Fitting Conventional Neural Network Time Series Models on Sand Price Indices Dataset

  • Authors

    • Nor Azura Md Ghani
    • Saadi Bin Ahmad Kamaruddin
    • Ismail Musirin
    • Hishamuddin Hashim
    2018-08-13
    https://doi.org/10.14419/ijet.v7i3.15.17396
  • Neural Network, Conventional Nonlinear Autoregressive (NAR), Conventional Nonlinear Autoregressive Moving Average (NARMA), Sand Price Indices

  • This result-based paper discusses on the best aftereffects of both fitted BPNN-NAR and BPNN-NARMA on MCCI Sand dataset regarding distinctive error measures. This exploration examine the outcomes as far as the execution of the fitted forecasting models by every arrangement of input lags and error lags utilized, the execution of the fitted anticipating models by various hidden nodes utilized, the execution of the fitted estimating models when joining both inputs and hidden nodes, the consistency of error measures utilized for the fitted determining models, and in addition the general best fitted estimating models for Malaysian sand price indices dataset. In this examination, Malaysian sand price indices monthly data from January 1980 to December 2013 were adapted. The examination of BPNN-NAR on Malaysian sand data shows that insufficient or inadequate combination of input and error lags lead to greater RMSE. Correspondingly, the number of input lags for BPNN-NAR, as well as the number of input and error lags for BPNN-NARMA really have direct effect to the models’ performances. The higher or the lesser hidden nodes to the input lags, the higher the network’s RMSE. On the other hand, the higher the input lags lead to the higher network’s RMSE.

     

     

  • References

    1. [1] Samarasinghe, S. (2006). Neural networks for applied sciences and engineering: from fundamentals to complex pattern recognition. CRC Press

      [2] Zhang, G. P. (2004). Business forecasting with artificial neural networks: An overview. Neural networks in business forecasting, 1-22.

      [3] Kim, D. (2001). Neural Networks for Trip Generation Model. Journal of the Eastern Asia Society for Transportation Studies, 4(2), pp. 201-208.

      [4] Ghosh, S. & Konar, A. (2012). Call Admission Control in Mobile Cellular Networks (Vol. 437). Springer.

      [5] Qiu, F. & Jensen, J. R. (2004). Opening the black box of neural networks for remote sensing image classification. International Journal of Remote Sensing, 25(9), pp. 1749-1768.

      [6] Heinert, M. (2008). Artificial neural networks–how to open the black boxes.Application of Artificial Intelligence in Engineering Geodesy, 1(2008), pp. 42-62.

      [7] Hametner, C. & Jakubek, S. (2011). Nonlinear Identification with Local Model Networks Using GTLS Techniques & Equality Constraints. IEEE Trans Neural Networks, 22(9), pp. 1406-1418.

      [8] Barbosa, B. H. G., Aguirre, L. A., Martinez, C. B. & Braga, A. P. (2011). Black and Gray-Box Identification of a Hydraulic Pumping System. IEEE Trans. Control Systems Technology, 19(2), pp. 398-406.

      [9] Ahmadi, S. S. & Karrari, M. (2011). Nonlinear identification of synchronous generators using a local model approach. Przeglad Elektrotechniczny (Electrical Review), vol. 8, pp. 166-170.

      [10] Talmon, R., Kushnir, D., Coifman, R. R., Cohen, I., & Gannot, S. (2012). Parametrization of linear systems using diffusion kernels. IEEE Transactions on Signal Processing, 60(3), pp. 1159-1173.

      [11] Olvera M. A. G.- & Tang, Y. (2010). Black-Box Identification of a Class of Nonlinear Systems by a Recurrent Neurofuzzy Network. IEEE Trans Neural Networks, 21(4), pp. 672-679.

      [12] Dong, N. & Chen, Z. (2012). A novel data based control method based upon neural network and simultaneous perturbation stochastic approximation. Nonlinear Dynamics, 1(67), pp. 957-963.

      [13] Safak, C., Topuz, V. & Baba, A. F. (2010). Pneumatic motor speed control by trajectory tracking fuzzy logic controller. Sadhana, 35(1), pp. 75-86.

      [14] Rashid, M. T., Frasca, M., Ali, A. A., Ali, R. S., Fortuna, L. & Xibilia, M. G. (2012). Nonlinear model identification for Artemia population motion. Nonlinear Dynamics, 69(4), pp. 2237-2243.

      [15] Boëly, N. & Botez, R. M. (2010). New Approach for the Identification and Validation of a Nonlinear F/A-18 Model by Use of Neural Networks. IEEE Trans Neural Networks, 21(11), pp. 1759-1765.

      [16] Ren, X. & Lv, X. (2011). Identification of Extended Hammerstein Systems Using Dynamic Self-Optimizing Neural Networks, IEEE Trans Neural Networks, vol. 22(8), pp. 1169-1179.

      [17] Boëly, N. & Botez, R. M. (2010). New Approach for the Identification and Validation of a Nonlinear F/A-18 Model by Use of Neural Networks. IEEE Trans Neural Networks, 21(11), pp. 1759-1765.

      [18] Arnerić, J., Poklepović, T., & Aljinović, Z. (2014). GARCH based artificial neural networks in forecasting conditional variance of stock returns. Croatian Operational Research Review, 5(2), pp. 329-343.

      [19] Beliakov, G., Kelarev, A. & Yearwood, J. (2011). Robust artificial neural networks & outlier detection. Technical report.

      [20] Kordos, M., & Rusiecki, A. (2015). Reducing noise impact on MLP training. Soft Computing, 1(1), pp. 1-17.

      [21] Baruah, M., Misra, A., & Sarma, K. K. (2017). Split FTDNN-DFE equalizer for complex non-linear wireless channels with NARMA approximation. Journal of Intelligent Systems, 26(1), 87-107.

      [22] Janczak, A. (2004). Identification of nonlinear systems using neural networks and polynomial models: a block-oriented approach (Vol. 310). Springer Science & Business Media.

      [23] Yassin, I. M., Zabidi, A., Salleh, M. K. M. & Khalid, N. E. A. (2013). Malaysian tourism interest forecasting using Nonlinear Auto-Regressive (NAR) model. 2013 IEEE 3rd International Conference on System Engineering & Technology (ICSET), 1(1), pp. 32-36.

      [24] Allende, H., Salas, R., Torres, R. & Moraga, C. (2005). Modular Neural Network Applied to Non-Stationary Time Series. Computational Intelligence, Theory and Applications, pp. 585-598.

      [25] Nelles, O. (2013). Nonlinear system identification: from classical approaches to neural networks and fuzzy models. Springer Science & Business Media.

      [26] Kamaruddin, S. A., Ghani, N. A. M., & Ramli, N. M. (2013). Determining the best forecasting method to estimate unitary charges price indexes of PFI data in central region Peninsular Malaysia. Research in Mathematical Sciences, vol. 1522, no. 1, pp. 1232-1239.

      [27] Kamaruddin, S. A., Ghani, N. A. M., & Ramli, N. M. (2014). Best Forecasting Models for Private Financial Initiative Unitary Charges Data of East Coast and Southern Regions in Peninsular Malaysia. International Journal of Economics and Statistics, vol. 2, pp. 119-126

      [28] Kamaruddin, S. A., Ghani, N. A. M., & Ramli, N. M. (2014). Comparative Study of Particle Swarm Optimization (PSO) and Firefly Algorithm (FA) on Least Median Squares (LMedS) for Robust Backpropagation Neural Network Learning Algorithm. Australian Journal of Basic and Applied Science, 8(24), pp.117-129.

      [29] Kamaruddin, S. A., Ghani, N. A. M., & Ramli, N. M. (2016). The improved BPNN-NAR and BPNN-NARMA models on Malaysian aggregate Price indices with outlying data. Jurnal Teknologi, 78(12-3), pp. 77-83.

      [30] Kamaruddin, S. A., Ghani, N. A. M., & Ramli, N. M. (2016). The Superiority of Panel SPSM-KSS Fourier Univariate Unit Root Test towards Problematic PFI Time Series Data. International Journal of Economics and Management Systems, vol. 1, pp. 31-38

      [31] Kamaruddin, S. A., Ghani, N. A. M., & Ramli, N. M. (2016). The Superiority of Evolutionary Algorithms to Robustify Backpropagation Neural Network Learning Algorithm. Journal of Applied Environmental and Biological Sciences, 6(25), pp. 17-31.

      [32] Kamaruddin, S. A., Ghani, N. A. M., & Ramli, N. M. (2016). The Improved BPNN-NAR and BPNN-NARMA Models on Malaysian Aggregate Price Indices with Outlying Data. Jurnal Teknologi, 78 (11–4), pp. 77-84

      [33] Ghani, N. A. M., Kamaruddin, S. B. A., Ramli, N. M., Musirin, I., & Hashim, H. (2017). Modified BPNN via Iterated Least Median Squares, Particle Swarm Optimization and Firefly Algorithm. Indonesian Journal of Electrical Engineering and Computer Science, 8(3), pp. 779-786.

      [34] Ghani, N. A. M., Kamaruddin, S. A., Ramli, N. M., Musirin, I., & Hashim, H. (2017). Enhanced BFGS Quasi-Newton Backpropagation Models on MCCI Data. Indonesian Journal of Electrical Engineering and Computer Science, 8(1), 101-106.

      [35] Kamaruddin, S. B. A., Tolos, S. M., Hee, P. C., Ghani, N. A. M., Ramli, N. M., Nasir, N. B. M., ... & Huq, M. S. (2017). The quadriceps muscle of knee joint modelling Using Hybrid Particle Swarm Optimization-Neural Network (PSO-NN). Journal of Physics, vol. 819, No. 1, pp. 012-029.

      [36] Kamaruddin, S. A., Ghani, N. A. M., & Ramli, N. M. (2018). Consolidated Backpropagation Neural Network for Malaysian Construction Prices Indices Data with Outliers Problem. Pertanika J. Sci. & Technol., 26 (1): 353 – 366.

  • Downloads

  • How to Cite

    Azura Md Ghani, N., Bin Ahmad Kamaruddin, S., Musirin, I., & Hashim, H. (2018). Fitting Conventional Neural Network Time Series Models on Sand Price Indices Dataset. International Journal of Engineering & Technology, 7(3.15), 11-15. https://doi.org/10.14419/ijet.v7i3.15.17396