[1]郭坤,王浩,姚宏亮,等.逻辑回归分析的马尔可夫毯学习算法[J].智能系统学报,2012,7(2):153-160.
GUO Kun,WANG Hao,YAO Hongliang,et al.An algorithm for a Markov blanket based on ?logistic regression analysis[J].CAAI Transactions on Intelligent Systems,2012,7(2):153-160.
点击复制
GUO Kun,WANG Hao,YAO Hongliang,et al.An algorithm for a Markov blanket based on ?logistic regression analysis[J].CAAI Transactions on Intelligent Systems,2012,7(2):153-160.
逻辑回归分析的马尔可夫毯学习算法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
7
期数:
2012年第2期
页码:
153-160
栏目:
学术论文—机器学习
出版日期:
2012-04-25
- Title:
- An algorithm for a Markov blanket based on ?logistic regression analysis
- 文章编号:
- 1673-4785(2012)02-0153-08
- Keywords:
- Bayesian networks; Markov blanket; logistic regression analysis; conditional independence test
- 分类号:
- TP181
- 文献标志码:
- A
- 摘要:
- 针对当前的马尔可夫毯学习算法会引入不正确的父子节点和配偶节点的问题，提出了一种基于逻辑回归分析的马尔可夫毯学习算法RAMMMB.利用MMMB算法得到候选的马尔可夫毯，建立目标变量与候选马尔可夫毯的逻辑回归方程，通过回归分析在保留与目标变量相关性很强的变量的同时，去掉MMMB等算法所引入的弱相关性的错误变量以及其他的弱相关性变量；然后利用G2测试去掉回归分析后候选马尔可夫毯中的兄弟节点，得到目标变量的马尔可夫毯.RAMMMB算法通过回归分析，减少了条件独立测试的次数，提高了学习的精度.实验比较和分析表明，RAMMMB算法能有效地发现变量的马尔可夫毯.
- Abstract:
- To solve the problem of incorrect parent, child, and spouse nodes being brought into the current algorithms, an improved algorithm called a regression analysismax min Markov blanket (RAMMMB) was presented using the Markov Blanket based on logistic regression analysis. First, a logistic regression equation was established between the target variable and a set of its candidate Markov blankets obtained from the maxmin Markov blanket (MMMB) algorithm. Regression analysis can retain the variables strongly correlated with the target variable, and can remove the error variables and other variables weakly correlated with it as well. The incorrect nodes in the MMMB algorithm were also removed from the candidate Markov blanket; then, after the G2 conditiond independence test, which removed the brother node of the target variable in the candidate Markov blanket, returned after the regression analysis, the Markov blanket of the target variable was obtained. By the method of regression analysis, the RAMMMB algorithm reduces the number of condition tests of independence and improves the accuracy of discovering the Markov blanket for the target variable. The result shows that the method can discover the Markov blanket of the target variable efficiently.
- 参考文献/References:
-
［1］MARGARITIS D，THRUN S. Bayesian network induction via local neighborhoods［C］//Advances in Neural Information Processing Systems. Denver, Colorado, USA, 1999: 505511.
［2］TSAMARDINOS I, ALIFERIS C F, STATNIKOV A. Algorithms for large scale Markov blanket discovery［C］//Proceedings of the Sixteenth International Florida Artificial Intelligence Research Society Conference. St Augustine, Florida, USA, 2003: 376380.
［3］FU Shunkai, Desmarais M C. Markov blanket based feature selection: a review of past decade［C］// Proceedings of the World Congress on Engineering London, UK, 2010： 2227.
［4］TSAMARDINOS I, ALIFERIS C F, STATNIKOV A. Time and sample efficient discovery of Markov blankets and direct causal relations［C］//Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Washington, DC, USA, 2003: 673678.
［5］PEA J M, NILSSON R, BJRKEGREN J, et al. Towards scalable and data efficient learning of Markov boundaries［J］. International Journal of Approximate Reasoning, 2007, 45(2): 211232.
［6］ALIFERIS C F, TSAMARDINOS I, STATNIKOV A. HITON: a novel Markov blanket algorithm for optimal variable selection［C］//Proceedings of the 2003 American Medical Informatics Association Annual Symposium.Washington, DC, USA, 2003: 2125.
［7］TSAMARDINOS I, BROWN L E, ALIFERIS C F. The maxmin hillclimbing Bayesian network structure learning algorithm［J］.Machine Learning, 2006, 65: 3178.
［8］孟晓东,袁道华,施惠丰. 基于回归模型的数据挖掘研究［J］. 计算机与现代化, 2010, 173(1): 2628.
MENG Xiaodong, YUAN Daohua, SHI Huifeng. Research on regressbase system on data mining［J］. Computer and Modernization, 2010, 173(1): 2628.
［9］SINGH S, KUBICA J, LARSEN S, et al. Parallel large scale feature selection for logistic regression［C］//SIAM International Conference on Data Mining(SDM). Sparks, Nevada, USA, 2009: 11711182.
［10］施朝健,张明铭. Logistic回归模型分析［J］.计算机辅助工程, 2005, 14(3): 7478.
SHI Chaojian, ZHANG Mingming. Analysis of logistic regression models［J］.Computer Aided Engineering, 2005,14(3): 7478.
［11］高晓光,赵欢欢,任佳.基于蚁群优化的贝叶斯网络学习［J］. 系统工程与电子技术, 2010, 32(7): 15091512.
［12］SPIRTES P, GLYMOUR C, SCHEINES R. Causation,prediction, and search［M］. 2nd ed. Cambrdge, USA: The MIT Press, 2000： 2328.
GAO Xiaoguang, ZHAO Huanhuan,REN Jia. Bayesiannetwork learning on algorithm based on ant colony optimization［J］. Systems Engineering and Electronics, 2010, 32(7): 15091512.
- 相似文献/References:
-
[1]杨有龙,刘? 蔚,吴?? 艳.贝叶斯网络的非忠实性分布[J].智能系统学报,2009,4(4):335.
YANG You-long,LIU Wei,WU Yan.Unfaithful distributions with respect to Bayesian networks[J].CAAI Transactions on Intelligent Systems,2009,4():335.
[2]李冰寒,高晓利,刘三阳,等.利用互信息学习贝叶斯网络结构[J].智能系统学报,2011,6(1):68.
LI-Binghan,GAO-Xiaoli,LIU-Sanyang,et al.Learning Bayesian network structures based on mutual information[J].CAAI Transactions on Intelligent Systems,2011,6():68.
[3]段海滨,马冠军,赵振宇.基于模糊规则和动态蚁群贝叶斯网络的无人作战飞机态势评估[J].智能系统学报,2013,8(2):119.[doi:10.3969/j.issn.1673-4785.201211031]
DUAN Haibin,MA Guanjun,ZHAO Zhenyu.UCAV situation assessment based on fuzzy rules and dynamic ant colony-Bayesian network[J].CAAI Transactions on Intelligent Systems,2013,8():119.[doi:10.3969/j.issn.1673-4785.201211031]
[4]张平,刘三阳,朱明敏.基于人工蜂群算法的贝叶斯网络结构学习[J].智能系统学报,2014,9(3):325.[doi:10.3969/j.issn.1673-4785.201310014]
ZHANG Ping,LIU Sanyang,ZHU Mingmin.Structure learning of Bayesian networks by use of the artificial bee colony algorithm[J].CAAI Transactions on Intelligent Systems,2014,9():325.[doi:10.3969/j.issn.1673-4785.201310014]
[5]张兴,陈昊.差分隐私的高维数据发布研究综述[J].智能系统学报,2021,16(6):989.[doi:10.11992/tis.202104023]
ZHANG Xing,CHEN Hao.A research review of high-dimensional data publishing based on a differential privacy model[J].CAAI Transactions on Intelligent Systems,2021,16():989.[doi:10.11992/tis.202104023]
备注/Memo
收稿日期：2011-12-08.
网络出版日期：2012-04-160.
基金项目：国家自然科学基金资助项目（61070131，61175051).
通信作者：郭坤.????????????????????E-mail：guokun19871005@163.com.
作者简介：
郭坤，男，1987年生，硕士研究生，主要研究方向为机器学习与数据挖掘.
王浩，男，1962年生，教授，博士，主要研究方向为人工智能.
?姚宏亮，男，1972年生，副教授，博士，主要研究方向为机器学习与知识工程.
更新日期/Last Update:
2012-07-12