苑霸^1,2,,,
姚萍¹,
郑天垚¹
①.中国科学院计算技术研究所 ??北京 ??100190
②.中国科学院大学 ??北京 ??100049
基金项目:中国科学院战略先导科技专项(A类)(XDA19020400)

详细信息

作者简介:苑霸：苑 ? 霸，男，中国科学院计算技术研究所硕士研究生，研究方向为数字信号处理、机器学习等。E-mail: yuanba@ict.ac.cn
姚萍：姚　萍，女，中国科学院计算技术研究所副研究员，硕士生导师，研究方向为数字信号处理与嵌入式系统
郑天垚，男，中国科学院计算技术研究所高级工程师，硕士生导师，研究方向为计算机系统结构、信号处理、遥感图像

通讯作者:苑霸? yuanba@ict.ac.cn

中图分类号:TN957.51

计量

文章访问数:1282
HTML全文浏览量:341
PDF下载量:160
被引次数:0

出版历程

收稿日期:2018-07-09
修回日期:2018-08-28
网络出版日期:2018-10-08

Radar Emitter Signal Identification Based on Weighted Normalized Singular-value Decomposition

YUAN Ba^1,2,,,
YAO Ping¹,
ZHENG Tianyao¹
①. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
②. University of Chinese Academy of Sciences, Beijing 100049, China
Funds:The Strategic Priority Research Program of the Chinese Academy of Sciences (XDA19020400)

More Information

Corresponding author:YUAN Ba, yuanba@ict.ac.cn

摘要
摘要:随着现代技术不断更新，雷达种类及相关技术得到不断发展，雷达辐射源信号的识别逐渐成为一个十分重要的研究领域。该文主要针对辐射源信号识别中的调制类型识别问题，从数据能量角度出发，在奇异值分解(Singular Value Decomposition, SVD)基础上进行优化，提出基于权重归一化奇异值分解特征提取算法。该文从奇异值分解的滤波效果、数据矩阵行数对分解结果的影响及不同分类模型识别效果等方面进行分析。实验结果表明该算法对常用雷达信号有较好滤波和识别效果，在–20 dB条件下滤波重构信号与原始信号余弦相似度值仍保持在0.94左右，在判别置信度$\alpha $为0.65条件下识别正确率仍维持在97%以上。此外实验还表明相对于传统PCA算法，基于权重归一化奇异值分解特征提取算法拥有更好的鲁棒性。
关键词:奇异值分解/
调制类型识别/
辐射源信号识别/
机器学习
Abstract:With the continuous advancement of modern technology, more types of radar and related technologies are continuously being developed, and the identification of radar emitter signals has gradually become a very important research field. This paper focuses on the identification of modulation types in radar emitter signal identification. We propose a weighted normalized Singular-Value Decomposition (SVD) feature extraction algorithm, which is based on the perspective of data energy and SVD. The filtering effect of complex SVD is analyzed, as well as the influence of the number of rows of data matrix on the decomposition results, and the recognition effect of different classification models. The experimental results show that the algorithm has better filtering and recognition effects on common radar signals. Under –20 dB, the cosine similarity values of the reconstructed and original signals remain at about 0.94, and the recognition accuracy remains above 97% under a confidence level $\alpha $ of 0.65. In addition, experiments show that the weighted normalized SVD feature extraction algorithm has better robustness than the traditional Principal Component Analysis (PCA) algorithm.
Key words:Singular Value Decomposition (SVD)/
Identification of modulation types/
The identification of radar emitter signals/
Machine learning



PDF全文下载地址:

https://plugin.sowise.cn/viewpdf/198_4544a66c-8e93-4fcb-b99a-9c5ed3bd01df_R18053