Channel Modeling Based on Transformer Symbolic Regression for Inter-Satellite Terahertz Communication
Applied Sciences · 30.03.2024 · 14 (7) · 2929
DOI: 10.3390/app14072929 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 30.03.2024. Verfasst von Yuanzhi He und 2 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development (R&D) Program.
Abstract (Originalsprache)
Channel modeling is crucial for inter-satellite terahertz communication system design. The conventional method involves manually constructing a mathematical channel model, which is labor-intensive, and using a neural network directly as a channel model lacks interpretability. This paper introduces a channel modeling approach based on symbolic regression. It is the first time that using transformer neural networks as the implementation tool of symbolic regression to generate the mathematical channel model from the channel data directly. It can save manpower and avoid the interpretability issue of using neural networks as a channel model. The feasibility of the proposed method is verified by generating a free space path loss model from simulation data in the terahertz frequency band.
Förderung
- National Key Research and Development (R&D) Program
Zitieren
APA
He, Y., Sheng, B., & Li, Z. (2024). Channel Modeling Based on Transformer Symbolic Regression for Inter-Satellite Terahertz Communication. Applied Sciences, 14(7), 2929. https://doi.org/10.3390/app14072929
Vancouver
He Y, Sheng B, Li Z. Channel Modeling Based on Transformer Symbolic Regression for Inter-Satellite Terahertz Communication. Applied Sciences. 2024;14(7):2929. doi:10.3390/app14072929
BibTeX
@article{He2024,
author = {He, Yuanzhi and Sheng, Biao and Li, Zhiqiang},
title = {Channel Modeling Based on Transformer Symbolic Regression for Inter-Satellite Terahertz Communication},
journal = {Applied Sciences},
year = {2024},
volume = {14},
number = {7},
pages = {2929},
doi = {10.3390/app14072929}
}
EUVIMED