Preliminary Quantity Estimate of Highway Bridges using Neural Networks

Generalized linear model-based expert system for estimating the cost of transportation projects

“…Furthermore, many studies have investigated unit cost estimating relationships (CERs) between cost (dollar per lane length) and plan quantity or between cost and cost drivers for building and infrastructure construction using either statistical techniques or neural networks (Al-Tabtabai, Alex, & Tantash, 1999;Bell, 1987;Chengalur-Smith et al, 1997;Emsley, Lowe, Duff, Harding, & Hickson, 2002;Hegazy & Ayed, 1998;Herbsman, 1983;Jrade & Alkass, 2002;Lowe, Emsley, & Harding, 2006;Masi, 2003;Morcous, Bakhoum, Taha, & El-Said, 2001;Phaobunjong & Popescu, 2003;Saito et al, 1991;Sanders et al, 1992;Williams, 2005;Yu, 2006). Hegazy and Ayed (1998) developed a parametric cost estimating model for highway projects using a neural network approach, rather than using black-box commercial software.…”

“…In this study, the use of the spreadsheet interface unraveled the complicated analysis process and the total budget cost for the project was output. Morcous et al (2001) used neural networks to estimate preliminary item-level quantity of concrete volume and prestressing weight for highway bridges in Egypt. The estimate errors were found to be within ±7.5% and ±11.5% for concrete volume and prestressing weight respectively.…”

Early Bill-of-Quantities Estimation of Concrete Road Bridges: An Artificial Intelligence-Based Application

“…Similarly, Ugwu and Kumaraswamy (2004) used data of location, pavement material, and project configuration from 74 highway bridges in Hong Kong to train an ANN to predict their construction cost. Furthermore, Morcous, Bakhoum, Taha, and El-Said (2001) used data from 22 prestressed concrete bridges constructed in Egypt to develop an ANN capable of estimating the concrete volume and prestressed steel weight of bridge superstructures. The input attributes selected for the training of the ANN model were the maximum span length, the superstructure type, the structure system, the construction method, the contract type, and the design type.…”

Construction cost estimation of reinforced and prestressed concrete bridges using machine learning

“…The network was trained using a set of eighteen highway projects constructed in Newfoundland, Canada. Marcous et al used ANN with backpropagation learning algorithm to predict the volume of concrete and the weight of prestressing steel in bridge superstructure [8]. A set of twenty-two prestressed concrete bridges over the Nile in Egypt was used for network training.…”