| 基于模糊k近邻的样本预选取的支持向量机分类算法 |
| |
| 引用本文： | 南光浩.基于模糊k近邻的样本预选取的支持向量机分类算法[J].延边大学理工学报,2009,35(3):263-265. |
| |
| 作者姓名： | 南光浩 |
| |
| 作者单位： | 延边大学工学院,计算机科学与技术系,智能信息处理研究室,吉林,延吉,133002 |
| |
| 摘 要： | 在支持向量机（SVM）方法中采用模糊☆近邻方法进行样本预选取，旨在保留最优分类超平面附近的样本点，去除远处样本点，使训练样本集减小，消除冗余，从而减小所需内存．实验结果表明，该方法无论是训练速度还是分类精度都远远好于单独的SVM分类器．
|
| 关 键 词： | 支持向量机 模糊k近邻 样本预选取 分类 |
Pre-selection Sample Method of Fuzzy KNN in Classify of Support Vector Machines |
| |
| NAN Guang-hao.Pre-selection Sample Method of Fuzzy KNN in Classify of Support Vector Machines[J].Journal of Yanbian University (Natural Science),2009,35(3):263-265. |
| |
| Authors: | NAN Guang-hao |
| |
| Affiliation: | NAN Guang-hao ( Intelligent Information Processing Laboratory, Department of Computer Science and Technology, College of Engineering, Yanbian University, Yanji 133002, China ) |
| |
| Abstract: | A sample pre-selection method of support vector machine （SVM） with Fuzzy k nearest neighbor （KNN） is proposed order to hold the samples nearing the supper plane, delete the samples far off the supper plane, decrease the training set and the storage. Experimental results show that the algorithm performs better than sole SVM in aspects of training and accuracy of classification. |
| |
| Keywords: | SVM Fuzzy KNN sample pre-selection classification |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
