| 摘要: |
| 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。 |
| 关键词: QAM调制信号 自动识别 调制分类 高阶循环累积量 循环平
稳性 支持矢量机 |
| DOI： |
|
| 基金项目: |
|
| Hierarchical modulation classification algorithm based on higher-order cyclic cumulants and support vector machines |
| FENG Xiang,YUAN Hong-bo |
| () |
| Abstract: |
| A support vector machines(SVM) based hierarchical algorithm for the au
tomatic classification of QAM modulation signals is proposed. The algorithm util
izes the cyclostationary property of communication signals and presents classifi
cation features in cyclic cumulants domain. The algorithm is less complex comput
ationally and has faster classifier training speed compared with other algorithm
s. Moreover, it is robust to the presence of time delay and phase offsets. Inter
esting signals can also be classified under the presence of interference signals
. The efficiency of the proposed classification algorithm is verified via theore
tical analysis and extensive simulations. |
| Key words: QAM modulation signal automatic identification modulation classification higher
-order cyclic cumulants cyclostationary support vector machine |
