Search results

This paper aims to examine selected similar Greek highway projects to create artificial neural network-based models to predict their actual construction duration based on data available at the bidding stage.

Relevant literature review is presented that highlights similar research approaches. Thirty-seven highway projects, constructed in Greece, with similar type of available data, were examined. Considering each project’s characteristics and the actual construction duration, correlation analysis is implemented, with the aid of SPSS. Correlation analysis identified the most significant project variables toward predicting actual duration. Furthermore, the WEKA application, through its attribute selection function, highlighted the most important subset of variables. The selected variables through correlation analysis and/or WEKA and appropriate combinations of these are used as input neurons for a neural network. Fast Artificial Neural Network (FANN) Tool is used to construct neural network models in an effort to predict projects’ actual duration.

Variables that significantly correlate with actual time at completion include initial cost, initial duration, length, lanes, technical projects, bridges, tunnels, geotechnical projects, embankment, landfill, land requirement (expropriation) and tender offer. Neural networks’ models succeeded in predicting actual completion time with significant accuracy. The optimum neural network model produced a mean squared error with a value of 6.96E-06 and was based on initial cost, initial duration, length, lanes, technical projects, tender offer, embankment, existence of bridges, geotechnical projects and landfills.

The sample size is limited to 37 projects. These are extensive highway projects with similar work packages, constructed in Greece.

The proposed models could early in the planning stage predict the actual project duration.

The originality of the current study focuses both on the methodology applied (combination of Correlation Analysis, WEKA, FannTool) and on the resulting models and their potential application for future projects.