| 一种改进的决策树分类算法研究 |
| |
| 引用本文： | 吴碧霞.一种改进的决策树分类算法研究[J].成都大学学报(自然科学版),2011,30(4):335-338. |
| |
| 作者姓名： | 吴碧霞 |
| |
| 作者单位： | 闽北职业技术学院信息与工程系,福建南平,353000 |
| |
| 摘 要： | 传统的ID3决策树算法存在诸多不足,如计算效率低、多值偏向等,对此,提出了属性值空缺、多值属性的选择以及属性选择标准方面的改进方案,并将加权熵和简化熵引入决策树算法以改进传统ID3算法.实验结果表明,改进后的算法在整体性能方面较目前广泛应用的ID3算法有更优秀的性能表现.
|
| 关 键 词： | 决策树 ID3 加权简化熵 数据挖掘 |
Research on Classification Algorithm of One Improved Decision Tree |
| |
| WU Bixia.Research on Classification Algorithm of One Improved Decision Tree[J].Journal of Chengdu University (Natural Science),2011,30(4):335-338. |
| |
| Authors: | WU Bixia |
| |
| Institution: | WU Bixia(Department of Information and Engineering,Minbei Voctional and Technical College,Nanping 353000,China) |
| |
| Abstract: | The traditional decision tree ID3 algorithm has many disadvantages,such as low computational efficiency,variety bias and so on.A scheme was proposed to improve attribute value vacancy,multi-valued attribute selection and attribute selection criteria and weighted entropy and simplified entropy were introduced into decision tree algorithm to improve traditional ID3 algorithm.The experimental results show that the improved algorithm has more excellent performance than present extensive use ID3 algorithm in terms of overall performance. |
| |
| Keywords: | decision Tree ID3 weighted simplified entropy data mining |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
