| 考虑标记间依赖关系的多标记分类算法 |
| |
| 作者单位： | ;1.信阳师范学院计算机与信息技术学院;2.北京交通大学计算机与信息技术学院 |
| |
| 摘 要： | 提出了一种考虑标记间依赖关系的多标记分类算法.首先依据RAk EL算法将标记集合划分为若干子集,然后在子集内部应用概率分类器链算法训练分类器.这样不仅充分考虑了标记间的依赖关系,而且对标记进行分组,从而提高了分类的性能.在5个数据集上与其他经典算法进行了对比实验,结果表明本文所提算法可显著提高分类性能.
|
| 关 键 词： | 数据挖掘 分类 多标记 依赖关系 |
Multi-label Classifier Using the Dependency among Labels |
| |
| Affiliation: | ,College of Computer and Information Technology,Xinyang Normal University,College of Computer and Information Technology,Beijing Jiaotong University |
| |
| Abstract: | A multi-label classifier considering the dependency among labels was proposed. The label set was divided into several subsets based on RAk EL algorithm. Then,a classifier was built on each subset using probabilistic classifier chain. By experimental evaluations on five datasets,the results showed that the proposed algorithm achieved better performance than previous methods. |
| |
| Keywords: | data mining classification multi-label dependence relationship |
| 本文献已被 CNKI 等数据库收录！ |
|
