Representing Hypoexponential Distributions in Continuous Time Bayesian Networks

  • Manxia LiuEmail author
  • Fabio Stella
  • Arjen Hommersom
  • Peter J. F. Lucas
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 855)


Continuous time Bayesian networks offer a compact representation for modeling structured stochastic processes that evolve over continuous time. In these models, the time duration that a variable stays in a state until a transition occurs is assumed to be exponentially distributed. In real-world scenarios, however, this assumption is rarely satisfied, in particular when describing more complex temporal processes. To relax this assumption, we propose an extension to support the modeling of the transitioning time as a hypoexponential distribution by introducing an additional hidden variable. Using such an approach, we also allow CTBNs to obtain memory, which is lacking in standard CTBNs. The parameter estimation in the proposed models is transformed into a learning task in their equivalent Markovian models.


Continuous time Bayesian networks Dynamic Bayesian networks Phase-type distribution Memory Hidden variable 


  1. 1.
    Nodelman, U.D.: Continuous time Bayesian Networks. Ph.D. thesis, Stanford University (2007)Google Scholar
  2. 2.
    Boudali, H., Dugan, J.B.: A continuous-time Bayesian network reliability modeling, and analysis framework. IEEE Trans. Reliab. 55(1), 86–97 (2006)CrossRefGoogle Scholar
  3. 3.
    Xu, J., Shelton, C.R.: Continuous time Bayesian networks for host level network intrusion detection. In: Daelemans, W., Goethals, B., Morik, K. (eds.) ECML PKDD 2008. LNCS (LNAI), vol. 5212, pp. 613–627. Springer, Heidelberg (2008). Scholar
  4. 4.
    Xu, J., Shelton, C.R.: Intrusion detection using continuous time Bayesian networks. J. Artif. Intell. Res. 39, 745–774 (2010)MathSciNetzbMATHGoogle Scholar
  5. 5.
    Gatti, E., Luciani, D., Stella, F.: A continuous time Bayesian network model for cardiogenic heart failure. Flex. Serv, Manuf. J. 24(4), 496–515 (2012)CrossRefGoogle Scholar
  6. 6.
    Liu, M., Hommersom, A., van der Heijden, M., Lucas, P.J.F.: Hybrid time Bayesian networks. Int. J. Approximate Reasoning 80, 460–474 (2017)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Acerbi, E., Viganò, E., Poidinger, M., Mortellaro, A., Zelante, T., Stella, F.: Continuous time Bayesian networks identify Prdm1 as a negative regulator of TH17 cell differentiation in humans. Scientific reports 6 (2016)Google Scholar
  8. 8.
    Angus, I.: An introduction to Erlang B and Erlang C. Telemanagement 187, 6–8 (2001)Google Scholar
  9. 9.
    Nodelman, U., Horvitz, E.: Continuous time Bayesian networks for inferring users’ presence and activities with extensions for modeling and evaluation. Microsoft Research, July–August 2003Google Scholar
  10. 10.
    Gopalratnam, K., Kautz, H., Weld, D.S.: Extending continuous time Bayesian networks. In: Proceedings of the National Conference on Artificial Intelligence, vol. 20, p. 981. AAAI Press, MIT Press; 1999, Menlo Park, Cambridge, London (2005)Google Scholar
  11. 11.
    Nodelman, U., Shelton, C.R., Kollerthu, D.: Expectation maximization and complex duration distributions for continuous time Bayesian networks. In: Proceedings of the Twenty-First International Conference on Uncertainty in Artificial Intelligence, pp. 421–430 (2005)Google Scholar
  12. 12.
    Nodelman, U., Shelton, C.R., Koller, D.: Continuous time Bayesian networks. In: Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence, pp. 378–387 (2002)Google Scholar
  13. 13.
    Verbelen, R.: Phase-type distributions & mixtures of Erlangs (2013)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Manxia Liu
    • 1
    • 4
    Email author
  • Fabio Stella
    • 5
  • Arjen Hommersom
    • 1
    • 2
  • Peter J. F. Lucas
    • 1
    • 3
  1. 1.Radboud University, ICISNijmegenThe Netherlands
  2. 2.Open University of the NetherlandsHeerlenThe Netherlands
  3. 3.Leiden University, LIACSLeidenThe Netherlands
  4. 4.University of Porto, CINTESISPortoPortugal
  5. 5.University of Milano-BicoccaMilanItaly

Personalised recommendations