基于动态聚类的MPSK信号调制分类

通信信号的自动识别技术受到日益广泛的重视，本文提出了一种新的MPSK信号调制分类算法，对截获接收机输出的频带MPSK信号在未知载波频率的情况下，通过对延迟乘积信号进行分析处理，进而得到与原信号调制类型一致的基带相位信号序列。在未知噪声类型的情况下，利用动态聚类算法对此基带相位信号序列求取最佳聚类数M，从而实现了MPSK信号的调制分类。理论分析和实测信号处理证明了本文提出的算法的可行性。

Modulation classification of MPSK signals based on dynamic clustering

Identification and classification techniques for digital communication signals are growing more and more important. In this paper, a new algorithm based on dynamic clustering is proposed for classification of MPSK signals. This method analyzes the product of original signal and delayed signal to obtain baseband sequence without knowing carrier. Then dynamic clustering algorithm is used to determine the optimal number of clusters. And modulation classification of MPSK signals is realized without knowing the distribution of noise. Theoretical analysis and practical signal processing justify the robusticity and the efficiency of the new classification algorithm.