Wang, S; Gao, S; Yang, W; Loh, T H; Yang, Y; Qin, F (2024) Area Restoration of Channel Impulse Response with Time Decomposition based Super-Resolution Method. IEEE Transactions on Wireless Communications, 23 (8). pp. 9687-9700.

Full text not available from this repository.

Abstract

With the application and development of the fifth-generation (5G) communication, it is essential to deeply understand the characteristics of wireless channels, represented by Channel Impulse Response (CIR), to ensure the effective design of algorithms and systems. However, both the traditional channel measurement and modelling are essentially point measurement based and without the capability to obtain the channel information of a given surrounding area. To overcome this limitation, this paper proposes to re-assemble the discretely sampled channel impulse responses into equalized low-resolution video streams. With this basis, a deep learning based video super-resolution method named Time Decomposition Video Super-Resolution (TDVSR) has been proposed to restore the area channel information for the first time. A time decomposition module based on Bidirectional Long Short-Term Memory (BiLSTM) has been designed to decompose the re-assembled channel impulse responses into video form in the time dimension. A retrained video super-resolution model will then process the composited data and output high-resolution frames, which will be reversed to the channel impulse responses at the dense density target area. A data set with various typical fading scenarios has been constructed by Ray Tracing (RT) method. Extensive experiments demonstrate that the proposed TDVSR model successfully learned the nonlinear propagation laws through the data-driven method, which shows satisfied restoration accuracy with significantly increased computation efficiency.

Item Type:	Article
Subjects:	Electromagnetics > Wireless Communications
Divisions:	Electromagnetic & Electrochemical Technologies
Identification number/DOI:	10.1109/TWC.2024.3364666
Last Modified:	10 Sep 2024 13:50
URI:	https://eprintspublications.npl.co.uk/id/eprint/10009