欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
抽取有效鉴别特征是雷达一维高分辨距离像识别的关键．基于统计学习理论的核化原理，提出一种新的鉴别特征提取方法——核最优变换与聚类中心算法．该算法通过非线性变换，将数据映射到，陔空间，在核空间执行最优变换与聚类中心算法，能够提取一维距离像的稳健非线性鉴别特征．同时，基于训练样本在核空间所张成的子空间的一组基，给出一种快速计算方法，提高了特征提取速度．基于微波暗室实测数据的实验表明了该方法的有效性．
英文摘要：
How to extract effective discriminant features is the key problem for radar automatic target recognition based on high resolution range profile （HRRP）. A novel method for extracting discriminant features by using kernel methods, kernel optimal transformation and cluster centers algorithm （KOT-CC）, is presented. In KOT-CC, all data are mapped to a kernel space via some nonlinear mapping, and the optimal transformation and cluster centers （OT- CC） is performed in the kernel space. KOT-CC is a powerful technique for extracting nonlinear discriminant features. A fast algorithm for KOT-CC is also proposed based on a basis of the sub-space which is spanned by the training samples mapped onto the kernel space, which can improve the efficiency of the feature extraction process. Experimental results using range profiles from microwave unreflected chamber show the effectiveness of the proposed algorithm.
同期刊论文项目
同项目期刊论文
Pattern Expression Nonnegative Matrix Factorization: algorithm and Applications to Blind Source Sepa
期刊信息
位置：