| 一种基于NNIA多目标优化的代价敏感决策树构建方法 |
| |
| 引用本文： | 赵士伟,卓力,王素玉,沈兰荪.一种基于NNIA多目标优化的代价敏感决策树构建方法[J].电子学报,2011,39(10):2348-2352. |
| |
| 作者姓名： | 赵士伟 卓力 王素玉 沈兰荪 |
| |
| 作者单位： | 北京工业大学信号与信息处理研究室,北京,100124 |
| |
| 基金项目： | 国家自然科学基金(No.61003289); 北京市自然科学基金(No.4102008); 人力资源与社会保障部留学归国人员科技活动优秀类资助; 教育部留学归国人员科研启动基金 |
| |
| 摘 要： | 本文提出了一种基于非支配邻域免疫算法(NNIA,Nondominated Neighbor Immune Algorithm)多目标优化的代价敏感决策树构建方法.将平均误分类代价和平均测试代价作为两个优化目标,然后利用NNIA对决策树进行优化,最终获取了一组Pareto最优的决策树.对多个测试集的测试结果表明,与C4....
|
| 关 键 词： | 代价敏感 误分类代价 测试代价 多目标优化 决策树 |
| 收稿时间： | 2009-12-30 |
A Multi-Objective Optimization Based Constructing Cost-Sensitive Decision Trees Method |
| |
| ZHAO Shi-wei,ZHUO Li,WANG Su-yu,SHEN Lan-sun.A Multi-Objective Optimization Based Constructing Cost-Sensitive Decision Trees Method[J].Acta Electronica Sinica,2011,39(10):2348-2352. |
| |
| Authors: | ZHAO Shi-wei ZHUO Li WANG Su-yu SHEN Lan-sun |
| |
| Affiliation: | ZHAO Shi-wei,ZHUO Li,WANG Su-yu,SHEN Lan-sun(Signal and Information Processing Laboratory,Beijing University of Technology,Beijing 100124,China) |
| |
| Abstract: | A novel method of constructing the cost-sensitive decision trees based on multi-objective optimization is proposed in this paper.The average misclassification cost and the average test cost are treated as the two optimization objectives.NNIA(Nondominated Neighbor Immune Algorithm) is exploited to optimize the decision trees.And some Pareto decision trees are finally obtained.Experimental results show that,compared with the C4.5 algorithm and CSDB(Cost Sensitive Decision Tree) algorithm,the proposed method i... |
| |
| Keywords: | cost-sensitive misclassification costs test costs multi-objective optimization decision tree |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《电子学报》浏览原始摘要信息 |
|
点击此处可从《电子学报》下载全文 |
