基于熵特征和支持向量机的调制识别方法  

Modulation recognition using entropy features and SVM

作　　者：李一兵[1] 葛娟[1] 林云[1] 

机构地区：[1]哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001

出　　处：《系统工程与电子技术》2012年第8期1691-1695,共5页Systems Engineering and Electronics

基　　金：国家重点基础研究发展计划(973计划)(61393010101-1);船舶工业国防科技预研项目(10J3.1.6);中央高校基本科研业务费专项资金(HEUCF100810)资助课题

摘　　要：通信信号调制识别在非合作通信领域是一项重要的研究课题。针对当前算法计算量大,能识别的调制类型少的特点,提出了一种基于熵特征和支持向量机(support vector machine,SVM)的调制识别新方法。该算法通过提取接收信号的多维熵特征,作为调制识别的特征参数,并利用基于二叉树的SVM作为分类器,对接收信号进行调制识别。除了信号的信噪比,该算法不需要信号带宽和载频等其他先验知识。理论分析与计算机仿真结果表明,该方法具有很高的识别率,计算量小,具有很好的应用价值。The modulation recognition of communication signals is an important research issue in non-coop- erative fields. A method based on entropy features and support vector machine （SVM） for modulation recogni- tion is put forward. Multidimensional entropy features are extracted as the input coefficients of the classifier. The performance of the binary tree based SVM classifier is investigated using these entropy features. Besides signal-to-noise ratio, the algorithm needs no further information for the received signal such as signal bandwidth or carrier frequency. Theoretical analysis and simulation results show that the algorithm is practically valuable for it s high recognition accuracy and less computation load.

关 键 词：调制识别 非合作通信 支持向量机 多维熵特征 

分 类 号：TN911[电子电信—通信与信息系统]