摘要
通信信号的个体识别是近年来非合作通信领域一个重要研究课题.根据瞬态信号的非线性特征,采用递归图的分析方法提取瞬态信号的起始时刻,然后采用小波变换进行特征提取,在此基础上采用遗传算法挑选出分辨能力强的特征,利用支持向量机分类器实现对通信辐射源信号的个体识别.实验结果表明该方法用较少的特征获得较高的正确识别率,正确识别率大于90%.
Individual communication signals identification is an important issue in the field of communication reconnaissance in recent years. The recurrence plot method is proposed to detect the start-up point of the transient signals, which is based on the nonlinear characteristics of the transient signal. Wavelet transform is used to extract features from the transmitters. The most discriminatory features are selected from a large number of wavelet transform features by genetic algorithms, and Support Vector Machines (SVM) are used to realize the individual identification. Experimental results show that the introduced method achieves good accuracy recognition rate in terms of a little features as reference, with the accuracy recognition being more than 90%.
出处
《西安电子科技大学学报》
EI
CAS
CSCD
北大核心
2009年第4期736-740,共5页
Journal of Xidian University
基金
国家级重点实验室基金资助(9140C13050108DZ46)
关键词
辐射源识别
细微特征
特征选择
小波变换
遗传算法
transmitter identification
fine feature
feature selection
wavelet transforms
genetic algorithms