Xiao Jian

A multi-scale attention based channel estimation framework is proposed for reconfigurable intelligent surface (RIS) aided massive multiple-input multiple-output systems, in which both hardware imperfections and time-varying characteristics of 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.

A hybrid-field STAR-RIS dataset. we have provided the paired samples for hybrid-field cascaded channel estimation in STAR-RIS systems, in which the data preprocessing and normalization operations have been completed.

The simulation parameters of this dataset have been elaborated in our submitted paper. For instance, M_1 x M_2 = 4 x 8, N_1 x N_2 = 4 x 32, f_c = 28GHz, and Q=N/4.  The  description of each data file is listed as follows.

inHmix_28_32_128_K2_32pilot.mat: the training dataset and validation dataset in the ES protocol.<br/>

A multi-scale attention based channel estimation framework is proposed for reconfigurable intelligent surface (RIS) aided massive multiple-input multiple-output systems, in which both hardware imperfections and time-varying characteristics of 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.