| 基于修正系数的决策树分类算法 |
| |
| 引用本文： | 狄文辉,李卿,楼新远.基于修正系数的决策树分类算法[J].计算机工程与设计,2008,29(24). |
| |
| 作者姓名： | 狄文辉 李卿 楼新远 |
| |
| 作者单位： | 1. 河南机电高等专科学校计算机科学与技术系,河南新乡,453002
2. 西南交通大学信息科学与技术学院,四川成都,610031 |
| |
| 基金项目： | 河南省基础与前沿技术研究计划基金项目
，
河南省高等学校青年骨干教师计划基金项目
，
河南省教育厅自然科学研究基金项目
|
| |
| 摘 要： | ID3算法是决策树算法中的经典算法,但存在多值偏向问题.一些改进的ID3算法虽避免了多值偏向问题,但多存在主观性强,没有考虑属性信息熵等问题.为了解决该问题,提出了一种基于修正系数的决策树分类算法MC.该算法利用修正系数降低取值个数多的属性的信息增益,并通过实验与ID3算法进行了比较,结果表明,当样本集中各属性取值个数不同时,算法MC在生成决策树的结点总数和分类准确率上明显优于ID3算法.
|
| 关 键 词： | 决策树 多值偏向 修正系数 ID3算法 |
Decision tree classification algorithm based on modified degree |
| |
| DI Wen-hui,LI Qing,LOU Xin-yuan.Decision tree classification algorithm based on modified degree[J].Computer Engineering and Design,2008,29(24). |
| |
| Authors: | DI Wen-hui LI Qing LOU Xin-yuan |
| |
| Affiliation: | DI Wen-hui1,LI Qing2,LOU Xin-yuan2(1.Department of Computer Science , Technology,Henan Mechanical , Electrical Engineering College,Xinxiang 453002,China,2.School of Information Science , Technology,Southwest Jiaotong University,Chengdu 610031,China) |
| |
| Abstract: | ID3 is the key algorithm of decision tree algorithm,but there is existing variety bias problem.The shortcoming of current algorithms for improved ID3 which are subjective to measure the attributes which are important or not and without regard to attributes information entropy is analyzed.For solving these problems,a decision tree algorithm based on modified degree is proposed.The main idea of the approach algorithm is using modified coefficient to reduce information gain of attributes which has many values.... |
| |
| Keywords: | decision tree variety bias modified coefficient ID3 algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
