Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Transformer-based Efficient CSI Feedback for THz band FDD MIMO Systems

Authors
Ji, Dong JinChung, Byung Chang
Issue Date
Nov-2023
Publisher
Institute of Electrical and Electronics Engineers Inc.
Keywords
6G mobile communication; Antenna arrays; channel feedback; Computational modeling; Computer architecture; deep learning; Machine learning for communications; multiple-input multiple-output; Receiving antennas; Tensors; Transformers
Citation
IEEE Wireless Communications Letters, pp 1 - 1
Pages
1
Indexed
SCIE
SCOPUS
Journal Title
IEEE Wireless Communications Letters
Start Page
1
End Page
1
URI
https://scholarworks.gnu.ac.kr/handle/sw.gnu/69427
DOI
10.1109/LWC.2023.3329019
ISSN
2162-2337
2162-2345
Abstract
Machine learning algorithms have been extensively explored for the feedback of multiple-input multiple-output (MIMO) channel state information (CSI) in orthogonal frequency division multiplexing (OFDM) systems. However, their viability in sixth-generation (6G) wireless communication systems, operating in the terahertz (THz) band, remains uncertain. To address this, we propose ChannelTransformer, a transformer-model-based CSI feedback scheme that incorporates multi-head self-attention and a CSI-feedback-aware transformer structure, and a lightweight user equipment(UE) model. Through simulations in the DeepMIMO O1 scenario at 140GHz, ChannelTransformer demonstrates superior performance in terms of normalized mean square error (NMSE) and cosine similarity across various feedback lengths compared to conventional schemes with a much smaller UE model size. IEEE
Files in This Item
There are no files associated with this item.
Appears in
Collections
해양과학대학 > 지능형통신공학과 > Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Chung, Byung Chang photo

Chung, Byung Chang
IT공과대학 (AI정보공학과)
Read more

Altmetrics

Total Views & Downloads

BROWSE