基于LSTM神经网络的QPSK智能接收机设计

doi:10.11896/jsjkx.230200219

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 230200219-5.doi: 10.11896/jsjkx.230200219

基于LSTM神经网络的QPSK智能接收机设计

朱力¹, 韩会梅¹, 翟文超²

1 浙江工业大学信息工程学院杭州 310023
2 中国计量大学信息工程学院杭州 310018

发布日期:2023-11-09
通讯作者: 韩会梅(hmhan1215@zjut.edu.cn)
作者简介:(zhu67805@163.com)
基金资助:
国家自然科学基金(62001419)

Design of QPSK Intelligent Receiver Based on LSTM Neural Network

ZHU Li¹, HAN Huimei¹, ZHAI Wenchao²

1 College of Information Engineering,Zhejiang University of Technology,Hangzhou 310023,China
2 College of Information Engineering,China Jiliang University,Hangzhou 310018,China

Published:2023-11-09
About author:ZHU Li,born in 2002.His main research interests include communication receiver and deep learning.
HAN Huimen,born in 1990,Ph.D,gra-duate supervisor.Her main research interests include random access schemes for massive MIMO systems,machine-to-machine communications,machine learning,intelligent reflecting surface,and federated learning.
Supported by:
National Natural Science Foundation of China(62001419).

摘要/Abstract

摘要： 针对正交相移键控(Quadrature Phase Shift Keying,QPSK)接收机检测信号准确率低以及复杂度高的问题,提出了一种基于长短期记忆(Long Short-term Memory,LSTM)神经网络的QPSK智能接收机设计方案。该方案中的神经网络模型由LSTM和全连接层构成,其利用LSTM提取接收信号的时间相关性,具有较低复杂度。仿真实验结果表明,在加性高斯白噪声、同相和正交( Inphase and Quadrature,IQ)失衡、频率偏差信道因素影响下,与现有QPSK接收机相比,所提出的QPSK智能接收机显著提高了检测性能。

关键词: 深度学习, 长短期记忆神经网络, 智能接收机, QPSK调制

Abstract: To solve the problem of low detection accuracy and high complexity of quadrature phase shift keying(QPSK) receiver,this paper proposes a QPSK intelligent receiver based on long short-term memory(LSTM) neural network.The proposed intelligent receiver consists of LSTM and fully connected layers,which employs the LSTM to capture the temporal correlation of the received signal.Furthermore,the proposed intelligent receiver has low complexity.Simulation results show that,compared with the existing QPSK receivers,the proposed QPSK intelligent receiver significantly improves detection performance in the scenarios of additive Gaussian white noise,inphase quadrature imbalance and frequency deviation channel.

Key words: Deep learning, Long short-term memory neural network, Intelligent receiver, QPSK modulation

中图分类号:

TN919.3

朱力, 韩会梅, 翟文超. 基于LSTM神经网络的QPSK智能接收机设计[J]. 计算机科学, 2023, 50(11A): 230200219-5. https://doi.org/10.11896/jsjkx.230200219

ZHU Li, HAN Huimei, ZHAI Wenchao. Design of QPSK Intelligent Receiver Based on LSTM Neural Network[J]. Computer Science, 2023, 50(11A): 230200219-5. https://doi.org/10.11896/jsjkx.230200219

参考文献

[1]MILEANT A,HINEDI S.On the effects of phase jitter onQPSK lock detection[J].IEEE Transactionson Communications,1993,41(7):1043-1046.
[2]XIA J J,DENG D,FAN D.A note on implementation methodo-logies ofdeep learning-based signal detection for conventional MIMO transmitters[J].IEEE Transactions on Broadcasting,2020,66(3):744-745.
[3]ZHANG Y B,WANG J,SUN J L,et al.CV-3DCNN:complex-valued deep learning for CSI prediction in FDD massive MIMO systems[J].IEEE Wireless Communications Letters,2021,10(2):266-270.
[4]WANG J,GUI G,OHTSUKI T,et al.Compressive sampled CSI feedback method based on deep learning for FDD massive MIMO systems[J].IEEE Transactions on Communications,2021,69(9):5873-5885.
[5]HUANG H J,SONG Y W,YANG J,et al.Deep-learning-basedmillimeter-wave massive MIMO for hybrid precoding[J].IEEE Transactions on Vehicular Technology,2019,68(3):3027-3032.
[6]MA W Y,QI C H,ZHANG Z C,et al.Sparse channel estimationand hybrid precoding using deep learning for millimeter wave massive MIMO[J].IEEE Transactions on Communications,2020,68(5):2838-2849.
[7]FANG L,WU L.Deep learning detection method for signal demodulation in short range multipath channel[C]//2017 IEEE 2ndInternational Conference on Opto-Electronic Information Processing (ICOIP).2017:16-20.
[8]SHENTAL O,HOYDIS J.“Machine LLRning”:Learning tosoftly demodulate[J].arXiv:1907.01512,2019.
[9]NARIMAN F,ANDREA G.Neural network detection of data sequences in communication systems[J].IEEE Transactions on Signal Processing,2018,66(21):5663-5678.
[10]XU W,ZHONG Z,BE’ERY Y,et al.Joint neural networkequalizer and decoder[C]//2018 15th International Sympo-sium on Wireless Communication Systems (ISWCS).2018:1-5.
[11]ZHENG S,CHEN S,YANG X.DeepReceiver:A Deep Learning-Based Intelligent Receiver for Wireless Communications in the Physical Layer[J].IEEE Transactions on Cognitive Communications and Networking,2021,7(1):5-20.
[12]HOCHREITER S,SCHMIDHUBER J.Long Short-Term Me-mory[J].Neural Computation,1997,9:1735-1780.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于LSTM神经网络的QPSK智能接收机设计

Design of QPSK Intelligent Receiver Based on LSTM Neural Network

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

Metrics

本文评价

推荐阅读 0