalizability neural network for modulation format recognition in multi-scenario visible light communications. Chinese Optics Letters, 24(4), 040601. https://doi.org/10.3788/col202624.040601
Vancouver
Zhang Y, Zhu X, Zhou H, Zhang H, Liu X, Zhang M. Strong generalizability neural network for modulation format recognition in multi-scenario visible light communications. Chinese Optics Letters. 2026;24(4):040601. doi:10.3788/col202624.040601
BibTeX
@article{Zhang2026,
author = {Zhang, Yufeng and Zhu, Xiao and Zhou, Hongyu and Zhang, Hongyuan and Liu, Xiaodong and Zhang, Minglun},
title = {Strong generalizability neural network for modulation format recognition in multi-scenario visible light communications},
journal = {Chinese Optics Letters},
year = {2026},
volume = {24},
number = {4},
pages = {040601},
doi = {10.3788/col202624.040601}
}
EUVIMED