Abstract
The introduction of temporal dimension makes it difficult and complex to learn dynamic Bayesian network (DBN) structure for huge search space, hence many studies focus on some particular types of DBN, such as dynamic Naive Bayesian Classifier (DNBC). In order to overcome the limited applicability of DBN structure learning methods, this paper proposes an unsupervised evolutionary algorithm in which the selection of initial population has been implemented by means of mutual information to reduce the search space. Furthermore, in view of the poor performance of traditional encoding scheme and the recount of Bayesian information criterion (BIC) score when calculating the individual fitness, we provide a new structure representation without a necessity of the acyclicity test and an updating algorithm for BIC scores with the help of family inheritance to improve the efficiency. Simulations on synthetic data demonstrate that the proposed unsupervised evolutionary algorithm is effective in DBN structure learning.
References
Heckerman, D.: Bayesian networks for data mining. Data Min. Knowl. Disc. 1, 79–119 (1997)
Zhang, L., Zhang, J., Sun, Y.: The construction and application of Bayesian network in data mining. In: 6th IEEE International Conference on Information Management, Innovation Management and Industrial Engineering, pp. 501–503. IEEE Press, New York (2013)
Wachsmuth, S., Brandt-Pook, H., Socher, G., Kummert, F., Sagerer, G.: Multilevel integration of vision and speech understanding using Bayesian networks. In: Christensen, H.I. (ed.) ICVS 1999. LNCS, vol. 1542, pp. 231–254. Springer, Heidelberg (1998)
Chickering, D.M.: Learning Bayesian networks is NP-complete. In: Fisher, D., Lenz, H. (eds.) Learning from Data. LNS, vol. 112, pp. 121–130. Springer, Heidelberg (1999)
Xia, J., Richard, E.N., Michael, B., Shyam, V.: Learning genetic epistasis using Bayesian network scoring criteria. BMC Bioinform. 12, 1–12 (2011)
Liu, Z., Malone, B., Yuan, C.: Empirical evaluation of scoring functions for Bayesian network model selection. BMC Bioinform. S15, 14 (2012)
Wang, S., Xu, G., Du, R.: Restricted Bayesian classification networks. Sc. China Inf. Sci. 56, 1–15 (2013)
Song, W., Yu, J.X., Cheng, H., Liu, H., He, J., Du, X.: Bayesian network structure learning from attribute uncertain data. In: Gao, H., Lim, L., Wang, W., Li, C., Chen, L. (eds.) WAIM 2012. LNCS, vol. 7418, pp. 314–321. Springer, Heidelberg (2012)
Tsamardinos, I., Brown, L.E., Aliferis, C.F.: The max-min hill-climbing Bayesian network structure learning algorithm. Mach. Learn. 65, 31–78 (2006)
Wong, M.L., Leung, K.S.: An efficient data mining method for learning Bayesian networks using an evolutionary algorithm-based hybrid approach. IEEE Trans. Evol. Comput. 8, 378–404 (2004)
Srinivasa, K.G., Seema, S., Jaiswal, M.: Modelling of time series microarray data using dynamic Bayesian network. Retrovirology 84, 489–492 (2009)
Shibata, K., Nakano, H., Miyauchi, A.: A learning method for dynamic Bayesian network structures using a multi-objective particle swarm optimizer. Artif. Life Robot. 16, 329–332 (2011)
Shin, J., Lee, T., Kim, J., Lee, H.: Stochastic model of production and inventory control using dynamic Bayesian network. Artif. Life Robot. 13, 148–154 (2008)
Palacios-Alonso, M.A., Brizuela, C.A., Sucar, L.E.: Evolutionary learning of dynamic Naive Bayesian classifiers. J. Autom. Reason. 45, 21–37 (2010)
Wu, X., Wen, X., Li, J., Yao, L.: A new dynamic Bayesian network approach for determining effective connectivity from fMRI data. Neural Comput. Appl. 24, 91–97 (2014)
Wei, Z., Xu, H., Li, W., Gui, X., Wu, X.: Improved Bayesian network structure learning with node ordering via K2 algorithm. In: Huang, D.-S., Jo, K.-H., Wang, L. (eds.) ICIC 2014. LNCS, vol. 8589, pp. 44–55. Springer, Heidelberg (2014)
Wang H., Yu K., Yao H.: Learning dynamic Bayesian networks using evolutionary MCMC. In: 2nd IEEE International Conference on Computational Intelligence and Security, pp. 45–50. IEEE Press, Guangzhou (2006)
Salama, K.M., Freitas, A.A.: Learning Bayesian network classifiers using ant colony optimization. Swarm Intell. 7, 229–254 (2013)
Li, J., Chen, J.: A hybrid optimization algorithm for Bayesian network structure learning based on database. J. Comput. 9, 2787–2791 (2014)
Bac, F.Q., Perov, V.L.: New evolutionary genetic algorithms for NP-complete combinatorial optimization problems. Biol. Cybern. 69, 229–234 (1993)
Lee, J., Chung, W., Kim, E., Kim, S.: A new genetic approach for structure learning of Bayesian networks: matrix genetic algorithm. Int. J. Control Autom. Syst. 8, 398–407 (2010)
Ross, B.J., Zuviria, E.: Evolving dynamic Bayesian networks with multi-objective genetic algorithms. Appl. Intell. 26, 13–23 (2007)
Robinson, R.W.: Counting unlabeled acyclic digraphs. In: Little, C.H.C. (ed.) Combinatorial Mathematics V. LNM, vol. 622, pp. 28–43. Springer, Heidelberg (1977)
Chen, X.W.: Improving Bayesian network structure learning with mutual information-based node ordering in the K2 algorithm. IEEE Trans. Knowl. Data Eng. 20, 628–640 (2007)
Acknowledgments
This paper was supported by the International S&T Cooperation Projects of China (2015DFR10510), the National Natural Science Foundation of China (61162010; 61440048; 61562018), and the Natural Science Foundation of Hainan Province, China (614227).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Dai, J., Ren, J. (2015). Unsupervised Evolutionary Algorithm for Dynamic Bayesian Network Structure Learning. In: Suzuki, J., Ueno, M. (eds) Advanced Methodologies for Bayesian Networks. AMBN 2015. Lecture Notes in Computer Science(), vol 9505. Springer, Cham. https://doi.org/10.1007/978-3-319-28379-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-28379-1_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-28378-4
Online ISBN: 978-3-319-28379-1
eBook Packages: Computer ScienceComputer Science (R0)