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

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

doi:10.3969/j.issn.0372-2112.2020.06.022

您当前的位置：

首页 >

文章列表页 >

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

更新时间：2025-07-16

- Emitter Signal Modulation Recognition Based on Stacked Sparse Denoising Auto-Encoders
- Acta Electronica Sinica Vol. 48, Issue 6, Pages: 1198-1204(2020)
- 作者机构：
  
  中国人民解放军空军预警学院,湖北,武汉,430019
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2020.06.022
  CLC： TN957.51
- Published Online：25 June 2020，
  
  Published：2020
- 稿件说明：
移动端阅览
LI Dong-jin, YANG Rui-juan, LI Xiao-bai, et al. Emitter Signal Modulation Recognition Based on Stacked Sparse Denoising Auto-Encoders[J]. Acta Electronica Sinica, 2020, 48(6): 1198-1204.
DOI：

LI Dong-jin, YANG Rui-juan, LI Xiao-bai, et al. Emitter Signal Modulation Recognition Based on Stacked Sparse Denoising Auto-Encoders[J]. Acta Electronica Sinica, 2020, 48(6): 1198-1204. DOI： 10.3969/j.issn.0372-2112.2020.06.022.

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%.

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%.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multiple Classifier Based Walking Pattern Recognizing Algorithm Using Acceleration Signals

Emitter Signal Modulation Recognition Based on Kernel Collaborative Representation and Discriminative Projection

Related Author

LI Yue-xiang

LIU Yan

YUAN Tao

WANG Wen-jian

Related Institution

School of Computer and Information Technology, Shanxi University

Department of Automation,Tsinghua University

School of Computer and Information TechnologyShanxi UniversityTaiyuanShanxi 030006China

Department of AutomationTsinghua UniversityBeijing 100084China

⁰