基于核主成分分析的二次雷达脉冲信号初始特征提取

Initial Feature Extraction of Secondary Radar Pulse Signal Based on Kernel Principal Component Analysis

针对二次雷达脉冲信号的特征选择与分类问题进行研究,提出了一种基于核主成分分析(KPCA)的初始特征提取方法。根据二次雷达脉冲信号的特点,首先经过数据整编、预处理,获取样本的初始特征参数;然后利用KPCA方法对特征参数进行主成分组合,以消除信号特征间的相关性和压缩特征向量的维数,最后利用聚类工具进行分类。数学分析和可视化实验结果都表明这种分析方法是有效的。试验还表明,KPCA在特征选取方面性能优于PCA。

For the problem of secondary radar pulse signal feature selection and classification,a recognition method based on kernel principal component analysis( KPCA) is presented. According to the characteristic of pulse signal,the initial feature parameters are obtained using data preprocessing approach. Then the eliminating correlation and dimensionality reduction for these feature parameters are realized using a KPCA algorithm,which effectively supports character recognition algorithm. Both mathematical analysis and visual results show the efficiency and good performance of the proposed method. Experimental result also demonstrates that KPCA has a higher performance in nonlinear classified feature than principal component analysis( PCA).