数据挖掘中决策树分类算法的研究与改进 |
| |
引用本文: | 但小容,陈轩恕,刘飞,柳德伟. 数据挖掘中决策树分类算法的研究与改进[J]. 人天科学研究, 2009, 0(2) |
| |
作者姓名: | 但小容 陈轩恕 刘飞 柳德伟 |
| |
作者单位: | 国网电力科学研究院 |
| |
摘 要: | 决策树分类算法是数据挖掘中一个重要的内容,而ID3算法又是决策树分类算法中的一种重要方法且被广泛应用。然而在实际应用过程中,现存的决策树算法也存在着很多不足之处,如计算效率低下、多值偏向等。为了解决这些问题,提出了一种基于ID3算法的加权简化信息熵算法,它提高了决策树的构建速度,减少了算法的计算运行时间,同时也克服了ID3算法往往偏向于选择取值较多的属性作为测试属性的缺陷。并且随着数据规模的增大,决策树的分类性能表现得越好。
|
关 键 词: | 数据挖掘 决策树 ID3算法 改进 加权简化信息熵 |
Research and Improvement on the Decision Tree Classification Algorithm of Data Mining |
| |
Affiliation: | Dan Xiaorong Chen Xuanshu Liu fei et al.; |
| |
Abstract: | Data algorithm is one of important contents in Data mining, ID3 algorithm is one important method in the technology of deci- sion tree classification and so is widely applied. While applied to the reality tasks, there is some issues in the most existent decision tree algorithms, such as: namely mufti-value bias,lower efficiently in computation etc. In order to overcome these disadvantages, this paper mainly introduces the information entropy power of simplification algorithm based on ID3. It can raise the s... |
| |
Keywords: | Data Mining Decision Tree ID3 Algorithm Improvement Information Entropy Power of Simplification |
本文献已被 维普 等数据库收录! |
|