基于Fisher判别字典学习的辐射源调制特征识别  

Emitter Signal Modulation Feature Recognition Based on Fisher Discrimination Dictionary Learning

作　　者：吴笑天 王星[1] 王志鹏 周一鹏[1] 陈游[1] WU Xiao-tian;WANG Xing;WANG Zhi-peng;ZHOU Yi-peng;CHEN You(Aeronautics and Astronautics Engineering College, Air Force Engineering University, Xi＇an 710038, Shaanxi, China;Unit 94895 of PLA, Zhangzhou 363000, Fujian, China)

机构地区：[1]空军工程大学航空航天工程学院 [2]94895部队

出　　处：《兵工学报》2018年第3期553-559,共7页Acta Armamentarii

基　　金：航空科学基金项目(20152096019)

摘　　要：针对基于字典的信号调制类型识别方法中解析字典原子形态单一、无法与复杂辐射源信号最优匹配的问题,提出一种基于Fisher判别准则的字典学习方法。对辐射源信号进行时频分析,借鉴图像处理的方法提取信号时频特征列向量,在字典训练过程中加入信号调制类型信息,根据Fisher准则训练字典,使字典原子类间距离最大同时类内距离最小,以增强字典的识别性能;通过仿真分析Fisher判别字典的识别性能以及原子个数对字典性能的影响。研究结果表明:该方法相比于解析字典法和无监督字典法,具有更好的识别性能,在低信噪比时识别性能突出、抗噪声干扰性能好;综合考虑识别性能和计算量,当字典原子数取20时该方法性能最优。The limited forms of atoms in analytical dictionary lead to sub-optimal matching of atoms and complex emitter signal,resulting in low recognition rate of signal modulation. A dictionary learning method based on Fisher discrimination criterion is proposed to improve the recognition efficiency. The timefrequency transformation of emitter signal is made. The feature vectors are extracted from time-frequency graph using image processing method,which are added class labels. In the dictionary training,the Fisher criterion with small within-class scatter and big between-class scatter is introduced,by which the dictionary not only represents signal more suitably,but also owns better classification performance. The simulated result proves that,compared to analytical dictionary and non-supervision dictionary,the proposed method can obtain a better recognition rate,especially under low SNR. For the atom number Ns= 20,Fisher discrimination dictionary can achieve a pretty good balance in recognition rate and calculation amount.

关 键 词：辐射源信号 调制特征 FISHER判别 字典学习 时频分析 

分 类 号：TN911.72[电子电信—通信与信息系统]