Abstract
Bayesian networks, which have a solid mathematical basis as classifiers, take the prior information of samples into consideration. They have gained considerable popularity for solving classification problems. However, many real-world applications can be viewed as classification problems in which instances have to be assigned to a set of different classes at the same time. To address this problem, multi-dimensional Bayesian network classifiers (MBCs), which organize class and feature variables as three subgraphs, have recently been proposed. Because each subgraph has different structural restrictions, three different learning algorithms are needed. In this paper, we present for the first time an MBC learning algorithm based on an optimization model (MBC-OM) that is inspired by the constraint-based Bayesian network structure learning method. MBC-OM uses the chi-squared statistic and mutual information to estimate the dependence coefficients among variables, and these are used to construct an objective function as an overall measure of the dependence for a classifier structure. Therefore, the problem of searching for an optimal classifier becomes one of finding the maximum value of the objective function in feasible fields. We prove the existence and uniqueness of the numerical solution. Moreover, we validate our method on five benchmark data sets. Experimental results are competitive, and outperform state-of-the-art algorithms for multi-dimensional classification.
Similar content being viewed by others
References
Cai Z, Sun S, Si S, Yannou B (2011) Identifying product failure rate based on a conditional Bayesian network classifier. Expert Syst Appl 38(5):5036–5043
Hsieh NC, Hung LP (2011) A data driven ensemble classifier for credit scoring analysis. Expert Syst Appl 37(1):534–545
Mukherjee S, Sharma N (2012) Intrusion Detection using Naive Bayes Classifier with Feature Reduction. Procedia Technol 4:119–128
Friedman N, Geiger D, Goldszmidt M (1997) Bayesian network classifiers. Mach Learn 29(2−3):131–163
Jiang L, Zhang H, Cai Z (2009) A Novel Bayes model: hidden Naive Bayes. IEEE Trans Knowl Data Eng 21(10):1361–1371
Balamurugan AA, Rajaram R, Pramala S, Rajalakshmi S, Jeyendran, C, Dinesh Surya Prakash J (2011) NB+: An improved Naive Bayesian algorithm Knowledge-Based Systems, vol. 24, no. 5, pp 563-569
Jiang L, Cai Z, Wang D, Zhang H (2012) Improving Tree augmented Naive Bayes for class probability estimation. Knowl-Based Syst 26:239–245
Lpez-Cruz PL, Larranaga P, DeFelipe J, Bielza C (2014) Bayesian network modeling of the consensus between experts: An application to neuron classification. Int J Approx Reason 55:3–22
Madden MG (2009) On the classification performance of TAN and general Bayesian networks, Knowledge-Based Systems, vol. 22,no. 7, pp. 489-495
Zhang ML, Zhou ZH (2006) Multi-label neural networks with applications to functional genomics and text categorization. IEEE Trans Knowl Data Eng 18(10):1338–1351
Ortigosa-Hernandez J, Rodriguez JD, Alzate L, Lucania M, Inza I, Lozano JA (2012) Approaching Sentiment Analysis by using semi-supervised learning of multi-dimensional classifiers. Neurocomputing 92:98–115
Boutell MR, Luo J, Shen X, Brown CM (2004) Learning multi-label scene classification. Pattern Recogn 37(9):1757–1771
Gopal S, Yang Y (2010) Multi-label classification with metalevel features, in Proc. 33rd SIGIR, Geneva Switzerland 315–322
Sanden C, Zhang JZ (2011) Enhancing multi-label music genre classification through ensemble techniques, in Proc. 34th SIGIR, Beijing China 705–714
Pang B, Lee L (2008) Opinion mining and sentiment analysis. Foundationsand Trends in Information Retrieva l2(1-2):1–135
Rodriguez JD, Perez A, Lozano JA (2010) Sensitivity analysis of k-fold cross validation inprediction error estimation. IEEE Trans Pattern Anal Mach Intell 32(3):569–574
Zhang ML, Zhou ZH (2014) A review on multi-label learning algorithms. IEEE Trans Knowl Data Eng 26(8):819–1837
Zhang ML, Zhou ZH (2007) ML-KNN: a lazy learning approach to multi-label learning. Pattern Recognit 40(7):2038–2048
van der Gaag LC, de Waal PR (2006) Multi-dimensional Bayesian network classifiers. In: Third European Conference on Probabilistic Graphical Models, pp. 107-114
Sucar LE, Bielza C, Morales EF, Hernandez-Leal P (2014) Multi-label classification with Bayesian network-based chain Classifiers. Pattern Recogn Lett 41:14–22
de Waal PR, van der Gaag LC (2007) Inference and learning in multi-dimensional Bayesian network classifiers. In: European Conference on Symbolic and Quantitative Approaches to Reasoning under Uncertainty Lecture Notes in Artificial Intelligence 4724 501–511
Bielza C, Li G, Larranaga P (2011) Multi-dimensional classification with Bayesian networks. Int J Approx Reason 52:705–727
Rodriguez JD, Lozano JA (2008) Multi-objective learning of multi-dimensional Bayesian classifiers. In: Proceedings of the Eighth International Conference on Hybrid Intelligent Systems, pp. 501-506
Borchani H, Bielza C, Martłnez-Martłn P, Larranaga P (2012) Markov blanket based approach for learning multi-dimensional Bayesian network classifiers: an application to predict the European quality of life-5dimensions (EQ-5D) from the 39-item Parkinson’s disease questionnaire (PDQ-39). J Biomed Inform 45:1175–1184
Zaragoza JC, Sucar LE, Morales EF (2011) A two-step method to learn multidimensional Bayesian network classifiers based on mutual information measures. In: Proceedings of the 24th International Florida Artificial Intelligence Research Society Conference (FLAIRS) AAAI Press, pp644–649
Gasse M, Aussem A, Elghazel H (2014) A hybrid algorithm for Bayesian network structure learning with application to multi-label learning. Expert Syst Appl 41:6755–6772
Borgelt C (2010) A conditional independence algorithm for learning undirected graphical models. J Comput Syst Sci 76(1):1–33
Zhang Y, Zhang W, Xie Y (2013) Improved heuristic equivalent search algorithm based on Maximal Information Coefficient for Bayesian Network Structure Learning. Neurocomputing 117:186–195
de Campos LM (2006) A Scoring Function for Learning Bayesian Networks based on Mutual Information and Conditional Independence Tests. J Mach Learn Res 7(1):2149–2187
Chen XW, Anantha G, Lin XT (2008) Improving Bayesian Network Structure Learning with Mutual Information-Based Node Ordering in the K2 Algorithm. IEEE Trans Knowl Data Eng 20(5):1–13
Conover WJ (1999) Statistics, Practical Nonparametric John Wiley and Sons Inc.
Rodriguez JD, Lozano JA (2010) Learning Bayesian Network Classifiers for Multi-dimensional Supervised Classification Problems by Means of a Multi-objective Approach, Technical Report EHU-KZAA-TR-3-2010. Department of Computer Science and Artificial Intelligence University of the Basque Country San Sebastian, Spain
Kullback S (1968) Information Theory and Statistics. Dover Publication
Chartrand G, Zhang P (2005) Introduction to Graph Theory. McGraw-Hill College
Neapolitan RE (2004) Learning Bayesian Networks. Prentice-Hall, Englewood Cliffs, NJ
Chickering DM, Meek C (2006) On the incompatibility of faithfulness and monotone DAG faithfulness. Artif Intell 170(8–9):653–666
Acknowledgments
The authors would like to thank the editor and the anonymous reviewers for their insightful comments and suggestions. This work has been partially supported by the National Natural Science Foundation of China (Grant No. 61373174, 11401454), the Natural Science Foundation of Shannxi Province, China (Grant No. 2014JQ1031) and the Fundamental Research Funds for the Central Universities (Grant No. JB140711, 72135992).
Author information
Authors and Affiliations
Corresponding author
Appendix A
Appendix A
Rights and permissions
About this article
Cite this article
Zhu, M., Liu, S. & Jiang, J. A hybrid method for learning multi-dimensional Bayesian network classifiers based on an optimization model. Appl Intell 44, 123–148 (2016). https://doi.org/10.1007/s10489-015-0698-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-015-0698-2