Online Structure Learning for Traffic Management

  • Evangelos MichelioudakisEmail author
  • Alexander Artikis
  • Georgios Paliouras
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10326)


Most event recognition approaches in sensor environments are based on manually constructed patterns for detecting events, and lack the ability to learn relational structures in the presence of uncertainty. We describe the application of \(\mathtt {OSL}\alpha \), an online structure learner for Markov Logic Networks that exploits Event Calculus axiomatizations, to event recognition for traffic management. Our empirical evaluation is based on large volumes of real sensor data, as well as synthetic data generated by a professional traffic micro-simulator. The experimental results demonstrate that \(\mathtt {OSL}\alpha \) can effectively learn traffic congestion definitions and, in some cases, outperform rules constructed by human experts.


Markov Logic Networks Event Calculus Uncertainty 



Funded by EU FP7 project SPEEDD (619435).


  1. 1.
    Artikis, A., Skarlatidis, A., Portet, F., Paliouras, G.: Logic-based event recognition. Knowl. Eng. Rev. 27(4), 469–506 (2012)CrossRefGoogle Scholar
  2. 2.
    Baber, C., Starke, S., Morar, N., Howes, A., Kibangou, A., Schmitt, M., Ramesh, C., Lygeros, J., Fournier, F., Artikis, A.: Deliverable 8.5 - intermediate evaluation report of SPEEDD prototype for traffic management. SPEEDD Project.
  3. 3.
    Cugola, G., Margara, A.: Processing flows of information: from data stream to complex event processing. ACM Comput. Surv. 44(3), 15 (2012)CrossRefGoogle Scholar
  4. 4.
    de Wit, C.C., Bellicot, I., Garin, F., Grandinetti, P., Ladino, A., Singhal, R., Kibangou, A., Morbidi, F., Schmitt, M., Hempel, A., Baber, C., Cooke, N.: Deliverable 8.1 - user requirements and scenario definition. SPEEDD project.
  5. 5.
    Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12, 2121–2159 (2011)MathSciNetzbMATHGoogle Scholar
  6. 6.
    Huynh, T.N., Mooney, R.J.: Max-margin weight learning for Markov logic networks. In: Buntine, W., Grobelnik, M., Mladenić, D., Shawe-Taylor, J. (eds.) ECML PKDD 2009. LNCS, vol. 5781, pp. 564–579. Springer, Heidelberg (2009). doi: 10.1007/978-3-642-04180-8_54 CrossRefGoogle Scholar
  7. 7.
    Huynh, T.N., Mooney, R.J.: Online structure learning for Markov logic networks. Proc. ECML PKDD 2, 81–96 (2011)Google Scholar
  8. 8.
    Kowalski, R., Sergot, M.: A logic-based calculus of events. New Gener. Comput. 4(1), 67–95 (1986)CrossRefzbMATHGoogle Scholar
  9. 9.
    Michelioudakis, E., Skarlatidis, A., Paliouras, G., Artikis, A.: Online structure learning using background knowledge axiomatization. Proc. ECML-PKDD 1, 237–242 (2016)Google Scholar
  10. 10.
    Mueller, E.T.: Event calculus. in handbook of knowledge representation. In: Foundations of Artificial Intelligence, vol. 3, pp. 671–708. Elsevier (2008)Google Scholar
  11. 11.
    Richards, B.L., Mooney, R.J.: Learning relations by pathfinding. In: Proceedings of AAAI, pp. 50–55. AAAI Press (1992)Google Scholar
  12. 12.
    Richardson, M., Domingos, P.M.: Markov logic networks. Mach. Learn. 62(1–2), 107–136 (2006)CrossRefGoogle Scholar
  13. 13.
    Singhal, R., Andreev, A., Kibangou, A.: Deliverable 8.4 - final version of micro-simulator. SPEEDD project.
  14. 14.
    Skarlatidis, A., Paliouras, G., Artikis, A., Vouros, G.A.: Probabilistic event calculus for event recognition. ACM Trans. Comput. Log. 16(2), 11:1–11:37 (2015)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Evangelos Michelioudakis
    • 1
    Email author
  • Alexander Artikis
    • 2
    • 1
  • Georgios Paliouras
    • 1
  1. 1.Institute of Informatics and TelecommunicationsNCSR “Demokritos”Agia ParaskeviGreece
  2. 2.Department of Maritime StudiesUniversity of PiraeusPiraeusGreece

Personalised recommendations