Comparison of Several Extreme Learning Machine Algorithm for Modeling Concrete Compressive Strength

Abstract:

Modeling concrete compressive strength is useful to ensure quality of civil engineering. This paper aims to compare several Extreme learning machines (ELMs) based modeling approaches for predicting the concrete compressive strength. Normal ELM algorithm, Partial least square-based extreme learning machines (PLS-ELMs) algorithm and Kernel ELM (KELM) algorithm are used and evaluated. Results indicate that the normal ELMs algorithm has the highest modeling speed, and the KELM has the best prediction accuracy. Every method is validated for modeling concrete compressive strength. The appropriate modeling approach should be selected according different purposes.

• Periodical: Applied Mechanics and Materials (Volumes 548-549)
• Pages: 1735-1738
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.548-549.1735
• Online since: April 2014
• Authors: Jian Tang*, Dong Yan, Li Jie Zhao
• Keywords: Extreme Learning Machine, Kernel Learning, Partial Least Squares, Regression Modeling

References

[1] J. Tang, W. Yu, T. Y. Chai and L. J. Zhao: Neurocomputing, Vol. 82 (2012), p.1168.

[2] G. B. Huang, Q. Y. Zhu, C. K. Siew: Neurocomputing, Vol. 70 (2006), p.489.

[3] B. Igelnik, Y. H. Pao: IEEE Transactions On Neural Networks, Vol. 6 (1995), p.1320.

[4] Y. H. Pao, G. H. Park, D. J. Sobajic: Neurocomputing, Vol. 6, (1994), p.163.

[5] L.P. Wang, C. R Wan: IEEE Transactions on Neural Networks, Vol. 19, (2008), p.1494.

[6] L. J. Zhao, D. H. Wang, T. Y. Chai: Neural Computing and Applications, Vol. 21, (2012), p.1.

[7] G. B. Huang, H. M. Zhou, X. J. Ding, R. Zhang: IEEE Transaction on Systems Man and Cybernetics-part B: Cybernetics, Vol. 42 (2011), p.513.

[8] I. C. Yeh: Cement and Concrete Research, Vol. 28, (1998), p.1797.