基于高阶循环累积量和支持矢量机的分级调制分类算法

利用观测样本的高阶循环累积量特征，提出一种基于支持矢量机的分级调制分类算法，实现了对QAM调制信号的自动识别。该算法具有较快的分类器训练速度和较低的复杂度，对时延和相位旋转具有稳健性，并可在干扰环境下实现对感兴趣信号调制类型的识别。理论分析和仿真结果均证明了算法的正确性和有效性。

Hierarchical modulation classification algorithm based on higher-order cyclic cumulants and support vector machines

A support vector machines(SVM) based hierarchical algorithm for the automatic classification of QAM modulation signals is proposed. The algorithm utilizes the cyclostationary property of communication signals and presents classification features in cyclic cumulants domain. The algorithm is less complex computationally and has faster classifier training speed compared with other algorithms. Moreover, it is robust to the presence of time delay and phase offsets. Interesting signals can also be classified under the presence of interference signals. The efficiency of the proposed classification algorithm is verified via theoretical analysis and extensive simulations.