| 基于核方法的分类算法比较研究 |
| |
| 引用本文： | 陈将宏.基于核方法的分类算法比较研究[J].甘肃联合大学学报(自然科学版),2009,23(6):67-69. |
| |
| 作者姓名： | 陈将宏 |
| |
| 作者单位： | 三峡大学,理学院,湖北,宜昌,443002 |
| |
| 摘 要： | 讨论基于核方法的分类算法的原理及其用于统计建模的一般步骤，研究了支持向量机和核Fisher线性判别分类算法的性能，数值实验表明基于核的分类算法与传统分类算法相比具有高精度，自适应的优点．
|
| 关 键 词： | 核方法 分类算法 特征空间 |
The Comparative Study of Classification Algorithm Based on Kernel methods |
| |
| CHEN Jiang-hong.The Comparative Study of Classification Algorithm Based on Kernel methods[J].Journal of Gansu Lianhe University :Natural Sciences,2009,23(6):67-69. |
| |
| Authors: | CHEN Jiang-hong |
| |
| Institution: | CHEN Jiang-hong ( College of Science,China Three Gorges University,Yichang 443002,China) |
| |
| Abstract: | The principle of classification algorithm which based on kernel methods was discussed,its general steps for statistical modeling were also discussed.The performance of the support vector machine and kernel fisher linear discriminate analysis classification were studied.numerical experiments show that kernel-based classification algorithm compared with the general classification algorithms has high accuracy and adaptive advantages. |
| |
| Keywords: | kernel methods classification algorithm feature spaces |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
