|
|||||
|
|
| 基于主成分和支持向量机的降维和模式分类 | |
| 引用本文： | 何晓桃,郑文丰,宋晖. 基于主成分和支持向量机的降维和模式分类[J]. 淮阴工学院学报, 2011, 20(1): 32-35 |
| 作者姓名： | 何晓桃 郑文丰 宋晖 |
| 作者单位： | 1. 广东工业大学计算机学院,广州,510006 2. 广东省科普信息中心,广州,510006 3. 华南师范大学物理与电信工程学院,广州,510006 |
| 基金项目： | 广东省自然科学基金项目 |
| 摘 要： | 首先讨论主成分分析和支持向量机的基本思想和实现过程,由于主成分分析PCA方法具备降维的功能,而支持向量机SVM方法又具有高分类准确率的优点,尝试将两者结合起来进行模式分类,最终经过实验验证获得成功.采用UCI数据库中的wine数据库分别对PCA、SVM、主成分和支持向量机结合的模式分类这三种方法进行实验仿真和比较,并取... |
| 关 键 词： | 主成分分析法 支持向量机 模式识别 |
Dimensionality Reduction and Pattern Classification Method Based on the SVM and PCA |
|
| HE Xiao-tao,ZHENG Wen-feng,SONG Hui. Dimensionality Reduction and Pattern Classification Method Based on the SVM and PCA[J]. Journal of Huaiyin Institute of Technology, 2011, 20(1): 32-35 | |
| Authors: | HE Xiao-tao ZHENG Wen-feng SONG Hui |
| Affiliation: | 1.Faculty of Computer Science,Guangdong University of Technology,Guangzhou 510006,China; 2.Guangdong Science ＆ Information Center,Guangzhou 510006,China; 3.School of Physics ＆ Telecommunication Engineering,South China Normal University, Guangzhou 510006,China) |
| Abstract: | The basic theory and realization of principal component analysis and supported vector machines are discussed in this paper.A dimensionality reduction and pattern classification method based on the SVM and PCA are proposed because of dimensionality reduction of PCA and high classification accuracy of SVM.The three methods are carried out through simulation experiments with database of UCI,and achieved more satisfactory results. |
| Keywords: | principal component analysis supported vector machine pattern identification |
| 本文献已被 维普 万方数据 等数据库收录！ | |