Version 1
: Received: 30 June 2023 / Approved: 30 June 2023 / Online: 4 July 2023 (03:38:33 CEST)
How to cite:
Li, X.; Li, T.; Wang, A. Joint Channel Estimation and Signal Detection in Mine Based on Deep Learning. Preprints2023, 2023062235. https://doi.org/10.20944/preprints202306.2235.v1
Li, X.; Li, T.; Wang, A. Joint Channel Estimation and Signal Detection in Mine Based on Deep Learning. Preprints 2023, 2023062235. https://doi.org/10.20944/preprints202306.2235.v1
Li, X.; Li, T.; Wang, A. Joint Channel Estimation and Signal Detection in Mine Based on Deep Learning. Preprints2023, 2023062235. https://doi.org/10.20944/preprints202306.2235.v1
APA Style
Li, X., Li, T., & Wang, A. (2023). Joint Channel Estimation and Signal Detection in Mine Based on Deep Learning. Preprints. https://doi.org/10.20944/preprints202306.2235.v1
Chicago/Turabian Style
Li, X., Tongtong Li and Anyi Wang. 2023 "Joint Channel Estimation and Signal Detection in Mine Based on Deep Learning" Preprints. https://doi.org/10.20944/preprints202306.2235.v1
Abstract
This paper addresses the problem of low accuracy of conventional channel estimation and signal detection in complex fields like mines; and the problem of replacing the deep receiver at the receiver side with a deep neural network requires a large amount of data for training and slow training time. Combining the receiver side with traditional communication knowledge, a channel estimation and signal detection method based on the joint ReEsNet and SDRNet under the mine is proposed. The detailed step is to use ReEsNet network for interpolation of conventional channel estimation. Then, on the basis of ReEsNet, the output data is channel equalized and pilots removed, and the previously processed data is input to SDRNet to perform signal recovery. In the complex mine environment, the MSE values are 2e-2 for LS, 6e-3 for MMSE, and 8.44e-5 for ReEsNet at the 1500th sample data for interpolation compared to the conventional channel estimation. the MSE of ReEsNet is the smallest and is closer to the real channel estimation. Compared with the proposed joint channel estimation and signal detection methods, fewer trainable parameters reduce 97% of the parameters compared to CCRNet and 84% of the parameters compared to CNNNet; their detection results, however, are not very different.
Keywords
Channel estimation; Mine; Signal detection
Subject
Computer Science and Mathematics, Computer Networks and Communications
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
