Computational Technology Resources - CCP

M.A. Saif, M.S. Al-Bisy, "Stability Prediction of Asphaltic Concrete Mixes using Multiple Additive Regression Trees", in Y. Tsompanakis, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Fourth International Conference on Soft Computing Technology in Civil, Structural and Environmental Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 30, 2015. doi:10.4203/ccp.109.30

Keywords: asphaltic concrete, Marshall stability, Marshall flow, multiple additive regression trees.

Summary

The Marshall stability of asphalt concrete is one of the important features for performance of asphalt pavement. This paper presents the design, implementation, and testing of a multiple additive regression trees (MART) and multilayer perceptron neural networks (MLP) models. This can serve as a modern innovative technological approach to the prediction of stability of asphaltic concrete mixes on the basis of experimental data, without reliance on a mathematical relationship. The results indicate that the MART method's prediction accuracy and avoidance of over-fitting were superior to those of the MLP method. Moreover, the results obtained in this investigation demonstrate that the MART model was more efficient and robust than the other. Finally, the analysis of the results suggests that MART-based modeling is effective in predicting stability of asphaltic concrete mixes. This paper shows that transportation and highway engineers can use the MART model to predict the stability of asphaltic concrete mixes without conducting costly and time consuming experimental tests.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £50 +P&P)

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Proceedings ISSN 1759-3433 CCP: 109 PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON SOFT COMPUTING TECHNOLOGY IN CIVIL, STRUCTURAL AND ENVIRONMENTAL ENGINEERING Edited by: Y. Tsompanakis, J. Kruis and B.H.V. Topping Paper 30 Stability Prediction of Asphaltic Concrete Mixes using Multiple Additive Regression Trees M.A. Saif and M.S. Al-Bisy Civil Engineering Department, Umm Alqura University, Makkah, Saudi Arabia doi:10.4203/ccp.109.30 purchase the full-text of this paper Full Bibliographic Reference for this paper M.A. Saif, M.S. Al-Bisy, "Stability Prediction of Asphaltic Concrete Mixes using Multiple Additive Regression Trees", in Y. Tsompanakis, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Fourth International Conference on Soft Computing Technology in Civil, Structural and Environmental Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 30, 2015. doi:10.4203/ccp.109.30 Keywords: asphaltic concrete, Marshall stability, Marshall flow, multiple additive regression trees. Summary The Marshall stability of asphalt concrete is one of the important features for performance of asphalt pavement. This paper presents the design, implementation, and testing of a multiple additive regression trees (MART) and multilayer perceptron neural networks (MLP) models. This can serve as a modern innovative technological approach to the prediction of stability of asphaltic concrete mixes on the basis of experimental data, without reliance on a mathematical relationship. The results indicate that the MART method's prediction accuracy and avoidance of over-fitting were superior to those of the MLP method. Moreover, the results obtained in this investigation demonstrate that the MART model was more efficient and robust than the other. Finally, the analysis of the results suggests that MART-based modeling is effective in predicting stability of asphaltic concrete mixes. This paper shows that transportation and highway engineers can use the MART model to predict the stability of asphaltic concrete mixes without conducting costly and time consuming experimental tests. purchase the full-text of this paper (price £20) go to the previous paper go to the next paper return to the table of contents return to the book description purchase this book (price £50 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions