DEVELOPMENT OF THE ARTIFICIAL NEURAL NETWORK MODEL FOR PREDICTION OF IRAQI EXPRESS WAYS CONSTRUCTION COST

The main objective of this research is to introduce a new and alternative approach of using a neural network for cost estimation of the expressway project at the early stage. A preliminary literature survey and data collection have identified the problem and led to the formulation of the research hypothesis that there is a weakness in estimating the cost of the expressway construction projects because the current available techniques are poor and suffer some disadvantages such as being traditional, aged, slow and uncertain. Besides, the need for a modern efficient construction cost estimation techniques that have more advantages such as being modern, fast, accurate, flexible and easy to use is of value. Also, the application of Artificial Neural Networks, as a modern technique, in Iraqi construction industry is necessary to ensure successful management, and many of the construction companies feel the need of such system in project management One model was built for the prediction the cost of expressway project. The data used in this model was collected from Stat Commission for Roads and Bridges in Iraq. It was found that ANNs have the ability to predict the Total Cost for expressway project with a good degree of accuracy of the coefficient of correlation (R) was 90.0%, and average accuracy percentage 89%.The ANNs model developed to study the impact of the internal network parameters on model performance indicated that ANNs performance was relatively insensitive to the number of hidden layer nodes, momentum term, and learning rate.