Channel estimation for underwater acoustic OFDM based on super‐resolution network
Internet Technology Letters · 2024-11 · 7 (6)
DOI: 10.1002/itl2.496 ↗Kurz gefasst
Fachartikel in der Zeitschrift Internet Technology Letters, online erschienen am 14.01.2024. Verfasst von Xuerong Cui und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 16 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
In this letter, we propose a method for underwater acoustic channel estimation that combines image super‐resolution (SR) and is named FCDnNet. FCDnNet consists of two parts: Fast Super Resolution Convolutional Neural Network (FSRCNN) and Complex Denoising Convolutional Neural Network (C‐DnCNN). FSRCNN extracts effective features of pilot channels, uses deconvolution to achieve SR reconstruction, and generates a pre‐estimation channel matrix. C‐DnCNN preserves the relative positions of the real and imaginary parts of the channel, fully utilizing amplitude and phase information, and can more effectively recover the channel matrix from the pre‐estimation matrix. Experimental results show that the normalized mean square error (NMSE) of FCDnNet is at least 13.1–65.2 lower than other channel estimation methods based on deep learning.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Cui, X., Yuan, B., Li, J., Jiang, B., Li, S., & Liu, J. (2024). Channel estimation for underwater acoustic OFDM based on super‐resolution network. Internet Technology Letters, 7(6). https://doi.org/10.1002/itl2.496
Vancouver
Cui X, Yuan B, Li J, Jiang B, Li S, Liu J. Channel estimation for underwater acoustic OFDM based on super‐resolution network. Internet Technology Letters. 2024;7(6). doi:10.1002/itl2.496
BibTeX
@article{Cui2024,
author = {Cui, Xuerong and Yuan, Bin and Li, Juan and Jiang, Bin and Li, Shibao and Liu, Jianhang},
title = {Channel estimation for underwater acoustic OFDM based on super‐resolution network},
journal = {Internet Technology Letters},
year = {2024},
volume = {7},
number = {6},
doi = {10.1002/itl2.496}
}
EUVIMED