Wind and Structures

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

New criteria to fix number of hidden neurons in multilayer perceptron networks for wind speed prediction

  • Sheela, K. Gnana (Anna University, Regional Centre) ;
  • Deepa, S.N. (Anna University, Regional Centre)
  • Received : 2013.01.09
  • Accepted : 2014.02.01
  • Published : 2014.06.25
⟨ Previous Next ⟩

Abstract

This paper proposes new criteria to fix hidden neuron in Multilayer Perceptron Networks for wind speed prediction in renewable energy systems. To fix hidden neurons, 101 various criteria are examined based on the estimated mean squared error. The results show that proposed approach performs better in terms of testing mean squared errors. The convergence analysis is performed for the various proposed criteria. Mean squared error is used as an indicator for fixing neuron in hidden layer. The proposed criteria find solution to fix hidden neuron in neural networks. This approach is effective, accurate with minimal error than other approaches. The significance of increasing the number of hidden neurons in multilayer perceptron network is also analyzed using these criteria. To verify the effectiveness of the proposed method, simulations were conducted on real time wind data. Simulations infer that with minimum mean squared error the proposed approach can be used for wind speed prediction in renewable energy systems.

Keywords

References

  1. Choy, B., Lee, J.H. and Kim, D.H. (2008), "Solving local minima problem with large number of hidden nodes on two layered feed forward artificial neural networks", Neurocomputing, 71, 3640- 3643. https://doi.org/10.1016/j.neucom.2008.04.004
  2. Doukim, C.A., Dargham, J.A. and Chekima, A. (2010), "Finding the number of hidden neurons for an MLP neural network using coarse to fine search technique", Proceedings of the IEEE 10th Int. Conf. on Information Science, Signal Processing and their Applications.
  3. Fujita, O. (1998), "Statistical estimation of the number of hidden units for feed forward neural networks", Neural Networks, 11(5), 851-859. https://doi.org/10.1016/S0893-6080(98)00043-4
  4. Grewal, B.S. (2007), Higher engineering mathematics, Khanna Publishers, 40th Ed., New Delhi.
  5. Hagiwara, M. (1996), "A Simple and effective method for removal of hidden units and weights", Neuro Comput., 6(2), 207-218.
  6. Han, M. and Yin, J. (2008), "The hidden neurons selection of the wavelet networks using Support vector machines and ridge regression", Neurocomputing, 72(1-3), 471-479. https://doi.org/10.1016/j.neucom.2007.12.009
  7. Hunter, D., Yu, H., Pukish, M.S., Kolbusz, J. and Wilamowski, B.M. (2012), "Selection of proper neural network sizes and architectures- a comparative study", IEEE T. Ind. Inform., 8(2), 228-240. https://doi.org/10.1109/TII.2012.2187914
  8. Islam, M. and Murase, K. (2011), "A new algorithm to design compact two hidden layer artificial neural network", Neural Networks, 14(9), 1265-1278.
  9. Ke, J. and Liu, X. (2008), "Empirical analysis of optimal hidden neurons in neural network modeling for stock prediction", Proceedings of the IEEE Pacific Asia Workshop on Computa. Intel. and Indust. App.
  10. Keeni, K. and Kenji, N, (1999), Estimation of initial weights and hidden units for fast learning of multi layer neural networks for pattern classification, Dept. of Infor. Systems & Quantitative Sciences, Japan.
  11. kurkova, V., Kainen, P.C. and kreinovich, V. (1997), "Estimates of the number of hidden units and variation with respect to half spaces", Neural Networks, 10(6),1061-1068. https://doi.org/10.1016/S0893-6080(97)00028-2
  12. Lan, Y., Soh, Y.C. and Huang, G.B. (2010), "Constructive hidden nodes selection of extreme learning machine for regression", Neurocomputing, 73(16-18) 3191-3199. https://doi.org/10.1016/j.neucom.2010.05.022
  13. Li, J.Y., Chow, T.W.S. and Yu, Y.L. (1995), "The estimation theory and optimization algorithm for the number of hidden units in the higher order feedforward neural network", Neural Networks, 3, 1228- 1233.
  14. Liu, Y., Starzyk, J.A. and Zhu, Z. (2007), "Optimizing number of hidden neurons in neural networks", Proceedings of the IASTED Int Conf .
  15. Panchal, G., Ganatra, A., Kosta, Y.P. and Panchal, D. (2011), "Behaviour analysis of multilayer perceptrons with multiple hidden neurons and hidden layers", Int.J. Comput. Theory Eng., 3, 332-337.
  16. Sartori, M.A. and Antsaklis, P.J. (1991), "A simple method to derive bounds on the size and to train multilayer neural networks", IEEE T. Neural Networ., 2(4), 467-471. https://doi.org/10.1109/72.88168
  17. Sivanandam, S.N., Sumathi, S. and Deepa, S.N. (2008), Introduction to neural networks using Matlab 6.0, Tata McGraw Hill, 1st Ed.
  18. Sun, J. (2012), "Learning algorithm and hidden node selection scheme for local Coupled feed forward neural network classifier", Neurocomputing, 79, 158-163. https://doi.org/10.1016/j.neucom.2011.09.019
  19. Tamura, S. and Tateishi, M. (1997), "Capabilities of a four layered feed forward neural network: four layers versus three", IEEE T. Neural Networ., 8(2), 251-255. https://doi.org/10.1109/72.557662
  20. Trenn, S. (2008), "Multilayer perceptrons: approximation order and necessary number of hidden units", IEEE T. Neural Networ., 19(5), 836-844. https://doi.org/10.1109/TNN.2007.912306
  21. Xu, S. and Chen, L. (2008), "A novel approach for determining the optimal number of hidden layer neurons for FNN's and its application in data mining", Proceedings of the 5th Int. Conf. on Inform. Techn. and Appln.
  22. Zeng, X., and Yeung, D.S.(2006), "Hidden neuron pruning of multilayer perceptrons using a quantified sensitivity measure", Neurocomputing, 69(7-9)825-837. https://doi.org/10.1016/j.neucom.2005.04.010
  23. Zhang, Z., Ma, X. and Yang, Y. (2003), "Bounds on the number of hidden neurons in three layers Binary neural networks", Neural Networks, 16(7), 995-1002. https://doi.org/10.1016/S0893-6080(03)00006-6

Cited by

  1. An integrator based wind speed estimator for wind turbine control vol.21, pp.4, 2015, https://doi.org/10.12989/was.2015.21.4.443