基于多重分形特征的通信调制方式识别研究  

Communication Modulation Recognition Based on Multi-fractal Dimension Characteristics

作　　者：陈红[1] 蔡晓霞[1] 徐云[1] 刘文涛 

机构地区：[1]解放军电子工程学院 [2]解放军95915部队

出　　处：《电子与信息学报》2016年第4期863-869,共7页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(61571446);安徽省自然科学基金(KY13C152)~~

摘　　要：该文提出一种基于多重分形特征的数字通信信号调制方式识别新方法。对接收信号进行去噪预处理,基于2维数据阵列求取信号的广义维数和多重分形谱;详细讨论了权重因子q对多重分形谱的影响,提取了13个多重分形特征参数;设计了基于多重分形特征的支持向量机分类器对不同信号进行调制方式识别。仿真结果表明,该算法在低信噪比情况下具有很好的识别性能。A new modulation recognition algorithm of digital communication signals based on the multi-fractal dimension characteristics is proposed. Employing preprocessing the received signal, the generalized dimension and the multi-fractal spectrum can be calculated by 2D data array. The effect of multi-fractal spectrum due to the weighted factors q is discussed in detail, the 13 multi-fractal characteristic parameters are extracted. The Support Vector Machine（SVM） classifier based on the multi-fractal dimension characteristics is designed for recognition of different modulation signals. Simulation results show that the proposed method has a good recognition performance under low SNR.

关 键 词：调制方式识别 多重分形特征 广义维数 支持向量机 

分 类 号：TN92[电子电信—通信与信息系统]