基于分形维数的数字调制信号识别  

Digital Modulation Signal Identification Based on Fractal Dimension

作　　者：刘文涛[1] 陈红[1] 蔡晓霞[1] 刘俊彤[1] 

机构地区：[1]解放军电子工程学院,合肥230037

出　　处：《火力与指挥控制》2014年第10期88-90,94,共4页Fire Control & Command Control

摘　　要：在复杂的电磁环境下,如何快速准确地对低信噪比下的常见通信信号进行较全面的识别是一个亟待解决的问题。在对信号分形维数仿真讨论的基础上,提出了一种新的通信信号识别方法。首先,对接收到的信号进行预处理,然后提取其盒维数和信息维数,将两者作为识别的特征参数,最后基于支持向量机实现未知信号的识别。由仿真结果分析可知:预处理后的信号序列的盒维数和信息维数分离度高且受噪声和信号参数的影响小,识别结果较好。在信噪比为5 dB时,不同调制类型信号间的识别准确率最低为87%。Under the complex electromagnetic environment,how to quickly and accurately identify constant communication signals with a low signal to noise rate is a need be solved question. An identification method of communication signals is proposed on the basis of experiments and analysis. The received signal is pretreatment firstly,then the box dimension and information dimension are extracted and they are used as sorting characteristics. Finally,the sorting is completed by support vector machine algorithm. Simulation results show that box dimension and information dimension of the pretreatment signals are distinguishable and they are not sensitive to noise and signal parameters,and the lowest sorting rate of different signal is 87%at SNR=5 dB.

关 键 词：通信信号 盒维数 信息维数 识别 

分 类 号：TN92[电子电信—通信与信息系统]