通信信号分类算法研究  

Study on Classification Algorithm for Communication Signals

作　　者：冯祥[1] 贾承军[1] 梁伟洋[1] 

机构地区：[1]空军第一航空学院,河南信阳464000

出　　处：《通信技术》2010年第8期129-131,共3页Communications Technology

摘　　要：利用观测样本的高阶累积量特征,在累积量域内构造信号分类特征,采用支持矢量机作为分类器,在高维空间实现对GSM、CDMA和OFDM信号的分类。该算法通过提取观测样本的累积量的识别特征矢量以区分不同的信号类型,并将特征向量映射到高维空间中加以分类,首先在理论上分析了算法的正确性,并通过仿真实验进行了验证,结果表明,算法具有较好的推广能力,在较大的信噪比范围内对三种信号均有较高的识别率。An automatic classification algorithm for the communication signals is proposed. The algorithm presents high-order cumulants classification features in cumulants domain, and with support vector machines （SVM） as a classier, classifies GSM, CDMA and OFDM signals. The algorithm maps the classification features nonlinearly into the high dimension space and constructs the optimal separating hyperplane in the space for classifying the interesting signals. The efficiency of the proposed classification algorithm is verified via theoretical analysis and by extensive simulations. Simulation results show that the algorithm is of high popularization performance, and has fairly high correct classification ratios for the three signals in large SNR range.

关 键 词：信号分类 高阶累积量 支持矢量机 

分 类 号：TN911[电子电信—通信与信息系统]