Neural Networks and Cascade Modeling Technique in System Identification

  • Erdem Turker Senalp
  • Ersin Tulunay
  • Yurdanur Tulunay
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3949)


The use of the Middle East Technical University Neural Network and Cascade Modeling (METU-NN-C) technique in system identification to forecast complex nonlinear processes has been examined. Special cascade models based on Hammerstein system modeling have been developed. The total electron content (TEC) data evaluated from GPS measurements are vital in telecommunications and satellite navigation systems. Using the model, forecast of the TEC data in 10 minute intervals 1 hour ahead, during disturbed conditions have been made. In performance analysis an operation has been performed on a new validation data set by producing the forecast values. Forecast of GPS-TEC values have been achieved with high sensitivity and accuracy before, during and after the disturbed conditions. The performance results of the cascade modeling of the near Earth space process have been discussed in terms of system identification.


Total Electron Content Internal Variable Model Predictive Control Cascade Modeling Disturbed Condition 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ikonen, E., Najim, K.: Learning control and modelling of complex industrial processes, Overview report of the activities within the European Science Foundation’s programme on Control of Complex Systems (COSY) Theme 3: Learning control (February 1999)Google Scholar
  2. 2.
    Narendra, K.S., Gallman, P.G.: An Iterative Method for the Identification of Nonlinear Systems Using a Hammerstein Model. IEEE Transactions on Automatic Control, 546–550 (1966)Google Scholar
  3. 3.
    Fruzzetti, K.P., Palazoglu, A., McDonald, K.A.: Nonlinear model predictive control using Hammerstein models. J. Proc. Cont. 7(1), 31–41 (1997)CrossRefGoogle Scholar
  4. 4.
    Marchi, P.A., Coelho, L.S., Coelho, A.R.: Comparative Study of Parametric and Structural Methodologies in Identification of an Experimental Nonlinear Process. In: Proceedings of the 1999 IEEE International Conference on Control Applications, Hawaii, USA, August 22-27, 1999, pp. 1062–1067 (1999)Google Scholar
  5. 5.
    Bai, E.W., Fu, M.: A Blind Approach to Hammerstein Model Identification. IEEE Transactions on Signal Processing 50(7), 1610–1619 (2002)CrossRefGoogle Scholar
  6. 6.
    Westwick, D.T., Kearney, R.E.: Identification of a Hammerstein model of the stretch reflex EMG using separable least squares. In: Proceedings of the 22nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, July 23-28, 2000, vol. 3, pp. 1901–1904 (2000)Google Scholar
  7. 7.
    Chilbolton Weather Web, Space Weather – Total Electron Content of the Ionosphere, Rutherford Appleton Laboratory (2001),
  8. 8.
    Senalp, E.T., Tulunay, E., Tulunay, Y.: Neural Network Based Approach to Forecast the Total Electron Content Values. In: EGS 2002 Conference, 27th General Assembly of the European Geophysical Society, CD of Abstracts, Nice, France, April 21-26, EGS02-A-00867 (2002)Google Scholar
  9. 9.
    Tulunay, E., Senalp, E.T., Cander, L.R., Tulunay, Y.K., Bilge, A.H., Mizrahi, E., Kouris, S.S., Jakowski, N.: Development of algorithms and software for forecasting, nowcasting and variability of TEC. Annals of Geophysics 47(2/3), 1201–1214 (2004)Google Scholar
  10. 10.
    Cander, L.R., Milosavlijevic, M.M., Stankovic, S.S., Tomasevic, S.: Ionospheric Forecasting Technique by Artificial Neural Network. Electronics Letters 34(16), 1573–1574 (1998)CrossRefGoogle Scholar
  11. 11.
    Rycroft, M.: Lecture Notes, TUBITAK FGI Research Institute, Kandilli, Istanbul, Turkey (2004)Google Scholar
  12. 12.
    Tulunay, Y., Tulunay, E., Kutay, A.T., Senalp, E.T.: Neural Network Based Approaches for Some Nonlinear Processes. In: URSI-TURKIYE 2002, ITU – Istanbul, Turkey, September 18-20, 2002, pp. 403–406 (2002)Google Scholar
  13. 13.
    Tulunay, E., Tulunay, Y., Senalp, E.T.: Neural Network Based Approach to Forecast Ionospheric Parameters. In: SPECIAL Workshop, Lindau, Germany, November 8-11 (2000)Google Scholar
  14. 14.
    Tulunay, Y., Tulunay, E., Senalp, E.T., Ozkaptan, C.: Neural Network Modelling of the Effect of the IMF Turning on the Variability of HF Propagation Medium. In: AP 2000, Millennium Conference on Antennas & Propagation, ICAP&JINA, Davos, Switzerland, April 9-14, p. 132 (2000)Google Scholar
  15. 15.
    Tulunay, E., Senalp, E.T., Tulunay, Y.: Forecasting the Total Electron Content By Neural Networks. In: COST 271 Effects of the Upper Atmosphere on Terrestrial and Earth-Space Communications. In: Workshop, Ionospheric Modeling and Variability Studies for Telecommunications Applications, Book of Abstracts, Sopron, Hungary, September 25-27, 2001, p. 47 (2001)Google Scholar
  16. 16.
    Tulunay, Y., Tulunay, E., Senalp, E.T.: An Attempt to Model the Influence of the Trough on HF Communication by Using Neural Network. Radio Science 36(5), 1027–1041 (2001)CrossRefGoogle Scholar
  17. 17.
    Tulunay, Y., Tulunay, E., Senalp, E.T.: The Neural Network Technique-2: An Ionospheric Example Illustrating its Application. Adv. Space Res. 33(6), 988–992 (2004)CrossRefGoogle Scholar
  18. 18.
    COST271 WG 4 STM, Effects of the Upper Atmosphere on Terrestrial and Earth-Space Communications, Short term scientific mission work on the TEC data available at RAL to organize the input data for the METU NN model by E.T. Senalp under the supervision of Dr. Lj. Cander, Terms of Reference, RAL, Chilton, Didcot, U.K., June 30 – July 7 (2002) Google Scholar
  19. 19.
    Hagan, M.T., Menhaj, M.B.: Training Feedforward Networks with the Marquard Algorithm. IEEE Transactions on Neural Networks 5(6), 989–993 (1994)CrossRefGoogle Scholar
  20. 20.
    Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn., pp. 2, 10, 21–22, 83–84, 169, 215 . Prentice-Hall, Inc., New Jersey (1999)MATHGoogle Scholar
  21. 21.
    Tulunay, Y., Tulunay, E., Senalp, E.T.: The Neural Network Technique-1: A General Exposition. Adv. Space Res. 33(6), 983–987 (2004)CrossRefMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Erdem Turker Senalp
    • 1
  • Ersin Tulunay
    • 1
    • 2
  • Yurdanur Tulunay
    • 3
  1. 1.Department of Electrical and Electronics EngineeringMiddle East Technical UniversityBalgat, AnkaraTurkey
  2. 2.Information Technologies InstituteTUBITAK Marmara Research CenterGebze, KocaeliTurkey
  3. 3.Department of Aerospace EngineeringMiddle East Technical UniversityBalgat, AnkaraTurkey

Personalised recommendations