Application of artificial neural network to forecast construction duration of buildings at the predesign stage

Essential Causes Of The Critical Site Coordination Problems In Building Projects: A Hong Kong Study

“…Neural networks analysis has been commonly adopted in the recent researches because it is designed to capture functional forms automatically, allowing the uncovering of hidden nonlinear relationships between the modeling variables. The models formulated by Bhokha and Ogunlana (1999), based on eleven independent variables and a threelayered back-propagation network to forecast the construction duration at the predesign stage of buildings in Greater Bangkok, and the model formulated by Khosrowshahi (1999), based on eleven variables and a stochastic back-propagation paradigm with one hidden layer to predict the performance of the contractor at tender stage are typical applications of neural network analysis. This technique was also widely adopted in other studies such as: forecasting the cost index (Wang and Mei, 1998) and equipment productivity (Ok and Sinha, 2006); selection of vertical formwork systems (Tam et al, 2005); and assessing the maintainability of building façade (Chew, Silva and Tan, 2004).…”

Cost estimation of structural skeleton using an interactive automation algorithm: A conceptual approach

“…The process involves several estimate iterations in parallel with conceptual or preliminary design, and can be called by other names such as rough, preliminary, order of magnitude (approximate, budget, conceptual or cost target), and feasibility estimates [10]. Cost modeling has been classified into three main models according to the literature [11][12][13]:…”

Solution to the Problem of Inaccurate Duration-Estimation: Relational Database Model for Design/Build Organizations

“…Dissanayaka and Kumaraswamy [3] reported that multiple linear regression and artificial neural networks were applied in developing such quantitative models for determining time and cost performance; and that neural networks had superior prediction capabilities when compared with linear regession. A model using artificial neural network was developed by Bhokha and Ogunlana [4] to forecast theconsuuctionduration ofbuildingsat thepredesign stage. However, it is reported that artificial neural network is not appropriate technique for a small sample size where there were a large number of input variables involved [3].…”

“…Therefore, the current paradigm should be reviewed again instead of addressing same aspect of the solution by applying various computational models. With increased competition in the construction industqr, the essence of forecasting, therefore, emphasises not only its accuracybut also attempts to minimize the associated effort [4]. Arguably, this is a trade-off that needs to be solved by considering the accuracy of estimation, against the complexity and the number of operations in both gathering the data required and estimating the duration.…”