Analysis and improved implementation of decision tree algorithms

doi:10.3778/j.issn.1002-8331.2010.13.041

Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (13): 139-141.DOI: 10.3778/j.issn.1002-8331.2010.13.041

• 数据库、信号与信息处理 • Previous Articles Next Articles

Analysis and improved implementation of decision tree algorithms

GONG Gu¹，HUANG Yong-qing¹，HAO Guo-sheng^1，2

1.College of Computer Science and Technology，Xuzhou Normal University，Xuzhou，Jiangsu 221116，China
2.College of Information and Electronic Engineering，China University of Mining and Technology，Xuzhou，Jiangsu 221008，China

Received:2008-10-23 Revised:2008-12-22 Online:2010-05-01 Published:2010-05-01
Contact: GONG Gu

决策树算法的优化研究

巩固¹，黄永青¹，郝国生^1，2

1.徐州师范大学计算机科学与技术学院，江苏徐州 221116
2.中国矿业大学信息与电气工程学院，江苏徐州 221008

通讯作者: 巩固

Abstract

Abstract: In order to effectively deal with the problems that the training error and test error are comparatively high when decision tree is built based on C4.5 and C5.0 decision tree algorithms，three improved strategies are presented.The improved strategies are as follows：Attribute correlation that can not only remove irrelevant features ，also can find redundant feature with high feature correlation，is to quantify the correlation between attribute and concept； pruning strategy adopts appropriate confidence to good purpose，then reduces the attribute number and the different value of each attribute assuring the feasibility and effectiveness of the decision tree； a variation of the Chi2 algorithm is proposed to perform attribute discretization and selection great exactly.The improved strategies are applied to the Breast-cancer data and the simulation validates their efficiency.Through experiment testing，the improved algorithm can construct the better accuracy of classification compared with the classical decision tree algorithms.

Key words: attribute correlation, attribute reduction, pruning strategy, discretization, Chi2 algorithm

摘要： 针对决策树C4.5/5.0分类算法及改进的算法在创建决策树时训练误差率和校验误差率相对较高的缺点，提出一些改进策略，即利用属性相关性进行属性约简与度量以达到解决属性集合中的冗余属性，采用一定置信度值进行决策树的修剪，采用优化的Chi2算法更合理更准确地对连续属性进行离散化，基于改进策略设计并实现一个分类器，将改进的算法应用于Breast-cancer实例，实验结果证明改进的算法生成的决策树具有较高的分类正确率。

关键词: 属性相关性, 属性约束, 剪枝策略, 离散化, Chi2算法

CLC Number:

TP18

GONG Gu¹，HUANG Yong-qing¹，HAO Guo-sheng^1，2. Analysis and improved implementation of decision tree algorithms[J]. Computer Engineering and Applications, 2010, 46(13): 139-141.

巩固¹，黄永青¹，郝国生^1，2. 决策树算法的优化研究[J]. 计算机工程与应用, 2010, 46(13): 139-141.

[1]	DAI Qi, LI Min, LIU Yang, LI Lihong. Fast Attribute Reduction Algorithm Based on Fuzzy Hierarchical Quotient Space [J]. Computer Engineering and Applications, 2021, 57(4): 55-60.
[2]	GAO Tianyu, WANG Qingrong, YANG Lei. Data Mining Model Based on Attribute Dependability Enhancement of Rough Set [J]. Computer Engineering and Applications, 2021, 57(3): 87-93.
[3]	ZHANG Chengling, LI Jinjin, LIN Yidong. Attribute Reduction in Formal Contexts Based on OE-Concept Lattices [J]. Computer Engineering and Applications, 2021, 57(15): 82-89.
[4]	LIU Guizhi. Incremental Attribute Reduction of Incomplete Hybrid Data Based on Dimension Change [J]. Computer Engineering and Applications, 2021, 57(12): 161-169.
[5]	MOU En, ZHANG Xianyong, YAO Yuesong, DENG Qie. Class-Specific Attribute Reduct and Its Heuristic Algorithm of Neighborhood Approximation Condition-Entropy [J]. Computer Engineering and Applications, 2020, 56(24): 175-180.
[6]	GU Junhua, SU Ming, ZHANG Yajuan, ZHANG Danhong. Research on Fast Frequent Pattern Mining Algorithm Based on Bitmap-Code List [J]. Computer Engineering and Applications, 2020, 56(19): 86-93.
[7]	GAO Man, HAN Meng, LEI Bingbing. Survey of High Utility Pattern Generate Strategy [J]. Computer Engineering and Applications, 2020, 56(16): 1-12.
[8]	LI Yan, WANG Yangyang, ZHANG Hongyan, WU Youxi. Fast Pruning Algorithm for Unreachable Vertices and Its Application in Solving Shortest Path Problem [J]. Computer Engineering and Applications, 2020, 56(15): 51-57.
[9]	LI Xu, RONG Zijing, REN Yan. Attribute Reduction on Weighted Decision Table [J]. Computer Engineering and Applications, 2020, 56(12): 54-59.
[10]	CHEN Panpan, LIN Menglei. Attributes Reduction of Single Valued Neutrosophic Decision Information System Based on Inclusion Degree [J]. Computer Engineering and Applications, 2020, 56(12): 175-181.
[11]	WU Yangyang, TANG Jianguo. Research Progress of Attribute Reduction Based on Rough Set in Context of Big Data [J]. Computer Engineering and Applications, 2019, 55(6): 31-38.
[12]	YANG Zhen, GENG Xiuli. Research on Mining Association Rules Based on Multi-Granularity Attribute Reduction [J]. Computer Engineering and Applications, 2019, 55(6): 133-139.
[13]	LI Yun, MA Yinghong. Node Importance Rank by Attribute Reduction Set Evaluation [J]. Computer Engineering and Applications, 2019, 55(5): 149-158.
[14]	YANG Jingya, SUN Linfu, WU Qishi. Association Analysis Based on Automobile After-Sales Fault Data [J]. Computer Engineering and Applications, 2019, 55(22): 219-224.
[15]	REN Xiaoxia1, XUE Fan2，3. Heuristic attribute reduction algorithm based on fuzzy neighborhood rough set [J]. Computer Engineering and Applications, 2018, 54(9): 47-53.

Analysis and improved implementation of decision tree algorithms

决策树算法的优化研究

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics