Premium
Pavement Roughness Modeling Using Back‐Propagation Neural Networks
Author(s) -
Choi Jaeho,
Adams Teresa M.,
Bahia Hussain U.
Publication year - 2004
Publication title -
computer‐aided civil and infrastructure engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.773
H-Index - 82
eISSN - 1467-8667
pISSN - 1093-9687
DOI - 10.1111/j.1467-8667.2004.00356.x
Subject(s) - artificial neural network , computer science , set (abstract data type) , international roughness index , sensitivity (control systems) , backpropagation , data set , data mining , asphalt , surface finish , statistical analysis , term (time) , engineering , machine learning , artificial intelligence , statistics , mathematics , geography , mechanical engineering , physics , cartography , quantum mechanics , electronic engineering , programming language
Quantifying the relationship between material and construction (M&C) variables and pavement performance is an on‐going important research area. It is, however, realized that deriving such relationships is too complex and too poorly understood to develop using traditional statistical methods. Therefore, this study is focused on the analysis of a data set from the long‐term pavement performance (LTPP) database to quantify the contribution of M&C variables of asphalt concrete on pavement performance (i.e., international roughness indicator) using a back‐propagation neural network (BPNN) algorithm. It was found that by using sensitivity analysis neural network trained with optimal number of epochs could be used effectively for better understanding of the factors controlling overall performance indicators, establishing quantitative functions to weigh the role of such factors, and for use in performance‐related specifications.