Automatic Tuning of Computational Models

  • Matteo HesselEmail author
  • Fabio Ortalli
  • Francesco Borgatelli
  • Pier Luca Lanzi
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 402)


The aim of this paper is to present a methodology for automatic tuning of a computational model, in the context of the development of flight simulators. We will present alternative approaches to automatic parameter ranking and screening, developed in a collaboration between Politecnico di Milano and TXT e-solutions and designed to fit as much as possible the needs of the industry. We will show how the adoption of such techniques can make model tuning more efficient. Although our techniques have been validated against a helicopter simulator case study, they do not rely on any domain-specific feature or assumption, so they can, in principle, be applied in different domains.


Model tuning Parameter screening Machine learning Feature ranking Logistic regression Multilayer perceptron 


  1. 1.
    Morgan, P.J., Cleave-Hogg, D., Desousa Lam, S., McCulloch, J.: Applying theory to practice in undergraduate education using high fidelity simulation. Med. Teach. 28(1), e10–e15 (2006)CrossRefGoogle Scholar
  2. 2.
    Lewis, J.H., Jiang, S.B.: A theoretical model for respiratory motion artifacts in free-breathing CT scans. Phys. Med. Biol. 54(3), 745–755 (2009)CrossRefGoogle Scholar
  3. 3.
    Kern, S., Muller, S.D., Hansen, N., Büche, D., Ocenasek, J., Koumoutsakos, P.: Learning probability distributions in continuous evolutionary strategies—a comparative review. J. Nat. Comput. 3(1), 77–112 (2004)CrossRefzbMATHGoogle Scholar
  4. 4.
    Last, M., Luta, G., Orso, A., Porter, A., Young, S.: Pooled ANOVA. Comput. Stat. Data Anal. 52(12), 5215–5228 (2008)CrossRefMathSciNetzbMATHGoogle Scholar
  5. 5.
    Fisher, R.A.: The Design of Experiments, xi 251 pp. Oliver & Boyd, Oxford, England. (1935)Google Scholar
  6. 6.
    Harrel, F.: Regression Modeling Strategies. Springer-Verlag (2001)Google Scholar
  7. 7.
    Bishop, C.: Pattern Recognition and Machine Learning, pp. 217–218. Springer Science+Business Media, LLC (2006)Google Scholar
  8. 8.
    Bettonvil, B., Kleijnen, J.P.C.: Searching for important factors in simulation models with many factors: sequential bifurcation. Eur. J. Oper. Res. 96(1), 180–194 (1997)CrossRefzbMATHGoogle Scholar
  9. 9.
    Nelder, J., Wedderburn, R.: Generalized linear models. J Royal Statis Soc Series A (General) 135(3), 370–384 (1972)CrossRefGoogle Scholar
  10. 10.
    Haykin, S.: Neural Networks: A Comprehensive Foundation, 2 edn. Prentice Hall. ISBN 0-13273350-1 (1998)Google Scholar
  11. 11.
    Bergmeir, C., Benìtez, J.M.: Neural networks in R using the stuttgart neural network simulator: RSNNS. J. Statis. Softw. 46(7) (2012)Google Scholar
  12. 12.
    Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65, 386–408 (1958)CrossRefMathSciNetGoogle Scholar
  13. 13.
    Cybenko, G.: Approximations by superpositions of sigmoidal functions. Math. Control Signals Syst. 2(4), 303–314 (1989)CrossRefMathSciNetzbMATHGoogle Scholar
  14. 14.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagatingGoogle Scholar
  15. 15.
    Hessel, M., Borgatelli, F., Ortalli, F.: Machine learning for parameter screening in computer simulations, p. 8906. Springer, Lecture Notes in Computer Science seriesGoogle Scholar
  16. 16.
    Errors. Nature 323 (6088): 533–536. doi:10.1038/323533a0, 1986Google Scholar
  17. 17.
    Vidal, F.P., Villard, P., Lutton, E.: Automatic tuning of respiratory model for patient-based simulation. MIBISOC’13—International Conference on Medical Imaging using Bio-inspired and Soft Computing (2013)Google Scholar
  18. 18.
    Zhang, A.: One-factor-at-a-time screening designs for computer experiments. SAE Technical Paper 2007-01-1660. doi: 10.4271/2007-01-1660 (2007)

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Matteo Hessel
    • 1
    Email author
  • Fabio Ortalli
    • 2
  • Francesco Borgatelli
    • 2
  • Pier Luca Lanzi
    • 3
  1. 1.Politecnico Di MilanoMilanItaly
  2. 2.TXT E-SolutionsMilanItaly
  3. 3.DEIBPolitecnico Di MilanoMilanItaly

Personalised recommendations