5. Summary and conclusions
This research resulted in development of a novel estimation method of site overhead cost index. The approach proposed by the authors of the paper is based on artificial intelligence tools namely neural networks. A regressive model which employs artificial neural network chosen from a number of investigated networks has been proposed. The model is capable of mapping nonlinear relationships between a set of values of describing variables (which are features that characterize the construction site overheads for a project) onto a set of values of described variable which constituted the site overhead cost index. The describing variables of the model included characteristics of a construction project in relation to the type of works, the location of the construction site, the time of works completion, as well as the organizational assumptions for the construction process. The advantage of using neural networks approach instead of a classical multivariate regres sion approach is that there is no need to assume a priori functional relationships. The ANN, chosen to be the core of the proposed model, was fitted to the data (values often describing variables and one described variable) during the training process. The proposed neural networks based approach revealed its superiority over a classical multivariate linear regression approach. On the other hand, when compared to the traditional method of site overhead cost estimation, which is a preliminary detailed analysis of all the cost components, the use of the developed novel model is significantly faster and offers variant analysis of several sets of values of describing variables at a glance.
