Multivariate adaptive regression (MARS) and hinged hyperplanes (HHP) for doweled pavement performance modeling

Abstract Standard neural networks in infrastructure performance modeling cannot handle discontinuities in the input training data set, and the performance can in some cases be an issue in the presence of higher frequency and higher order non linearity in pavement condition, traffic and other environmental data. This makes the traditional neural network more of a “black box” with limited physical explanation of the results. This paper is a comparative analysis between multivariate adaptive regression and hinged hyperplanes for doweled pavement performance modeling.

[1]  Kurt D Smith,et al.  FIELD-CALIBRATED MECHANISTIC-EMPIRICAL MODELS FOR JOINTED CONCRETE PAVEMENTS , 1991 .

[2]  Peter Craven,et al.  Smoothing noisy data with spline functions , 1978 .

[3]  Nii O. Attoh-Okine.  Combining use of rough set and artificial neural networks in doweled-pavement-performance modeling: A hybrid approach , 2002 .

[4]  Dan Steinberg,et al.  An alternative to neural nets: multivariate adaptive regression splines (MARS) , 2001 .

[5]  Leo Breiman,et al.  Hinging hyperplanes for regression, classification, and function approximation , 1993, IEEE Trans. Inf. Theory.

[6]  Anastasios M. Ioannides,et al.  CONTROL OF FAULTING THROUGH JOINT LOAD TRANSFER DESIGN , 1990 .

[7]  E O Lukanen,et al.  PERFORMANCE HISTORY AND PREDICTION MODELING FOR MINNESOTA PAVEMENTS , 1994 .

[8]  P E Irick,et al.  The Pavement Serviceability-Performance Concept , 1960 .

[9]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[10]  J M Armaghani.  FACTORS AFFECTING PERFORMANCE OF CONCRETE PAVEMENTS , 1993 .

[11]  R. Tibshirani,et al.  Adaptive Principal Surfaces , 1994 .

[12]  William G. Davids,et al.  Effect of Dowel Looseness on Response of Jointed Concrete Pavements , 2000 .

[13]  Bruce R. Kowalski,et al.  MARS: A tutorial , 1992 .

[14]  Nii O Attoh-Okine,et al.  Modeling incremental pavement roughness using functional network , 2005 .

[15]  Musharraf Zaman,et al.  CONTACT-ELEMENT MODEL FOR DYNAMIC ANALYSIS OF JOINTED CONCRETE PAVEMENTS , 1995 .

[16]  Nii O. Attoh-Okine,et al.  Analysis of learning rate and momentum term in backpropagation neural network algorithm trained to predict pavement performance , 1999 .

[17]  Samer Madanat,et al.  Development of Pavement Performance Models by Combining Experimental and Field Data , 2004 .