海面短波地波通信中基于DNN神经网络的单样本极化滤波器预测研究

doi:10.3969/j.issn.0372-2112.2020.11.022

电子学报 ›› 2020, Vol. 48 ›› Issue (11): 2250-2257.DOI: 10.3969/j.issn.0372-2112.2020.11.022

海面短波地波通信中基于DNN神经网络的单样本极化滤波器预测研究

张嘉纹, 党小宇, 杨凌辉, 齐茹梦, 王萌

南京航空航天大学电子信息工程学院, 江苏南京 211106

收稿日期:2020-01-15 修回日期:2020-05-25 出版日期:2020-11-25
- 通讯作者:
- 党小宇
- 作者简介:
- 张嘉纹 女,1997年出生.现为南京航空航天大学硕士研究生.主要研究方向为海面无线信道建模、信号极化信息处理及极化滤波器设计研究.E-mail:17843103897@163.com
- 基金资助:
- 国家自然科学基金 (No.61971221，No.61971220）; 中央高校基本科研业务费专项资金资助 (No.2020104）; 南京航空航天大学研究生创新基地 (实验室）开放基金 (No.kfjj20190416）

Research on Single Sample Polarization Filter Based on Deep Neural Network in Short Ground-Wave Communication over the Sea Surface

ZHANG Jia-wen, DANG Xiao-yu, YANG Ling-hui, QI Ru-meng, WANG Meng

School of Electronic Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu 211106, China

Received:2020-01-15 Revised:2020-05-25 Online:2020-11-25 Published:2020-11-25
- Corresponding author:
- DANG Xiao-yu
- Supported by:
- National Natural Science Foundation of China (No.61971221, No.61971220); Fundamental Research Funds for the Central Universities (No.2020104); Open Fund of Postgraduate Innovation Base (laboratory) of Nanjing University of Aeronautics and Astronautics (No.kfjj20190416)

摘要/Abstract

摘要： 针对海面通信受大气噪声干扰严重的问题，该文提出一种基于DNN（Deep Neural Network）神经网络的单样本极化滤波器预测模型，研究其对海面短波地波通信链路中的大气噪声的抑制作用.与传统算法不同，DNN神经网络直接从大量输入数据获取信息间的非线性特性，并以此更新网络参数，通过对模型参数调整使得模型达到最优状态.选择三种脉冲成分比例不同的大气噪声进行仿真，结果表明传统算法与DNN网络模型在低信噪比约0~15dB时对信号的误码率影响基本一致，在高信噪比约超过15dB，误码率达到10^-4时，深度学习模型比传统算法所需信噪比显著提高约5dB.实验结果验证了神经网络在单样本极化滤波器预测方向的可行性与准确性，具有很好的实用参考价值.

关键词: 深度神经网络, 大气噪声, 单样本极化滤波器

Abstract: Aiming at the problem that the sea surface communication is seriously disturbed by atmospheric noise, this paper proposes a single sample polarization filter prediction model based on deep neural network, and studies its suppression effect on atmospheric noise in the sea surface short ground wave communication link. DNN neural network directly obtains the non-linear characteristics between information from a large amount of input data, which uses it to update the network parameters, and adjusts the model parameters to make the model reach the optimal state. Three types of atmospheric noise with different proportions of pulse components are selected for simulation. The results show that the traditional algorithm and the DNN network model have basically the same effect on the signal error rate when the signal-to-noise ratio is about 0~15dB. When the bit error rate reaches 10^-4, the deep learning model improves the signal-to-noise ratio by about 5dB compared with the traditional algorithm. The experimental results verify the feasibility and accuracy of the neural network in predicting the direction of the single-sample polarization filter coefficients, which has good practical value.

Key words: deep neural network, atmospheric noise, single sample polarization filter

中图分类号:

TN926

张嘉纹, 党小宇, 杨凌辉, 等. 海面短波地波通信中基于DNN神经网络的单样本极化滤波器预测研究[J]. 电子学报, 2020, 48(11): 2250-2257.

ZHANG Jia-wen, DANG Xiao-yu, YANG Ling-hui, et al. Research on Single Sample Polarization Filter Based on Deep Neural Network in Short Ground-Wave Communication over the Sea Surface[J]. Acta Electronica Sinica, 2020, 48(11): 2250-2257.

参考文献

[1] 张建飞,丁广,杨建东.海上云层和降水对船载高频段卫星通信的影响[J].电子学报,2018,46(2):381-386. ZHANG Jian-fei,DING Guang,YANG Jian-dong.Influence of ocean clouds and precipitation to shipborne high frequency band satellite communication[J].Acta Electronica Sinica,2018,46(2):381-386.(in Chinese)
[2] 刘西川,宋堃,高太长,胡云涛.复杂大气条件对微波传播衰减的影响研究[J].电子与信息学报,2018,40(1):181-188. LIU Xi-chuan,SONG Kun,GAO Tai-chang,HU Yun-tao.Research on the effect of complex atmospheric condition on microwave propagation attenuation[J].Journal of Electronics and Information Technology,2018,40(1):181-188.(in Chinese)
[3] 周万幸.天波超视距雷达发展综述[J].电子学报,2011,39(6):1373-1378. ZHOU Wan-xing.An overview on development of skywave over-the-horizon radar[J].Acta Electronica Sinica,2011,39(6):1373-1378.(in Chinese)
[4] 王玉珏.粗糙海面短波地波通信链路分析与计算[J].通信技术,2015,48(6):677-681. WANG Yu-jue.Analysis and calculation of short-wave ground wave communication link on rough sea surface[J].Journal of Electronics and Information Technology,2015,48(6):677-681.(in Chinese)
[5] 陈媛,刘金磊,孙奇福.SαS分布噪声环境下高分辨率二维DOA估计算法及快速实现[J].电子学报,2018,46(06):1384-1389. CHEN Yuan,LIU Jin-lei,SUN Qi-fu.A high resolution algorithm for 2d-doa estimation and its fast implementation in the presence of sαs distributed noise[J].Acta Electronica Sinica,2018,46(06):1384-1389.(in Chinese)
[6] 罗忠涛,卢鹏,张杨勇,张刚.抑制脉冲型噪声的限幅器自适应设计[J].电子与信息学报,2019,41(5):1160-1166. LUO Zhong-tao,PENG Lu,ZHANG Yang-yong,ZHANG Gang.Adaptive design of limiters for impulsive noise suppression[J].Journal of Electronics and Information Technology,2019,41(5):1160-1166.(in Chinese)
[7] BENAISSA A,ABDELMALEK A,FEHAM M.Improved reliability of power line communication under alpha-stable noise[A].Proceedings of 2017 International Conference on Electrical Engineering[C].Boumerdes,Algeria:2017.1-5.
[8] LAGUNA-SANCHEZ G,LOPEZ-GUERRERO M.On the use of alpha-stable distributions in noise modeling for PLC[J].IEEE Transactions on Power Delivery,2015,30(4):1863-1870.
[9] MAHMOOD A,CHITRE M.Optimal and near-optimal detection in bursty impulsive noise[J].IEEE Journal of Oceanic Engineering,2017,42(3):639-653.
[10] GHERARDELLI,M.Adaptive polarisation suppression of intentional radar disturbance[J].Radar Szgnal Process,IEE Processing F,1990,137(6):407-417.
[11] 毛兴鹏,刘永坦,邓维波.频域零相移多凹口极化滤波器[J].电子学报,2008,36(3):537-542. MAO Xing-peng,LIU Yong-tan,DENG Wei-bo.Frequency-domain zero-phase shift multi-notch polarization filter[J].Acta Electronica Sinica,2008,36(3):537-542.(in Chinese)
[12] Qiao X L,Jin M.Radio disturbance suppression for HF radar[J].IEE Proceedings-Radar Sonar and Navigation,2001,148(2):89-93.
[13] Xiaolin Q,Ming J,Xinpeng M.Atmospheric noise suppression for HF radar[A].CIE International Conference on Radar Proceedings (Cat No.01TH8559)[C].Beijing:2001.992-995.
[14] FRITSCHEK R,SCHAEFER R F,WUNDER G.Deep learning for channel coding via neural mutual information estimation[A].2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications[C].Cannes,France:2019.1-5.
[15] SOLTANI M,POURAHMADI V,MIRZAEI A,et al.Deep learning-based channel estimation[J].IEEE Communications Letters,2019,23(4):652-655.
[16] GRUBER T,CAMMERER S,HOYDIS J,et al.On deep learning-based channel decoding[A].201751st Annual Conference on Information Sciences and Systems (CISS)[C].Baltimore,MD,USA:2017.1-6.
[17] HAO Ye,LI G Y, JUANG B-H.Power of deep learning for channel estimation and signal detection in OFDM systems[J].IEEE Wireless Communications Letters,2018,7(1):114-117.

海面短波地波通信中基于DNN神经网络的单样本极化滤波器预测研究

Research on Single Sample Polarization Filter Based on Deep Neural Network in Short Ground-Wave Communication over the Sea Surface

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

[1]	王硕, 王坚, 王亚男, 宋亚飞. 一种基于特征融合的恶意代码快速检测方法[J]. 电子学报, 2023, 51(1): 57-66.
[2]	周奕涛, 张斌, 刘自豪. 基于多模态深度神经网络的应用层DDoS攻击检测模型[J]. 电子学报, 2022, 50(2): 508-512.
[3]	陈星宇, 叶锋, 黄添强, 翁彬, 陈家祯, 林文忠. 融合小型深度生成模型的显著性检测[J]. 电子学报, 2021, 49(4): 768-774.
[4]	黎毅达, 高发荣, 姚婷, 蔡利杰. 基于Fisher判别和GKF-RELM算法的多特征步态模式识别[J]. 电子学报, 2021, 49(10): 1993-2001.
[5]	崔子豪, 鲍长春. 基于广义合成分析和深度神经网络的自回归系数估计方法[J]. 电子学报, 2021, 49(1): 29-39.
[6]	袁文浩, 胡少东, 时云龙, 李钊, 梁春燕. 一种用于语音增强的卷积门控循环网络[J]. 电子学报, 2020, 48(7): 1276-1283.
[7]	袁文浩, 娄迎曦, 梁春燕, 夏斌. 利用生成噪声提高语音增强方法的泛化能力[J]. 电子学报, 2019, 47(4): 791-797.
[8]	徐少平, 李崇禧, 林官喜, 唐祎玲, 胡凌燕. 基于主成分分析与深度神经网络的快速噪声水平估计算法[J]. 电子学报, 2019, 47(2): 274-281.
[9]	陈楠, 鲍长春. 基于双耳线索编码原理的语音增强方法[J]. 电子学报, 2019, 47(1): 227-233.
[10]	孙晓, 潘汀. 基于兴趣区域深度神经网络的静态面部表情识别[J]. 电子学报, 2017, 45(5): 1189-1197.