Deep learning channel estimation algorithm for ultra-massive terahertz systems
In order to further improve the hybrid-field channel estimation performance in terahertz ultra-massive multiple-input multiple-output systems, an efficient cross channel Transformer module for image restoration and a fast Fourier transform convolutional network were introduced based on the fixed poi...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2025-01-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025018/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849721403847213056 |
|---|---|
| author | YU Shujuan ZHAO Yang WEI Yuyao ZHANG Yun GAO Gui ZHAO Shengmei |
| author_facet | YU Shujuan ZHAO Yang WEI Yuyao ZHANG Yun GAO Gui ZHAO Shengmei |
| author_sort | YU Shujuan |
| collection | DOAJ |
| description | In order to further improve the hybrid-field channel estimation performance in terahertz ultra-massive multiple-input multiple-output systems, an efficient cross channel Transformer module for image restoration and a fast Fourier transform convolutional network were introduced based on the fixed point network, and a scalable and efficient deep learning model FPN-OTFN was proposed, which models the channel estimation problem as an image restoration problem. Firstly, the least squares algorithm was used to obtain the channel information at the pilot location, and then the channel information was input into the proposed FPN-OTFN algorithm. By training and learning the mapping relationship between low precision channel images and high-precision images, the true channel state information was restored. The simulation results show that the proposed scheme not only inherits the high efficiency and adaptivity of the FPN framework, but also possesses high estimation accuracy and good robustness for THz channels. |
| format | Article |
| id | doaj-art-d7bad0b100cf4de7aaaff42c1cb4caaf |
| institution | DOAJ |
| issn | 1000-436X |
| language | zho |
| publishDate | 2025-01-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-d7bad0b100cf4de7aaaff42c1cb4caaf2025-08-20T03:11:40ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2025-01-014614415682296680Deep learning channel estimation algorithm for ultra-massive terahertz systemsYU ShujuanZHAO YangWEI YuyaoZHANG YunGAO GuiZHAO ShengmeiIn order to further improve the hybrid-field channel estimation performance in terahertz ultra-massive multiple-input multiple-output systems, an efficient cross channel Transformer module for image restoration and a fast Fourier transform convolutional network were introduced based on the fixed point network, and a scalable and efficient deep learning model FPN-OTFN was proposed, which models the channel estimation problem as an image restoration problem. Firstly, the least squares algorithm was used to obtain the channel information at the pilot location, and then the channel information was input into the proposed FPN-OTFN algorithm. By training and learning the mapping relationship between low precision channel images and high-precision images, the true channel state information was restored. The simulation results show that the proposed scheme not only inherits the high efficiency and adaptivity of the FPN framework, but also possesses high estimation accuracy and good robustness for THz channels.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025018/channel estimationTHz ultra-massive MIMO systemdeep learningimage restorationattention mechanism |
| spellingShingle | YU Shujuan ZHAO Yang WEI Yuyao ZHANG Yun GAO Gui ZHAO Shengmei Deep learning channel estimation algorithm for ultra-massive terahertz systems Tongxin xuebao channel estimation THz ultra-massive MIMO system deep learning image restoration attention mechanism |
| title | Deep learning channel estimation algorithm for ultra-massive terahertz systems |
| title_full | Deep learning channel estimation algorithm for ultra-massive terahertz systems |
| title_fullStr | Deep learning channel estimation algorithm for ultra-massive terahertz systems |
| title_full_unstemmed | Deep learning channel estimation algorithm for ultra-massive terahertz systems |
| title_short | Deep learning channel estimation algorithm for ultra-massive terahertz systems |
| title_sort | deep learning channel estimation algorithm for ultra massive terahertz systems |
| topic | channel estimation THz ultra-massive MIMO system deep learning image restoration attention mechanism |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025018/ |
| work_keys_str_mv | AT yushujuan deeplearningchannelestimationalgorithmforultramassiveterahertzsystems AT zhaoyang deeplearningchannelestimationalgorithmforultramassiveterahertzsystems AT weiyuyao deeplearningchannelestimationalgorithmforultramassiveterahertzsystems AT zhangyun deeplearningchannelestimationalgorithmforultramassiveterahertzsystems AT gaogui deeplearningchannelestimationalgorithmforultramassiveterahertzsystems AT zhaoshengmei deeplearningchannelestimationalgorithmforultramassiveterahertzsystems |