Abstract

Kareem A Abdel Moniem
Developing Parametric Model for Conceptual Cost Estimate of Highway Projects
Conceptual cost estimates have substantial consequences on success of infrastructure projects at early stages. This paper presents a parametric model for conceptual cost estimate of highway projects. A database of 75 highway projects was collected and complied for model development. In-depth interviews with experts were conducted to Select the convenient input factors for model development. A supervised neural network model with one hidden layer optimized using Genetic Algorithms was established for determination of parameters significantly impacting cost of highway projects. The model utilized Levenberg-Marquardt algorithm as a back-propagation rule and Hyperbolic Tangent function as a transfer function for both hidden and output layers. The model was trained and evaluated to derive the linkage between highway projects’ cost, its input factors and to ensure its predictive performance, respectively. Then, a case study was carried out to test its validity and accuracy in handling real practical applications. The results showed that the developed model is reliable to be used at early stages of highway projects. Accordingly, a graphical user interface module was coded for the model to facilitate its usage and manipulation with future highway projects.