摘要
针对单通道QPSK-16QAM时频重叠双信号,提出了一种利用接收信号二、四、六阶循环累积量(HOCCs)构建分类特征的调制识别方法。选用支持向量机(SVM)作为系统的分类器,与已有方法相比,该算法识别性能更趋稳健。当数据长度取得100个待识别信号码元时,可以在较低信噪比下实现对备选信号准确的识别。仿真试验证实了算法的有效性。
To solve the problems in modulation recognition for time-frequency overlapped two-signal combining QPSK with 16QAM in a single channel, a novel algorithm is proposed that adopts the combination of 2nd,4th, 6th cyclic cumulants and establishes some robust classification features. Designing a SVM classifier can map the 2-D features to higher dimension super-space. Compared with other methods, it has more robust performance. When the input data is sufficient, the algorithm can classify the above two-signal properly in low SNR. It is verified that the proposed algorithm is reasonable and efficient with experiment results
出处
《电子信息对抗技术》
2009年第6期14-18,共5页
Electronic Information Warfare Technology