Conventional Neural Network Time Series Models on Roof Materials Costs Indices Data
 Abstract
 Keywords
 References

Abstract
The Construction Financial Management Association (CFMA) found that twothirds of participant contractors identify variability in construction as an important risk affecting profits. Varieties in construction costs also have negative and horrible effects on public or private proprietor associations.Gradual changes in Construction Costs Indices (CCI) affect the accuracy of engineering cost estimates for proprietors causing construction projects to be delivered with higher costs, schedule delays, and several insolvencies. Reliable forecasting for future construction costs would help to guarantee spending plans and limited resources allocations more appropriately. Estimating costs based on such indexes are adopted widely in the construction industry (by (1) associating the total cost of a facility with several major parameters of the facility, such as size, system, and location; and (2) analysing the trend of indexes relevant to construction costs over time.This research implements two models which are backpropagation neural nonlinear autoregressive (BPNNNAR) and backpropagation neural nonlinear autoregressive moving average (BPNNNARMA) on Malaysian Roof Materials dataset. The best model for this data is BPNNNAR models with 101010 configurations based on RMSE=0.414. It is expected that this research is significant towards helping the policy makers and contractors to make proper decisions, biddings and budgeting on the nation’s infrastructure projects.

Keywords
Trend analysis, backpropagation, nonlinear autoregressive (NAR), nonlinear autoregressive moving average (NARMA0, Malaysian roof materials

References
[1] Shane, J. S., Molenaar, K. R.,&Anderson, S.,& Schexnayder, C. (2009). Construction project cost escalation factors. Journal of Management in Engineering, 25(4), pp. 221229.
[2] Williams, T. P. (1994). Predicting changes in construction cost indexes using neural networks. Journal of Construction Engineering and Management, 120(2), pp. 306–320.
[3] Ashuri, B. & Lu, J. (2010b). Forecasting ENR construction cost index: A time series analysis approach. Proceedings of Construction Research Congress 2010 & Innovation for Reshaping Construction Practice, 1(1), pp. 13451355.
[4] Ervin, E. (2007). How to protect profit as material prices rise. Puget Sound Business Journal, 1(1), pp. 17.
[5] Gallagher, J. P. (2008). Material Price Escalation: Managing the Risks. Construction eNewsletter.
[6] Wong, J. M., Ng, S. T. & Chan, A. P. (2010). Strategic planning for the sustainable development of the construction industry in Hong Kong. Habitat International, 34(2), pp. 256263.
[7] Rao, G. N. & Grobler, F. (1997). Integrated analysis of cost risk and schedule risk. Proc., 4th Congress on Computing in Civil Engineering, pp. 1404–1411.
[8] Flood, I. (1997). Modeling uncertainty in cost estimates: A universal extension of the central limit theorem. Proc., 4th Congress on Computing in Civil Engineering, 1(1), pp. 551–558.
[9] Trost, S. M. & Oberlender, G. D. (2003). Predicting accuracy of early cost estimates using factor analysis and multivariate regression. ASCE Journal of Construction Engineering and Management, 129(2), pp. 198204.
[10] Attalla, M. & Hegazy, T. (2003). Predicting cost deviation in reconstruction projects: Artificial neural networks versus regression. J. Constr. Eng. Manage., 129(4), pp. 405–411.
[11] Touran, A. (2003). Probabilistic model for cost contingency. Journal of Construction Engineering Management, 129(3), pp. 280–284.
[12] Doğan, S. Z., Arditi, D. & Günaydın, H. M. (2006). Determining attribute weights in a CBR model for early cost prediction of structural systems. J. Constr. Eng. Manage., 132(10), pp. 1092–1098.
[13] Diekmann, J. E. (1983).Probabilistic estimating: Mathematics and applications.J. Constr. Eng. Manage., 109(3), pp. 297–308.
[14] Koppula, S. D. (1981).Forecasting engineering costs: Two case studies. Journal Constr. Div., 107(4), pp. 733–743.
[15] Wilmot, C. G. & Cheng, G. (2003).Estimating future highway construction costs.Journal of Construction Engineering Management, 129(3), pp. 272–279.
[16] ElMelegy, M. T., Essai, M. H. & Ali, A. A. (2009). Robust training of artificial feedforward neural networks. Found Comput Intell 1, 1(1), pp. 217–242.
[17] Allende, H., Moraga, C. & Salas, R. (2002a). Artificial neural networks in time Series forecasting: A comparative analysis. Kybernetika, 38 (6), 685707.
[18] Allende, H., Moraga, C. & Salas, R. (2002b). Robust estimator for the learning process in neural networks applied in time series. Proceedings of International Conference on Artificial Neural Networks, pp. 10801086.
[19] Mohit, M. A., Ibrahim, M. & Rashid, Y. R. (2010). Assessment of residential satisfaction in newly designed public lowcost housing in Kuala Lumpur, Malaysia. Habitat International, 34(1), pp. 1827.
[20] Uilhoorn, F. E. (2016). Comparison of two nonconvex mixedinteger nonlinear programming algorithms applied to autoregressive moving average model structure and parameter estimation. Engineering Optimization, 1(1), pp. 114.
[21] Ding, F., Wang, X., Chen, Q. & Xiao, Y. (2016). Recursive least squares parameter estimation for a class of output nonlinear systems based on the model decomposition. Circuits, Systems, and Signal Processing, 1(1), pp. 116.
[22] PilotoRodríguez, R., SánchezBorroto, Y., Lapuerta, M., GoyosPérez, L. & Verhelst, S. (2013). Prediction of the cetane number of biodiesel using artificial neural networks and multiple linear regression. Energy Conversion and Management, 1(65), pp. 255261.
[23] Velo, A., Pérez, F. F., Tanhua, T., Gilcoto, M., Ríos, A. F. & Key, R. M. (2013). Total alkalinity estimation using MLR and neural network techniques.Journal of Marine Systems, 111, pp. 1118.
[24] Haviluddin, H., & Jawahir, A. (2015). Comparing of ARIMA and RBFNN for shortterm forecasting. International Journal of Advances in Intelligent Informatics, 1(1), 1522.
[25] Ghani, N. A. M., Kamaruddin, S. B. A., Musirin, I., & Hashim, H. (2018). Results of Fitted Neural Network Models on Malaysian Aggregate Dataset. Bulletin of Electrical Engineering and Informatics, 7(2), 272278.
[26] Ghani, N. A. M., Kamaruddin, S. B. A., Musirin, I., & Hashim, H. (2018). Conventional Neural Network Time Series Models on Sand Price Indices Dataset. International Journal of Engineering and Technology, 7(3.15), 1115.
[27] Saadi Bin Ahmad Kamaruddin, Nor Azura Md Ghani, Norazan Mohamed Ramli,(2018). Consolidated Backpropagation Neural Network for Malaysian Construction Costs Indices Data with Outliers Problem. Pertanika J. Sci. & Technol., 26 (1): 353 – 366.
[28] Ghani, N. A. M., Kamaruddin, S. A., Ramli, N. M., Musirin, I., & Hashim, H. (2017). Enhanced BFGS QuasiNewton Backpropagation Models on MCCI Data. Indonesian Journal of Electrical Engineering and Computer Science, 8(1), 101106.
[29] Sibi, P., Jones, S. A. & Siddarth, P. (2013). Analysis of different activation functions using back propagation neural networks. Journal of Theoretical and Applied Information Technology, 47(3), pp. 12641268.
[30] Sofian, I. M., Affandi, A. K., Iskandar, I., & Apriani, Y. (2018). Monthly rainfall prediction based on artificial neural networks with backpropagation and radial basis function. International Journal of Advances in Intelligent Informatics, 4(2).
[31] Beliakov, G., Kelarev, A. & Yearwood, J. (2012). Derivativefree optimization and neural networks for robust regression. Optimization, 61(12), pp. 14671490.
[32] Alfons, A., Croux, C. & Gelper, S. (2013). Sparse least trimmed squares regression for analyzing highdimensional large data sets. The Annals of Applied Statistics, 7 (1), pp. 226248.
[33] Zioutas, G., Avramidis, A. & Pitsoulis, L. (2007). Penalized Trimmed Squares and A ModiFication of Support Vectors for UnMasking Outliers in Linear Regression. REVSTAT–Statistical Journal, 5(1), pp. 115136.

View 
Download  Article ID: 25954 
