| 一种新的半监督支持向量机 |
| |
| 引用本文： | 王红蔚,席红旗,孔波. 一种新的半监督支持向量机[J]. 郑州大学学报(自然科学版), 2012, 0(3): 66-68 |
| |
| 作者姓名： | 王红蔚 席红旗 孔波 |
| |
| 作者单位： | [1]河南教育学院数学系,河南郑州450046 [2]河南教育学院信息技术系,河南郑州450046 |
| |
| 基金项目： | 河南省基础与前沿技术研究项目,编号122300410229; 河南省教育厅自然科学基金资助项目,编号12B110005 |
| |
| 摘 要： | 在模式识别中,采取支持向量机对有类别标签样本分类是非常有效的,但在实际应用中,对样本进行标记并不是一件容易的工作.通过综合利用有类别标签和无类别标签样本信息构造目标函数和约束条件,借助二次规划模型提出了一种新的半监督支持向量机,从而提高了仅依靠有类别标签样本支持向量机的分类准确率.
|
| 关 键 词： | 支持向量机 二次规划 无标签 半监督 |
A New Semi-supervised Support Vector Machine |
| |
| WANG Hong-wei,XI Hong-qi,KONG Bo. A New Semi-supervised Support Vector Machine[J]. Journal of Zhengzhou University (Natural Science), 2012, 0(3): 66-68 |
| |
| Authors: | WANG Hong-wei XI Hong-qi KONG Bo |
| |
| Affiliation: | 1.Department of Mathematics,Henan Institute of Education,Zhengzhou 450046,China; 2.Department of Information Technology,Henan Institute of Education,Zhengzhou 450046,China) |
| |
| Abstract: | Support vector machines（SVMs） were effective in various areas,especially in pattern classification.A quadratic program model of classifying unlabeled and labeled data was presented by constructing a new objective function and constraints.Based on this model,a new algorithm of semi-supervised learning was presented to improve the accuracy of SVMs when a rarely labeled data appeared. |
| |
| Keywords: | SVM quadratic programming unlabeled data semi-supervised learning |
| 本文献已被 维普 等数据库收录！ |
|
