Skip to main content
SpringerLink
Log in

Neural Network Regression for LHF Process Optimization

  • Conference paper
Book cover Advances in Neuro-Information Processing (ICONIP 2008)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 5507))

Included in the following conference series:

Abstract

We present a system for regression using MLP neural networks with hyperbolic tangent functions in the input, hidden and output layer. The activation functions in the input and output layer are adjusted during the network training to fit better the distribution of the underlying data, while the network weights are trained to fit desired input-output mapping. A non-gradient variable step size training algorithm is used since it proved effective for that kind of problems. Finally we present a practical implementation, the system found in the optimization of metallurgical processes.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Dasgupta, B., Schnitger, G.: The Power of Approximating: A Comparison of Activation Functions. In: Advances in Neural Information Processing Systems, vol. 5, pp. 615–622. Morgan Kaufmann, San Francisco (1993)

    Google Scholar 

  2. Hornik, K., Stinchcombe, M., White, H., Auer, P.: Degree of approximation results for feed-forward networks approximating unknown mappings and their derivatives, NeuroColt Technical Report Series, NC-TR-95-004, 1-15 (1995)

    Google Scholar 

  3. Angiulli, F., Pizzuti, C.: Fast outlier detection in high dimensional spaces. In: Elomaa, T., Mannila, H., Toivonen, H. (eds.) PKDD 2002. LNCS (LNAI), vol. 2431, pp. 15–27. Springer, Heidelberg (2002)

    Chapter  Google Scholar 

  4. Biesiada, J., Duch, W., Kachel, A., Mączka, K., Pałucha, S.: Feature ranking methods based on information entropy with Parzen windows. In: Proc. of Research in Electrotechnology and Applied Informatics, Katowice-Kraków, pp. 109–118 (2005)

    Google Scholar 

  5. Alexis, J., Jonsson, P., Jonsson, L.: Heating and electromagnetic stirring in a ladle furnace – a simulation model. ISIJ Int. 40(11), 1098–1104 (2000)

    Article  Google Scholar 

  6. Wieczorek, T.: Intelligent control of the electric-arc steelmaking process using artificial neural networks. Computer Methods in Material Science 6(1), 9–14 (2006)

    MathSciNet  Google Scholar 

  7. Siemens, A.G.: Optimization of the electrode control system with neural networks, pp. 1–8. Siemens Press (2003)

    Google Scholar 

  8. Wieczorek, T., Pyka, M.: Neural modeling of the arc-electric steelmaking process. In: Proc. of 9th Int. Conf. Research in Electrotechnology and Applied Informatics, Katowice, pp. 105–108 (2005)

    Google Scholar 

  9. Wieczorek, T., Blachnik, M., Mączka, K.: Building a model for time reduction of steel scrap meltdown in the electric arc furnace (EAF). General strategy with a comparison of feature selection methods. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2008. LNCS (LNAI), vol. 5097, pp. 1149–1159. Springer, Heidelberg (2008)

    Chapter  Google Scholar 

  10. Hall, M.A.: Correlation based feature selection for machine learning., PhD thesis, Dept. of Comp. Science, Univ. of Waikato, Hamilton, New Zealand (1998)

    Google Scholar 

  11. Kordos, M., Duch, W.: Variable step search algorithm for feedforward networks. Neurocomputing 71(13-15), 2470–2480 (2008)

    Article  Google Scholar 

  12. Gallagher, M.: Multi-layer Perceptron Error Surfaces Visualization, Structure and Modeling., PhD Thesis, University of Queensland (2000)

    Google Scholar 

  13. Kordos, M., Duch, W.: A Survey of Factors Influencing MLP Error Surface. Control and Cybernetics 33(4), 611–631 (2004)

    MathSciNet  MATH  Google Scholar 

  14. Schölkopf, B., Smola, A.J.: Learning with kernels. MIT Press, Cambridge (2002)

    MATH  Google Scholar 

  15. Eskander, G.S., et al.: Round Trip Time Prediction Using the Symbolic Function Network Approach, http://arxiv.org/ftp/arxiv/papers/0806/0806.3646.pdf

  16. Setiono, R., Thong, J.: An approach to generate rules from neural networks for regression problems. European Journal of Operational Research 155(1), 239–250 (2004)

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Material Engineering and Metallurgy, The Silesian University of Technology, Krasinskiego 8, 40-019, Katowice, Poland

    Miroslaw Kordos

Authors
  1. Miroslaw Kordos
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Network Design and Research Center, Kyushu Institute of Technology,, 680-4, Kawazu, Iizuka,, 820-8502, Fukuoka, Japan

    Mario Köppen

  2. Knowledge Engineering and Discovery Research Institute (KEDRI), School of Computing and Mathematical Sciences, Auckland University of Technology, 350 Queen Street, 10110, Auckland, New Zealand

    Nikola Kasabov

  3. Department of Electrical and Computer Engineering, Robotics Laboratory, Auckland University of Technology, 38 Princes Street,, 1142, Auckland, New Zealand

    George Coghill

Rights and permissions

Reprints and permissions

Copyright information

© 2009 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kordos, M. (2009). Neural Network Regression for LHF Process Optimization. In: Köppen, M., Kasabov, N., Coghill, G. (eds) Advances in Neuro-Information Processing. ICONIP 2008. Lecture Notes in Computer Science, vol 5507. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03040-6_55

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-03040-6_55

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-03039-0

  • Online ISBN: 978-3-642-03040-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation