File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TWC.2023.3329387
- Scopus: eid_2-s2.0-85177090143
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Article: Multi-Scale Attention Based Channel Estimation for RIS-Aided Massive MIMO Systems
Title | Multi-Scale Attention Based Channel Estimation for RIS-Aided Massive MIMO Systems |
---|---|
Authors | |
Keywords | channel estimation hardware impairments multi-scale attention Reconfigurable intelligent surface |
Issue Date | 2024 |
Citation | IEEE Transactions on Wireless Communications, 2024, v. 23, n. 6, p. 5969-5984 How to Cite? |
Abstract | A multi-scale attention based channel estimation framework is proposed for reconfigurable intelligent surface (RIS) aided massive multiple-input multiple-output systems, in which hardware imperfections and time-varying characteristics of the cascaded channel are investigated. By exploiting the spatial correlations of different scales in the RIS reflection element domain, we construct a Laplacian pyramid attention network (LPAN) to realize the high-dimensional cascaded channel reconstruction with limited pilot overhead. In LPAN, we leverage the multi-scale supervision learning to progressively capture the spatial correlations of the cascaded channel, where the attention mechanism based dual-branch architecture is designed. To balance network performance and complexity of LPAN, we further propose a lightweight LPAN-L architecture. In LPAN-L, the partial standard convolutional layers are decomposed into the group convolution, dilated convolution and point-wise convolution, which forms a sparse convolutional filter set to extract the channel feature with less computation cost. Furthermore, we leverage parameter sharing and recursion strategy to reduce the space complexity. Moreover, a selective fine-Tuning strategy is developed to realize the domain adaption. Simulation results show that the proposed LPAN can achieve higher estimation accuracy than the existing estimation schemes, while the LPAN-L architecture with a close performance to LPAN efficiently reduces the network complexity. The code is available at https://github.com/Holographic-Lab/LPAN. |
Persistent Identifier | http://hdl.handle.net/10722/349991 |
ISSN | 2023 Impact Factor: 8.9 2023 SCImago Journal Rankings: 5.371 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Xiao, Jian | - |
dc.contributor.author | Wang, Ji | - |
dc.contributor.author | Wang, Zhaolin | - |
dc.contributor.author | Xie, Wenwu | - |
dc.contributor.author | Liu, Yuanwei | - |
dc.date.accessioned | 2024-10-17T07:02:20Z | - |
dc.date.available | 2024-10-17T07:02:20Z | - |
dc.date.issued | 2024 | - |
dc.identifier.citation | IEEE Transactions on Wireless Communications, 2024, v. 23, n. 6, p. 5969-5984 | - |
dc.identifier.issn | 1536-1276 | - |
dc.identifier.uri | http://hdl.handle.net/10722/349991 | - |
dc.description.abstract | A multi-scale attention based channel estimation framework is proposed for reconfigurable intelligent surface (RIS) aided massive multiple-input multiple-output systems, in which hardware imperfections and time-varying characteristics of the cascaded channel are investigated. By exploiting the spatial correlations of different scales in the RIS reflection element domain, we construct a Laplacian pyramid attention network (LPAN) to realize the high-dimensional cascaded channel reconstruction with limited pilot overhead. In LPAN, we leverage the multi-scale supervision learning to progressively capture the spatial correlations of the cascaded channel, where the attention mechanism based dual-branch architecture is designed. To balance network performance and complexity of LPAN, we further propose a lightweight LPAN-L architecture. In LPAN-L, the partial standard convolutional layers are decomposed into the group convolution, dilated convolution and point-wise convolution, which forms a sparse convolutional filter set to extract the channel feature with less computation cost. Furthermore, we leverage parameter sharing and recursion strategy to reduce the space complexity. Moreover, a selective fine-Tuning strategy is developed to realize the domain adaption. Simulation results show that the proposed LPAN can achieve higher estimation accuracy than the existing estimation schemes, while the LPAN-L architecture with a close performance to LPAN efficiently reduces the network complexity. The code is available at https://github.com/Holographic-Lab/LPAN. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Transactions on Wireless Communications | - |
dc.subject | channel estimation | - |
dc.subject | hardware impairments | - |
dc.subject | multi-scale attention | - |
dc.subject | Reconfigurable intelligent surface | - |
dc.title | Multi-Scale Attention Based Channel Estimation for RIS-Aided Massive MIMO Systems | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TWC.2023.3329387 | - |
dc.identifier.scopus | eid_2-s2.0-85177090143 | - |
dc.identifier.volume | 23 | - |
dc.identifier.issue | 6 | - |
dc.identifier.spage | 5969 | - |
dc.identifier.epage | 5984 | - |
dc.identifier.eissn | 1558-2248 | - |