Combining Back-Propagation and Genetic Algorithms to Train Neural Networks for Ambient Temperature Modeling in Italy

  • Francesco Ceravolo
  • Matteo De Felice
  • Stefano Pizzuti
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5484)


This paper presents a hybrid approach based on soft computing techniques in order to estimate ambient temperature for those places where such datum is not available. Indeed, we combine the Back-Propagation (BP) algorithm and the Simple Genetic Algorithm (GA) in order to effectively train neural networks in such a way that the BP algorithm initialises a few individuals of the GA’s population. Experiments have been performed over all the available Italian places and results have shown a remarkable improvement in accuracy compared to the single and traditional methods.


Neural Networks Back-Propagation Algorithm Simple Genetic Algorithm Ambient Temperature Modeling Sustainable Building Design 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Arbib, M.A.: The Handbook of Brain Theory and Neural Networks. MIT Press, Cambridge (1995)Google Scholar
  2. 2.
    Atlante Italiano della Radiazione Solare,
  3. 3.
    Buvik, K., Hestnes, A.G.: Interdisciplinary approach to sustainable building. Experiences from working with a Norwegian demonstration building on retrofitting. Nordic Journal of Architectural Research 20(3) (2008)Google Scholar
  4. 4.
    Erbs, D.G., Klein, S.A., Beckman, W.A.: Estimation of degree-days and ambient temperature bin data from monthly-average temperatures. Ashrae Journal, 60–65 (1983)Google Scholar
  5. 5.
    Farag, W.A., Quintana, V.H., Lambert-Torres, G.: Genetic Algorithms and Back-Propagation: a Comparative Study. In: Canadian Conference on Electrical and Computer Engineering Proceedings of the 1998 llth Canadian Conference on Electrical and Computer Engineering, CCECE. Part 1, pp. 93–96 (1998)Google Scholar
  6. 6.
    Goldberg, D.E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley Publishing Company, Reading (1989)zbMATHGoogle Scholar
  7. 7.
    Haykin, S.: Neural Networks, a comprehensive foundation, 2nd edn. Prentice Hall, New Jersey (1999)zbMATHGoogle Scholar
  8. 8.
    Hestnes, A.G.: Integrated design processes - a must for low energy buildings. In: The Future of Civil Engineering (2008)Google Scholar
  9. 9.
    Holland, J.H.: Adaptation in natural and artificial systems. MIT Press, Cambridge (1975)Google Scholar
  10. 10.
    Jiang, Y.: Prediction of monthly mean daily diffuse solar radiation using artificial neural networks and comparison with other empirical models. Energy Policy 36, 3833–3837 (2008)CrossRefGoogle Scholar
  11. 11.
    Khan, A.U., Bandopadhyaya, T.K., Sharma, S.: Genetic Algorithm Based Backpropagation Neural Network Performs better than Backpropagation neural Network in Stock Rates Prediction. Intl. Journal of Computer Science and Network Security 8(7), 162–166 (2008)Google Scholar
  12. 12.
    Klein, S.A., Beckman, W.A., Mitchell, J.W., Duffie, J.A., Duffie, N.A., Freeman, T.L., Mitchell, J.C., Braun, J.E., Evans, B.L., Kummer, J.P., Urban, R.E., Fiksel, A., Thornton, J.W., Blair, N.J., Williams, P.M., Bradley, D.E. (eds.): TRNSYS, a Transient System Simulation Program. Solar Energy Lab, Univ. of Wisconsin-Madison (2000)Google Scholar
  13. 13.
    Kosko, B.: Neural networks and fuzzy systems. Prentice-Hall, Englewood Cliffs (1992)zbMATHGoogle Scholar
  14. 14.
    Krishnaiah, T., Srinivasa Rao, S., Madhumurthy, K., Reddy, K.S.: Neural Network Approach for Modelling Global Solar Radiation. Journal of Applied Sciences Research 3(10), 1105–1111 (2007)Google Scholar
  15. 15.
    Lu, C., Shi, B.: Hybrid Back-Propagation/Genetic Algorithm for Feedforward Neural Networks. In: ICSP 2000 (2000)Google Scholar
  16. 16.
    McInerney, M., Dhawan, A.P.: Use of Genetic Algorithms with Back Propagation in Training of Feed-Forward Neural Networks. In: IEEE International Conference on Neural Networks, pp. 203–208 (1993)Google Scholar
  17. 17.
    Mitra, A.K., Nath, S.: Forecasting maximum temperatures via fuzzy nearest neighbour model over Delhi. Appl. Comput. Math. 6(2), 288–294 (2007)Google Scholar
  18. 18.
    Narendra, K.S., Parthasarathy, K.: Identification and control of dynamical systems using neural networks. IEEE Trans. Neur. Netw. 1(1), 4–27 (1990)CrossRefGoogle Scholar
  19. 19.
    Nikravesh, M., Farell, A.E., Stanford, T.G.: Model identification of non linear time variant processes via artificial neural network. Computes and Chemical Engineering 20(11), 1277–1290 (1996)CrossRefGoogle Scholar
  20. 20.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by backpropagating errors. Nature 323, 533–536 (1986)CrossRefzbMATHGoogle Scholar
  21. 21.
    Sadeq, A.M., Wahdan, A.-M.A., Mahdi, H.M.K.: Genetic Algorithms and its use with back-propagation network. AIN Shams University Scientific Bullettin 35(3), 337–348 (2000)Google Scholar
  22. 22.
    Sen, Z.: Fuzzy algorithm for estimation irradiation from sunshine duration. Solar Energy 63(1), 39–49 (1998)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Soares, J., Oliveira, A.P., Zlata Boznar, M., Mlakar, P., Escobedo, J.F., Machado, A.J.: Modeling hourly diffuse solar-radiation in the city of So Paulo using a neural-network technique. Applied energy 79(2), 201–214 (2004)CrossRefGoogle Scholar
  24. 24.
    Sodoudi, S.: Estimation of temperature, precipitation and evaporation with Neuro-Fuzzy method. In: Workshop of statistical downscaling, Oslo (2005)Google Scholar
  25. 25.
    Tatli, H., Sen, Z.: A new fuzzy modeling approach for predicting the maximum daily temperature from a time series. Journal of Engineering and Environmental Science 23, 173–180 (1999)Google Scholar
  26. 26.
    Zhang, M., Ciesielski, V.: Using Back Propagation Algorithm and Genetic Algorithms to Train and Refine Neural Networks for Object Detection. In: Computer Science Postgraduate Student Conference, Melbourne (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Francesco Ceravolo
    • 1
  • Matteo De Felice
    • 1
    • 2
  • Stefano Pizzuti
    • 1
  1. 1.Energy, New technology and Environment Agency (ENEA)RomeItaly
  2. 2.Department of Informatics and AutomationUniversity of Rome “Roma 3”RomeItaly

Personalised recommendations