南方科技大学知识苑(SUSTech KC): Data-Driven OTFS Channel Estimation Based on Gated Recurrent Convolutional Autoencoder

题名	Data-Driven OTFS Channel Estimation Based on Gated Recurrent Convolutional Autoencoder
作者	Junshen Chen 1; Qihao Yuan 1; Shiyao Zhang2 ; Chang Liu 3
DOI	10.1109/ISCIT57293.2023.10376091
发表日期	2023
ISSN	2643-6140
ISBN	978-1-6654-5732-3
会议录名称	2023 22nd International Symposium on Communications and Information Technologies (ISCIT)
页码	7-12
会议日期	16-18 Oct. 2023
会议地点	Sydney, Australia
摘要	Considering the traffic environment with highmoving vehicles, orthogonal time frequency space (OTFS) has become an emerging technology to handle the rapid timevarying channels via vehicular communications. Due to sparse representation of the delay-Doppler (DD) domain, the related channel information can be estimated by means of the embedded pilot technique. However, the uncertainties of unknown and burst noise can incur system performance degradation issues. To tackle this problem, in this paper, we propose a novel gated recurrent convolutional autoencoder (GRCAE) model to denoise the complex noise for channel estimation in OTFS systems. Specifically, the proposed model can distinguish and retain the significant features of the signal during the denoising process through the gated recurrent unit (GRU) network. Meanwhile, the convolutional autoencoder can better capture the local spatial features of the signal and reconstruct them to obtain a denoised signal. The parallel procedure further improves the denoising accuracy and robustness. Our simulation results demonstrate that the proposed GRCAEbased approach present satisfactory performance in various noise scenarios.
关键词	Channel estimation gated recurrent convolutional autoencoder orthogonal time frequency space
学校署名	其他
相关链接	[IEEE记录]
收录类别	EI
EI入藏号	20240515472471
EI主题词	Channel estimation ; Convolution ; Frequency estimation ; Signal reconstruction
EI分类号	Information Theory and Signal Processing:716.1
来源库	IEEE
全文链接	https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10376091
引用统计
成果类型	会议论文
条目标识符	http://sustech.caswiz.com/handle/2SGJ60CL/673744
专题	南方科技大学
作者单位	1.Shenzhen University, Shenzhen, China 2.Southern University of Science and Technology, Shenzhen, China 3.The Hong Kong Polytechnic University, Hong Kong SAR, China
推荐引用方式 GB/T 7714	Junshen Chen,Qihao Yuan,Shiyao Zhang,et al. Data-Driven OTFS Channel Estimation Based on Gated Recurrent Convolutional Autoencoder[C],2023:7-12.