Computational & Technology Resources
an online resource for computational,
engineering & technology publications
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 32

Pavement Roughness Progression Modeling using Artificial Neural Networks and Multivariate Adaptive Regression Splines

P. Georgiou, C. Plati and A. Loizos

Laboratory of Pavement Engineering, National Technical University of Athens, Greece

Full Bibliographic Reference for this paper
P. Georgiou, C. Plati, A. Loizos, "Pavement Roughness Progression Modeling using Artificial Neural Networks and Multivariate Adaptive Regression Splines", 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 32, 2015. doi:10.4203/ccp.109.32
Keywords: pavement, roughness, international roughness index, modeling, artificial neural networks, multivariate adaptive regression splines.

Summary
Pavement performance models are imperative for a complete pavement management system (PMS), providing the possibility of analysing, designing, planning, projecting, ranking and optimising the choice of alternatives, allocating costs and apportioning funds. Roughness can serve as an important indicator in determining the road surface's serviceability and thus the assessment of roughness progression over time is considered of outmost importance. In this paper, two models, based on artificial neural networks (ANNs) and multivariate adaptive regression splines (MARS) techniques are developed to predict roughness in terms of international roughness index (IRI), analyzing a series of field data collected from a Greek motorway. The results indicate that both ANN- and MARS-based models seem to be capable of predicting pavement surface roughness; hence they can be useful in support of decision making concerning maintenance priorities and strategies. The recommendation for which of the two techniques should be selected for the purpose of the analysis is mainly dependent on the analyser's skills, since the MARS one seems to require less expertise.

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