| Issue |
EPJ Web Conf.
Volume 330, 2025
The 5th International Conference on Electrical Sciences and Technologies in the Maghreb (CISTEM 2024)
|
|
|---|---|---|
| Article Number | 05005 | |
| Number of page(s) | 5 | |
| Section | Power Quality Monitoring and Fault Diagnostic | |
| DOI | https://doi.org/10.1051/epjconf/202533005005 | |
| Published online | 30 June 2025 | |
https://doi.org/10.1051/epjconf/202533005005
Channel estimation for rician fading with attention mechanism
1 Mohammadia School of Engineers, Mohammed V University in Rabat, Rabat, Morocco
2 ENSAM of Rabat, Mohammed V University in Rabat, Rabat, Morocco
* e-mail: a.assabir@research.emi.ac.ma
** e-mail: ghassane@emi.ac.ma
*** e-mail: abdelmoujoud.assabir@um5s.net.ma
Published online: 30 June 2025
The outdoor terahertz communication channel imposes challenging constraints in the sixth genera- tion (6G), which has attracted researchers to investigate this piece of spectrum band 0.3-10 Thz. In this paper, we deploy a new transformer architecture called HA02 to attain enhanced channel estimation in Orthogonal Frequency-Division Multiplexing (OFDM) systems. This method is based on the self-attention mechanism which focuses on the most important elements of the Least–Squares (LS) method, it utilizes a transformer en- coder block as the encoder and a residual neural network as the decoder. Using the Rician channel model while considering the presence of Free Space Path Loss (FSPL) and the influence of weather conditions on the Thz link’s performance. Our simulations demonstrate high estimation performance compared with some channel estimation techniques.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.