| 用改进核函数提高SVM的雷达目标识别率 |
| |
| 引用本文： | 许秀英 盛卫星. 用改进核函数提高SVM的雷达目标识别率[J]. 现代雷达, 2005, 27(10): 53-56 |
| |
| 作者姓名： | 许秀英 盛卫星 |
| |
| 作者单位： | [1]南京理工大学电光学院,南京210094 [2]福州大学物理信息学院,福州350002 |
| |
| 摘 要： | 对支持向量机中的高斯核进行了改进,利用改进的高斯核构造了一维高分辨率距离像的雷达目标识别算法,并将幂变换引入预处理过程.该技术提高了识别率,减少了识别时间;同时对所完成的目标识别算法的性能进行了评估,从方位角大小、信噪比和训练数据大小三个方面验证了该算法的稳健性.
|
| 关 键 词： | 雷达目标识别 一维高分辨率距离像 支持向量机 |
| 收稿时间： | 2004-10-12 |
| 修稿时间： | 2005-02-16 |
Improvement of Radar Target Recognition Based on an Improved Support Vector Machine |
| |
| XU Xiu-ying. Improvement of Radar Target Recognition Based on an Improved Support Vector Machine[J]. Modern Radar, 2005, 27(10): 53-56 |
| |
| Authors: | XU Xiu-ying |
| |
| Affiliation: | 1. School of Electronic Engineering and Optoelectronic Techniques, Nanjing University of Science and Technology, Nanjing 210094, China;2. College of Physics and Information Engineering, Fuzhou University, Fuzhou 350002, China |
| |
| Abstract: | An improved Gaussian kernel in support vector machine(SVM) is proposed.A classification algorithm for high resolution range profile(HRRP) based on this improved support vector machine is introduced.The power transformation technique is applied in this algorithm.Experiment results show that the recognition rate is improved and the computation time is reduced by using these techniques.The performance of the algorithm is evaluated in terms of azimuth angle size,signal-noise ratio and training set size,and the stability of the algorithm is verified. |
| |
| Keywords: | radar target recognition high resolution range profile support vector machine |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《现代雷达》浏览原始摘要信息 |
|
点击此处可从《现代雷达》下载全文 |
