Neural network models for actual duration of Greek highway projects

Abstract

Purpose 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. Design/methodology/approach 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. Findings 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. Research limitations/implications The sample size is limited to 37 projects. These are extensive highway projects with similar work packages, constructed in Greece. Practical implications The proposed models could early in the planning stage predict the actual project duration. Originality/value 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.

Conceptual estimation of construction duration and cost of public highway projects

“…Several studies have attempted to model the relationship between highway projects features and their durations in early stages (Nevett et al, 2021, Titirla and Aretoulis 2019, Son et al, 2019, Okere, 2019, Nani et al, 2017, Pesko et al, 2017. Pesko et al, (2017) concluded that integrating the estimation of duration and cost can compromise the significance of input data, leading to reduction of estimating accuracy compared to that based on separate estimation.…”

“…As a result, it is generally advised to create more than one predictive model (Elmousalami, 2021). In the current study, Artificial Neural Networks (ANN), Support vector Machines (SVM), and Random Forest (RF) algorithms were selected, as they are commonly used in construction research domain (Elmousalami, 2021, Meharie and Shaik, 2020, Juszczyk, 2020, Titirla and Aretoulis, 2019, Pesko et al, 2017. They were subsequently combined in an ensemble to benefit from their collective strengths and balance their weaknesses.…”

“…For example, they have been used for the conceptual estimation of highway projects cost especially when limited information is available (Meharie and Shaik, 2020, Tijanic et al, 2019, Karaca et al, 2020, Aretoulis, 2019, Cao et al, 2018, Gardner et al, 2017, Chou et al, 2015. Additionally, they have been applied to estimate the duration of highway projects in their early stages, though not as widely as cost (Titirla and Aretoulis, 2019, Nani et al, 2017, Pesko et al, 2017, Mensah et al, 2016. ANN has gained popularity in several disciplines owing to its superiority in comparison with other AI techniques for several reasons (Sharma et al, 2021).…”

Delay Risk Assessment Models for Road Projects

“…In fact, the reasons for delay for a significant number of the projects were personally witnessed by the author, who has 22 years of professional experience at Egnatia Odos S.A. (EOSA), the client organization responsible for the design, procurement and supervision of the construction of Egnatia Odos Highway and other major and minor road projects in Northern Greece and some of the Greek Islands. Furthermore, EOSA has been a source of data for construction management research in research domains such as actual duration prediction [27], value for money bridge design [39] and construction material consumption and actual cost prediction [40]. Hence, this data collection approach, which is alternative to interviewing or circulating a relevant questionnaire, belongs to a group of methods known as unobtrusive measures [38].…”

Modeling duration of building renovation projects

“…Waziri (2012a) developed a mathematical model in the form of Bromilow's time-cost model for the prediction of construction time of institutional building projects in North Eastern Nigeria. William (2008) conducted a study to develop mathematical models for the preliminary prediction of highway construction duration, Nani et al (2017) developed a model for forecasting duration for bridge projects, while Titirla and Aretoulis (2019) developed a model to predict the duration of Greek highway projects, while Alemu (2022) developed a model for predicting construction time for public building projects.…”