Dynamic Doppler prediction in high-speed rail using long short-term memory neural network,Transactions on Emerging Telecommunications Technologies

当前位置： X-MOL 学术 › Trans. Emerg. Telecommun. Technol. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Dynamic Doppler prediction in high-speed rail using long short-term memory neural network
Transactions on Emerging Telecommunications Technologies ( IF 2.5 ) Pub Date : 2021-04-10 , DOI: 10.1002/ett.4269
Lei Xiong ₁ , Zhengyu Zhang ₂ , Dongpin Yao ₂

Affiliation

In the high-speed rail (HSR), wireless communication systems are suffering considerably from the huge Doppler shift caused by the high speed moving of the train. Moreover, the Doppler shift in HSR changes rapidly, and results in the poor Doppler prediction performance on pay-load symbols. In this paper, a novel Doppler prediction algorithm based on long short-term memory (LSTM) neural network is proposed. The proposed algorithm is enable to learn the regularity of the Doppler shift by the pretraining and tracking training, and can achieve better prediction performance for high speed moving than traditional algorithms without modification of the communication protocol.

中文翻译：

基于长短期记忆神经网络的高铁动态多普勒预测

在高铁 (HSR) 中，无线通信系统正遭受着列车高速移动引起的巨大多普勒频移的严重影响。此外，HSR 中的多普勒频移变化很快，导致对有效载荷符号的多普勒预测性能较差。本文提出了一种新的基于长短期记忆（LSTM）神经网络的多普勒预测算法。该算法通过预训练和跟踪训练来学习多普勒频移的规律，在不修改通信协议的情况下，可以达到比传统算法更好的高速运动预测性能。

更新日期：2021-04-10

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11