电子学报 ›› 2020, Vol. 48 ›› Issue (6): 1198-1204.DOI: 10.3969/j.issn.0372-2112.2020.06.022

• 学术论文 • 上一篇    下一篇

基于栈式稀疏降噪自编码网络的辐射源调制识别

李东瑾, 杨瑞娟, 李晓柏, 董睿杰   

  1. 中国人民解放军空军预警学院, 湖北武汉 430019
  • 收稿日期:2019-08-19 修回日期:2019-11-17 出版日期:2020-06-25 发布日期:2020-06-25
  • 作者简介:李东瑾 男,1992年出生,四川广元人,空军预警学院博士研究生,主要研究方向为一体化系统智能应用. E-mail:li_dong_jin@163.com
    杨瑞娟 女,1964年出生,四川中江人, 空军预警学院教授、博士生导师,主要研究方向为雷达通信一体化及雷达组网. E-mail:ruijuany@sohu.com
    李晓柏 男,1983年出生,甘肃陇西人,空军预警学院讲师、博士.主要研究方向为雷达通信一体化及波形设计. E-mail:lxb2cici@163.com
    董睿杰 男,1995年出生,新疆库尔勒人, 硕士.主要研究方向为一体化系统智能应用. E-mail:drjkuw@126.com
  • 基金资助:
    国防科技创新特区基金(No.17H86304ZT00302201)

Emitter Signal Modulation Recognition Based on Stacked Sparse Denoising Auto-Encoders

LI Dong-jin, YANG Rui-juan, LI Xiao-bai, DONG Rui-jie   

  1. PLA Air Force Early Warning Academy, Wuhan, Hubei 430019, China
  • Received:2019-08-19 Revised:2019-11-17 Online:2020-06-25 Published:2020-06-25

摘要: 针对辐射源识别中噪声敏感和识别能力不足等问题,提出了一种基于核空间时频特征与栈式稀疏降噪自编码网络的识别系统.通过时频变换、稀疏域降噪和核空间降维投影降低噪声干扰和特征冗余,基于降噪自编码与稀疏自编码思想构建栈式稀疏降噪自编码识别网络.实验结果表明系统在识别率和时效性上综合性能最优,能够显著降低噪声敏感性,低信噪比环境下适应性较强.当信噪比为-12dB时,系统对8类辐射源信号的整体平均识别率达到96.75%.

关键词: 辐射源识别, 稀疏降噪自编码, 时频特征, 核映射, 批量随机梯度下降法, dropout正则化

Abstract: To enhance the classification performance and noise sensitivity of emitter signal recognition,a recognition system based on kernel space time-frequency feature and stacked sparse denoising auto-encoders (SSDAE) is proposed.Firstly,the noise interference and feature redundancy reduced by time-frequency transform,sparse-domain denoising and kernel space dimensionality reduction.Then,it is based on the idea of sparse auto-encoder (SAE) and denoising auto-encoder (DAE),an SSDAE based recognition network is constructed.Experimental results show that the system has the best comprehensive performance in recognition rate and time efficiency,which can significantly reduce noise sensitivity and improve low SNR environment adaptability.When the SNR is -12dB,the overall average recognition rate of the system for the 8 types of emitter signals reaches 96.75%.

Key words: emitter signal recognition, sparse denoising auto-encoder, time-frequency feature, kernel mapping, mini-batch stochastic gradient descent method (MSGD), dropout regularization

中图分类号: