|本期目录/Table of Contents|

[1]汪 璐,贾修一*,顾雁囡.三支决策贝叶斯网络分类器[J].南京大学学报(自然科学版),2016,52(5):833.[doi:10.13232/j.cnki.jnju.2016.05.009]
 Wang Lu,Jia Xiuyi*,Gu Yannan.Three­way decisions based Bayesian network classifier[J].Journal of Nanjing University(Natural Sciences),2016,52(5):833.[doi:10.13232/j.cnki.jnju.2016.05.009]
点击复制

三支决策贝叶斯网络分类器()
     

《南京大学学报(自然科学版)》[ISSN:0469-5097/CN:32-1169/N]

卷:
52
期数:
2016年第5期
页码:
833
栏目:
出版日期:
2016-10-01

文章信息/Info

Title:
Three­way decisions based Bayesian network classifier
作者:
汪 璐贾修一*顾雁囡
南京理工大学计算机科学与工程学院,南京,210094
Author(s):
Wang LuJia Xiuyi*Gu Yannan
School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing,210094,China
关键词:
三支决策贝叶斯网络分 类属性关联性
Keywords:
three­way decisionsBayesian networkclassificationattribute correlation
分类号:
TP181
DOI:
10.13232/j.cnki.jnju.2016.05.009
文献标志码:
A
摘要:
传统二支决策分类器在处理不精确或置信度不高的对象时往往具有较高的错分率,而三支决策由于引入延迟决策,使其具有较低的误分率.基于单评价函数的三支决策分类器通过判断对象的条件概率值和决策阈值之间的大小关系将对象划分到相应的区域中.决策阈值可以由三支决策粗糙集模型计算得出,而条件概率值则由分类器提供.提出一种三支决策贝叶斯网络分类器,考虑属性之间的关联性,从而将条件概率求解和阈值求解融合在一起,实验表明三支决策贝叶斯网络分类器具有更高的分类精度.
Abstract:
The traditional classification models are always two­way decision models,which are based on the attributes or features of objects to accept or reject objects.However,in many cases,because of the inaccurate information,a number of objects belonging to different classes have the similar probability value.Therefore,classical two­way decisions based classifiers usually have a high probability to misclassify the vague objects.To obtain a lower misclassification rate,three­way decisions based classifiers adopt the deferment decision to deal with those vague objects.Those vague objects are classified into boundary region waiting for further processing.In order to facilitate the calculation,most three­way decision classifications are based on the single evaluation function.In single function based three­way decisions,all objects will be classified into the corresponding regions by comparing their conditional probabilities with the decision thresholds.The decision thresholds can be computed by three­way decision­theoretic rough set model,while the conditional probability of an object has to be provided by a specific classifier.In the computational efficiency,Naive Bayesian Rough set model combines the Naive Bayes and the three­way decision,resulting high computational efficiency.However,Naive Bayesian model is based on the assumption of conditional independence so that the obtained values are usually inaccurate.In view of the problems existing in the Naive Bayesian Rough set model,this paper proposes a three­way decisions based Bayesian network classifier,which introduces the Bayesian network model and combines the computation of the object’s conditional probability and decision thresholds together.Experimental results show that our proposed classifier can have a high accuracy.

参考文献/References:

[1] Yao Y.An outline of a theory of three­way decisions.In:Rough Sets and Current Trends in Computing.Berlin Heidelberg:Springer,2012,1-17.
[2]  于 洪,王国胤,姚一豫.决策粗糙集理论研究现状与展望.计算机学报,2015(8):1628-1639.(Yu H,Wang G Y,Yao Y Y.Current research and future perspectives on decision­theoretic rough sets.Chinese Journal of Computers,2015(8):1628-1639.)
[3]  Yao Y Y,Zhou B.Naive Bayesian rough sets.In:Rough Set and Knowledge Technology.Berlin Heidelberg:Springer,2010:719-726.
[4]  Good I J.The estimation of probabilities:An essay on modern Bayesian methods.Biometrics,1965,23(23).
[5]  Zadrozny B,Elkan C.Transforming classifier scores into accurate multiclass probability estimates.In:The 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM,2002:694-699.
[6]  黄影平.贝叶斯网发展及其应用综述.北京理工大学学报,2013,33(12):1211-1219.(Huang Y P.Survey on Bayesian network development and application.2013,33(12):1211-1219.)
[7]  Yao Y.Decision­theoretic rough set models.In:Rough Sets and Knowledge Technology.Berlin Heidelberg:Springer,2007,1-12.
[8]  Schenker A,Last M,Bunke H.Classification of web documents using a graph model.In:The 7th International Conference on Document Analysis and Recognition.New York:IEEE,2003(1):240-244.
[9]  S'lzak D,Ziarko W.Variable precision Bayesian rough set model.In:Rough Sets,Fuzzy Sets,Data Mining and Granular Computing.Berlin Heidelberg:Springer,2003,312-315.
[10]  Lam W,Bacchus F.Learning Bayesian belief networks:an approach based on the MDL principle.Computational Intelligence,2000,10(3):269-293.
[11]  Silander T,Myllymaki P.A simple approach for finding the globally optimal Bayesian network structure.In:The 22nd Conference in Uncertainty in Artificial Intelligence.Corvallis:AUAI Press,2006:445-452.
[12]  Cheng J,Greiner R,Kelly J,et al.Learning Bayesian networks from data:An information­theory based approach.Artificial Intelligence,2002,137(12):43-90.
[13]  Murphy P M,Aha D W.UCI repository of machine learning databases.Technical Report.University of California at Irvine,2015-12-20.
[14]  Usama M F,Keki B I.Multi­interval discretization of continuous valued attributes for classification learning.In:The 5th International Joint Conference on Artificial Intelligence.Berlin Heidelberg:Springer,1993:1022-1029.
[15]  Jia X,Shang L.How to evaluate three­way decisions based binary classification?In:International Conference on Rough Sets,Fuzzy Sets,Data Mining,and Granular Computing.Berlin Heidelberg:Springer,2015:346-355.
[16]  NLPIR/ICTCLAS 2015.中科院汉语分词系统.2015-12-20.(NLPIR/ICTCLAS 2015.Chinese word segmentation system of Chinese Academy of Sciences.2015-12-20.)
[17]  石志伟,刘 涛,吴功宜.一种快速高效的文本分类方法.计算机工程与应用,2005,41(29):180-183.(Shi Z W,Liu T,Wu G Y.An effective and efficient algorithm for text categorization.Computer Engineering and Applications,2005,41(29):180-183.)

相似文献/References:

备注/Memo

备注/Memo:
基金项目:国家自然科学基金(61403200),江苏省自然科学基金(BK20140800)
收稿日期:2016-08-03
*通讯联系人,E­mail:jiaxy@njust.edu.cn
更新日期/Last Update: 2016-09-25