期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

多维贝叶斯网络分类器结构学习算法 被引量：1

Structure learning algorithm for general multi-dimensional Bayesian network classifiers
下载PDF
导出
摘要 传统多维贝叶斯网络分类器(MBNC)限制其模型结构必须是二分的,通过移除该限制可得到更准确的对关联分布建模的通用MBNC(GMBNC)。基于局部马尔可夫毯的迭代搜索,提出可准确学习GMBNC的算法IPCGMBNC。该算法由于无需学习全局贝叶斯网络(BN),可扩展性强。基于已知贝叶斯网络模型而随机生成的数据上所执行的实验显示,IPC-GMBNC可有效推导出目标结构;而且与传统的全局结构学习算法PC相比,IPC-GMBNC可节省大量的计算量。 The conventional Multi-dimensional Bayesian Network Classifier （MBNC） requires its structure be bi-partitie.Removing this constraint can result into a new tool named General MBNC （GMBNC）,and it enables us to model the underlying joint distribution more correctly.Based on iterative local search of Markov blankets,an algorithm called IPCGMBNC was proposed to induce the exact structure of GMBNC.The proposed algorithm has good scalability because it does not need to recover the global Bayesian Network （BN） first.The experiments on samples generated from known Bayesian network structures indicate that IPC-GMBNC is effective,and it brings great reduction on computing complexity compared to global search approach,e.g.PC algorithm.
作者 傅顺开 Sein Minn 李志强
机构地区 华侨大学计算机科学与技术学院
出处 《计算机应用》 CSCD 北大核心 2014年第4期1083-1088,共6页 journal of Computer Applications
基金 国家自然科学基金资助项目(61305058 61300139) 中央高校基本科研基金资助项目(11J0263) 厦门科技计划基金资助项目(3505Z20133027) 华侨大学科研基金资助项目(11Y0274 12HJY18)
关键词 多标签分类 多维分类 多维贝叶斯网络分类器 贝叶斯网络 马尔可夫毯 multi-label classification multi-dimensional classification Multi-dimensional Bayesian Network Classifier （MBNC） Bayesian Network （BN） Markov blanket
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献20

  • 1CHICKERING D M, GEIGER D, HECKERMAN D. Learning Bayesian network is NP-hard, MSR-TR-94-17 [ R]. [ S. 1. ] : Microsoft Research, 1994.
  • 2CHOW C K, LIU C N. Approximating discrete probability distribu- tions with dependence trees [ J]. IEEE Transactions on Information Theory, 1968, 14(3): 462-467.
  • 3de WAAL P R, van der GAAG L C. Inference and learning in multi-dimensional Bayesian network classifiers [ C]//Proceedings of the 9th European Conferences on Symbolic and Quantitative Approa- ches to Reasoning with Uncertainty, LNCS 4724. Berlin: Springer- Verlag, 2007:501-511.
  • 4REBANE G, PEARL J. The recovery of causal poly-trees from sta- tistical data [ C]//UAI '87: Proceedings of the 3rd Conference on Uncertainty in Artificial Intelligence. New York: Elsevier Science Inc., 1987:175-182.
  • 5ZARAGOZA J C, SUCAR E, MORALES E. A two-step method to learn multidimensional Bayesian network classifiers based on mutual information measures [ C]// Proceedings of the 24th International FLAIRS Conference. Menlo Park, California: AAAI Press, 2011: 644 - 649.
  • 6RODRIGUEZ J D, LOZANO J A. Multi-objective learning of multi- dimensional Bayesian classifiers [ C]//HIS '08: Proceedings of the 8th International Conference on Hybrid Intelligent Systems. Wash- inzton, DC: IEEE Comouter Society, 2008:501 -506.
  • 7BIELZ C, LI G, LARRANGA P. Multi-dimensional classification with Bayesian networks [ J]. International Journal of Approximate Reasoning, 2011, 52(6) : 705 -727.
  • 8BORCHANI H, BIELZA C, LARRANGA P. Learning CB-decom- posable multi-dimensional Bayesian network classifiers [ C ]// PGM'10: Proceedings of the 5th European Workshop on Probabilistic Graphical Models. Helsinki: HIIT Publications, 2010:23-32.
  • 9ZARAGOZA J H, SUCAR L E, MORALES E F, et al. Bayesian chain classifiers for muhidimensional classification [ C]//IJCAI '11 : Proceedings of the 22nd International Joint Conference on Artificial Intelligence. Menlo Park, California: AAAI Press, 2011, 3: 2192- 2197.
  • 10BORCHANI H, BIELZA C, MARTfNEZ-ARTN P, et al. Markov blanket-based approach for learning multi-dimensional Bayesian network classifiers: an application to predict the European Qualityof life-5 Dimensions (EQ-5D) from the 39-item Parkinson's Dis- ease Questionnaire (PDQ-39) [ J]. Journal of Biomedical Informat- ies, 2012, 45(6): 1175-1184.

同被引文献17

  • 1Chickering D M,Geiger D, Heckerman D. Learning Bayesian Network is NP-Hard[R]. Microsoft, 1994.
  • 2Zhang H, Liang Liang-xiao, Su J iang. Hidden Naive Bayes[C]// Proceedings of Canadian Artificial Intelligence Conference. 2005 : 432-441.
  • 3Bielza C, Larranaga P. Discrete Bayesian Network Classifiers: A Survey[J]. ACM Computing Surveys,2014,47(1).
  • 4Friedman N,Gierger D, Goldszmidt M. Bayesian Network Clas- sifters [J]. Machine Learning, 1997,29: 131-163.
  • 5van der Gaag L C, de Waal P R. Multi-dimensional Bayesian Network Classifiers [C] ffProceedings of 3 European Work- shop on Probabilistic Graphical Models (PGM). 2006.
  • 6de Waal P R,van der Gaag L C. Inference and learning in multi- dimensional Bayesian network classifiers [C] // Proceedings of 9th European Conference on Symbolic and Quantitative Approa- ches to Reasoning with Uncertainty (F_CSQARU). 2007:501-511.
  • 7Zaragoza J C,Sucar E,Morales E. A Two-step Method to Learn Multi-dimensional Bayesian Network Classifiers based on Mutual Information Measures [C] // Proceedings of 24th International FLAIRS Conference. 2011.
  • 8Borchani H, Bielza C, Martinez-Martin P, et al. Markov blanket- based approach for learning multi-dimensional Bayesian network classifiers: An application to predict the European Quality of Life-5 Dimensions (EQ-5D) from the 39-item Parkinson's Di- sease Questionnaire (PDQ-39) [J]. Journal of Biomedical Infor- matics, 2012,45 (6): 1175-1184.
  • 9Zaragoza J C, Sucar E, Morales E, et al. Bayesian chain classifi- ers for multidimensional classification [C]//Proceedings of 22"a International Joint Conference on Artificial Intelligence(IJ- CAD. 2011 : 2092-2097.
  • 10Zhang Min-ling, Zhou Zhi-hua. A Lazy Learning Approach to Multi-label Learning [J]. Pattern Recognition, 2007, 40 ( 7 ) : 2038-2048.

引证文献1

二级引证文献1

计算机应用
2014年 第4期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部