A new technique for using multivariate adaptive regression splines (MARS) in pavement roughness prediction-Reference-Cited by-同舟云学术

A new technique for using multivariate adaptive regression splines (MARS) in pavement roughness prediction

Published:2003-02 Issue:1 Volume:156 Page:51-55
ISSN:0965-092X
Container-title:Proceedings of the Institution of Civil Engineers - Transport
language:en
Short-container-title:Proceedings of the Institution of Civil Engineers - Transport

Author:

Attoh-Okine N. O.¹,Mensah S.¹,Nawaiseh M.²

Affiliation:

1. Department of Civil and Environmental Engineering, University of Delaware Newark, USA

2. Department of Civil and Environmental Engineering, Florida International Univeristy Miami, USA

Abstract

The paper presents the application of a new statistical technique, multivariate adaptive regression splines (MARS), to a flexible pavement roughness prediction model. MARS is a non-parametric function estimation technique that shows great promise for fitting non-linear multivariate functions. The MARS approach was used to develop a roughness equation, based on available input, and was able to identify the threshold values of each input and the most important variables contributing to the roughness equation. The MARS technique allows easy interpretation of the relative importance of pavement condition variables, environmental factors and traffic for the overall fit.

Publisher

Thomas Telford Ltd.

Subject

Transportation,Civil and Structural Engineering

Link

https://www.icevirtuallibrary.com/doi/pdf/10.1680/tran.2003.156.1.51

Reference13 articles.

1. Paterson W. D. O. Transferable Causal Model of Roughness Progression, 1989, TRB, National Research Council, Washington, DC, 70–84, Transportation Research Record 1215.

2. Carey W. N., Irick P. E. The pavement serviceability-performance concept, 1960, HRB, National Research Council, Washington, DC, 40–58, Bulletin 250.

3. Paterson W., Attoh-Okine N. O. Simplified models of paved road maintenance based on HDM-III, 1992, TRB, National Research Council, Washington, DC, 99–105, Transportation Research Record 1344.

Cited by 19 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Regression;Data Analysis in Pavement Engineering;2024

2. Modelling the effects of flexible pavement distresses in the long-term pavement performance database on performance;Journal of Innovative Transportation;2023-12-31

3. Performance of Soft Computing Technique in Predicting the Pavement International Roughness Index: Case Study;International Journal of Pavement Research and Technology;2023-07-03

4. Predicting Pavement Roughness Using Deep Learning Algorithms;Transportation Research Record: Journal of the Transportation Research Board;2021-07-24

5. A weighted multi-output neural network model for the prediction of rigid pavement deterioration;International Journal of Pavement Engineering;2021-01-08