计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (2): 57-57.

• 学术探讨 • 上一篇    下一篇

改进的决策树生成算法及其在RoboCup中的应用

徐怡,李龙澍,李学俊   

  1. 安徽大学计算机科学与技术学院
  • 收稿日期:2006-05-18 修回日期:1900-01-01 出版日期:2007-01-11 发布日期:2007-01-11
  • 通讯作者: 徐怡 xuyi1981

Improved Designing of Decision Tree and the Application In RoboCup

,Li Longshu,   

  1. 安徽大学计算机科学与技术学院
  • Received:2006-05-18 Revised:1900-01-01 Online:2007-01-11 Published:2007-01-11

摘要: 基于粗糙集理论,提出了一种新的决策树构造算法。详细分析了该算法的优点。通过实验证明它比传统的ID3算法在效率和精度上都有很大提高。把该算法用在RoboCup仿真球队中,以射门为例,进一步证明了该算法的有效性。

关键词: 粗糙集, 核属性, 分明矩阵, 决策树, RoboCup

Abstract: A new method to design the decision tree based on rough set is proposed .The advantages of this method are described in detail .Some examples are given to show that this method is obviously better than ID3 algorithm in efficiency and precision .From the application In RoboCup Simulator League, taking shooting for example, certify that this approach is effective.

Key words: rough set, core attribution, discernible matrix, decision tree, RoboCup