| Tri-training算法中分类器组合的改进 |
| |
| 引用本文： | 李心磊,杨思春,彭月娥.Tri-training算法中分类器组合的改进[J].苏州科技学院学报(自然科学版),2014(2):52-56. |
| |
| 作者姓名： | 李心磊 杨思春 彭月娥 |
| |
| 作者单位： | 安徽工业大学计算机科学与技术学院,安徽马鞍山243032 |
| |
| 基金项目： | 安徽省高校自然科学研究重点项目（KJ2011A048） |
| |
| 摘 要： | Tri-training算法是半监督协同算法里的经典算法,该文针对算法中分类器的使用做了一些改进,由原先单一的分类器换成两个不同分类器的组合。使用SVM分类器和最大熵分类器的不同组合作为Tri-training算法里的三个分类器构成分类器模型,然后分别对稀疏型数据、密集型数据与原始Tri-training算法进行实验比较,从而验证改进的有效性。
|
| 关 键 词： | 半监督学习 SVM 最大熵 Tri-training算法 |
Improved combination of classifiers in Tri-training algorithm |
| |
| LI Xinlei,YANG Sichun,PENG Yuee.Improved combination of classifiers in Tri-training algorithm[J].Journal of University of Science and Technology of Suzhou,2014(2):52-56. |
| |
| Authors: | LI Xinlei YANG Sichun PENG Yuee |
| |
| Institution: | (School of Computer Science and Technology ,Anhui University of Technology, Ma＇anshan 243032, China) |
| |
| Abstract: | Tri-training algorithm is a classical algorithm in semi-supervised learning. In this paper, we have im-proved the use of classifiers by combining two different classifiers instead of only employing one. With the differ-ent combinations of SVM classifier and Maximum Entropy classifier, we formed three classifiers of Tri-training algorithm and shaped the experimental model. Then we compared sparse data and intensive data with the original Tri-training algorithm. The results have confirmed the validity of the improvement. |
| |
| Keywords: | SVM semi-supervised learning SVM maximum entropy Tri-training algorithm |
| 本文献已被 CNKI 维普 等数据库收录！ |
