首页 | 本学科首页   官方微博 | 高级检索  
     

TAN分类器结构等价类空间及其在分类器学习算法中的应用
引用本文:王中锋,王志海.TAN分类器结构等价类空间及其在分类器学习算法中的应用[J].北京邮电大学学报,2012,35(1):72-76.
作者姓名:王中锋  王志海
作者单位:北京交通大学计算机与信息技术学院,北京100044;北京市劳动保护科学研究所安全与应急管理研究室,北京100054;北京交通大学计算机与信息技术学院,北京,100044
摘    要:为了认识树形贝叶斯网络(TAN)分类器结构中边的方向与分类精度的关系,以条件对数似然函数为优化目标,研究了TAN分类器结构空间和TAN分类器结构等价类空间,证明了随着训练数据集合的增大,TAN分类器结构中边的方向不对分类器的分类精度产生影响,并提出了一个不考虑边重定向的TAN分类器学习算法,用实验验证了其有效性.

关 键 词:数据挖掘  分类器  贝叶斯网络  等价类  结构学习

Equivalent Classes of TAN Classifier Structure and Their Application on Learning Algorithm
WANG Zhong-feng , WANG Zhi-hai.Equivalent Classes of TAN Classifier Structure and Their Application on Learning Algorithm[J].Journal of Beijing University of Posts and Telecommunications,2012,35(1):72-76.
Authors:WANG Zhong-feng  WANG Zhi-hai
Affiliation:1(1.School of Computer and Information Technology,Beijing Jiaotong University,Beijing 100044,China; 2.Safety and Emergency Management Laboratory,Beijing Municipal Institute of Labour Protection,Beijing 100054,China)
Abstract:As the structure of a tree augmented Nave Bayes(TAN) classifier is a directed acyclic graph,most of learning algorithms try to improve classifier’s performance by selecting the directions of arcs.With scoring criterion of log conditional likelihood,however,it is proven that TAN classifiers with same links are equivalent after analyzing the searching space and equivalent classes of TAN classifier structures.Therefore,a learning algorithm without taking arc reversal into account is proposed.Experiments show that the proposed algorithm is effective.
Keywords:data mining  classifier  Bayesian network  equivalent classes  structure learning
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号