| 基于主成分分析的决策树构造方法 |
| |
| 引用本文： | 孟凡荣,蒋晓云,田恬,施蕾,申丽君.基于主成分分析的决策树构造方法[J].小型微型计算机系统,2008,29(7). |
| |
| 作者姓名： | 孟凡荣 蒋晓云 田恬 施蕾 申丽君 |
| |
| 作者单位： | 1. 中国矿业大学,计算机学院,江苏,徐州,221008
2. 解放军理工大学,指挥自动化学院软件技术教研室,江苏,南京,210007 |
| |
| 摘 要： | 针对传统的ID3算法在选择分裂属性上对取值较多属性过分依赖的缺点,提出了基于主成分分析的决策树优化算法.该算法是通过主成分分析综合了信息增益和相关度系数来选择分裂属性.论文通过UCI提供的标准数据集,对优化算法进行测试,分析了优化算法的性能特点,验证了优化算法在分类正确率和执行效率上要优于ID3算法.
|
| 关 键 词： | 决策树 ID3 主成分分析 PCA-DT 主成分分析 决策树 构造方法 Principal Component Analysis Based Construction Method Tree 执行效率 正确率 分类 验证 算法的性能 优化算法 测试 数据集 标准 相关度系数 信息增益 分析综合 多属性 |
Decision Tree Construction Method Based on Principal Component Analysis |
| |
| MENG Fan-rong,JIANG Xiao-yun,TIAN Tian,SHI Lei,SHEN Li-jun.Decision Tree Construction Method Based on Principal Component Analysis[J].Mini-micro Systems,2008,29(7). |
| |
| Authors: | MENG Fan-rong JIANG Xiao-yun TIAN Tian SHI Lei SHEN Li-jun |
| |
| Affiliation: | MENG Fan-rong1,JIANG Xiao-yun1,TIAN Tian1,SHI Lei2,SHEN Li-jun21(College of Computer Science,China University of Mining , Technology,Xuzhou 221008,China)2(Institute of Comm, Automation,PLA University of Science , Technology,Nanjin 210007,China) |
| |
| Abstract: | In this paper,a decision tree optimization algorithm based on principal component analysis is proposed to overcome the disadvantage of ID3 that depended too much on attributes that had more values when chose splitting attributes.The algorithm used principal component analysis method to integrate information gain and correlation coefficient as the basis of the sequence of splitting attributes.The paper tested the optimization algorithm using the standard data sets provided by UCI.The characteristics of the o... |
| |
| Keywords: | decision tree ID3 principal component analysis PCA-DT |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
