一种基于支持向量机的分层调制识别方法

A Novel Hierarchical Digital Modulation Recognition Method Using Support Vector Machines

提出了一种新的在高斯白噪声条件下基于支持向量机的分层调制识别方法。其中选取信号的4阶、6阶累积量作为分类特征向量,并利用支持向量机作为分类器对其进行分层调制分类。该方法相比其他非分级调制识别方法具有较低的计算复杂度和较快的分类器训练速度。理论分析和仿真结果均证明了算法的正确性和有效性。

This paper presents a novel method based on support vectors machines for recognition of digital modulation signals in the presence of additive white Gaussian noise. The fourth and sixth order cumulants of the received signals are used as the classification vectors and support vector machines as the classifiers. This hierarchical method has the advantages over other non-hierarchical methods of less complex computation and faster classifier training speed. The efficiency of the proposed classification algorithm is verified via theoretical analysis and extensive simulations.