Abstract
The artificial intelligent methodology is applied to building inspection system in this paper. Inspection results from Applied Technology Council (ATC) procedures are used as an indicator to the building damage level. Backpropagation algorithm with one hidden layer is used to develop the neural network and Borland C++ is used as the programming language. The choice of input variables is a fundamental. The neural network performance is analysed by removed the input one by one from the network. The mean square error (MSE) value is equal to 0.027 when all inputs are applied to the network. The lowest MSE is 0.025 when the length is excluded from the network. Lower MSE value indicates lower error among others. Even though the lowest MSE is presented when the length is excluded from the network, but the different was too small which is 0.002. Thus, the length is still applied in network. From the application of Artificial Neural Network (ANN), building samples gave the lowest value of MSE equal to 0.027 when 15 hidden neurons applied and the highest linear correlation coefficient was obtained when r is equal to 0.839 in testing phase and 0.762 in validation phase. Out of 112 samples in the testing phase, 104 samples were predicted accurately for degree of damage rating for the building which represents 93 % from the total data used. In the validation phase, 39 out of 52 samples were predicted accurately with 75 % accuracy. The results of this study indicate that the ANNs provide an efficient means of damage forecasting and would be useful by the owners of the building to predict building conditions under seismic load.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
S. Giovinazzi, The vulnerability assessment and the damage scenario in seismic risk analysis. Ph.D. Thesis, Technical University Carolo-Wilhelmina at Braunschweig, Braunschweig, Germany and University of Florence, Florence, Italy, 2005
C. Stergiou, D. Siganos, Neural networks, in Report of An Introduction to Artificial Neural Networks (1999)
S. Ramhormozian, P. Omenzetter, R. Orense, Artificial neural networks approach to predict principal ground motion parameters for quick post-earthquake damage assessment of bridges, in NZSEE Conference (2013)
M. Mardiyono, R. Suryanita, A. Adnan, Intelligent monitoring system on prediction of building damage index using neural-network, TELKOMNIKA 10(1), 155–164 (2012)
A. Adnan, S.C. Alih, R. Ismail, The application of artificial neural network in predicting bridge condition based on seismic zonation, in The 14th World Conference on Earthquake Engineering, 2008, Beijing, China (2008)
A. Adnan, H. Hendriyawan, A. Marto, M. Irsyam, Development of seismic hazard map for peninsular malaysia, in Proceedings on Malaysian Science and Technology Congress. PWTC Kuala Lumpur, Malaysia, 1–26 Sept 2006
J. Leonard, M.A. Kramer, Improvement of the backpropagation algorithm for training neural networks (Elsevier, Oxford, Royaume-Uni, 1977)
S.C. Alih, The application of artificial neural network in nondestructive testing for concrete bridge inspection rating system. Master Degree Thesis, University of Technology Malaysia, 2007
R.R. Shrestha, S. Theobald, F. Nestmann, Simulation of flood in a river system using artificial neural network. Hydrol. Earth Syst. Sci. 9(4), 313–321 (2005)
C.H. Chen, W.Y. Tsai, W.H. Chao, The product-moment correlation coefficient and linear regression for truncated data. J. Am. Stat. Assoc. 91 (1996)
M.A. Abdullah, A.A. Ali, Artificial neural network approach for pavement maintenance. J. Comput. Civ. Eng. 249–255 (1998)
G. Redinbo, Optimum mean-square error use of convolutional codes. IEEE Trans. Inf. Theor. 31(1), 18–33 (1985)
Acknowledgments
A special thank you goes to project RAGS funder, Ministry of Education (MOE) and support from Research Management Institute (RMI), Universiti Teknologi MARA (UiTM).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media Singapore
About this paper
Cite this paper
Ismail, R., Ibrahim, A., Adnan, A. (2014). Effect of Input Variable for Neural Network Architecture in Predicting Building Damage Subjected to Earthquake. In: Hassan, R., Yusoff, M., Ismail, Z., Amin, N., Fadzil, M. (eds) InCIEC 2013. Springer, Singapore. https://doi.org/10.1007/978-981-4585-02-6_18
Download citation
DOI: https://doi.org/10.1007/978-981-4585-02-6_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-4585-01-9
Online ISBN: 978-981-4585-02-6
eBook Packages: EngineeringEngineering (R0)