Abstracts – Browse Results

Search or browse again.

Click on the titles below to expand the information about each abstract.
Viewing 8 results ...

Cheung, S O and Li, K (2019) Biases in construction project dispute resolution. Engineering, Construction and Architectural Management, 26(02), 321–48.

Edirisinghe, R (2019) Digital skin of the construction site. Engineering, Construction and Architectural Management, 26(02), 184–223.

Hong, Y, Hammad, A W, Sepasgozar, S and Akbarnezhad, A (2019) BIM adoption model for small and medium construction organisations in Australia. Engineering, Construction and Architectural Management, 26(02), 154–83.

Parn, E A and Edwards, D (2019) Cyber threats confronting the digital built environment. Engineering, Construction and Architectural Management, 26(02), 245–66.

Plantinga, H, Voordijk, H and Doree, A (2019) The reasoning behind infrastructure manager’s choice of procurement instruments. Engineering, Construction and Architectural Management, 26(02), 303–20.

Sutrisna, M and Goulding, J (2019) Managing information flow and design processes to reduce design risks in offsite construction projects. Engineering, Construction and Architectural Management, 26(02), 267–84.

Ungureanu, L C, Hartmann, T and Serbanoiu, I (2019) Quantitative lean assessment of line of balance schedules’ quality. Engineering, Construction and Architectural Management, 26(02), 224–44.

Utama, W P, Chan, A P, Zahoor, H, Gao, R and Jumas, D Y (2019) Making decision toward overseas construction projects. Engineering, Construction and Architectural Management, 26(02), 285–302.

  • Type: Journal Article
  • Keywords: International construction; Simulation;
  • ISBN/ISSN: 0969-9988
  • URL: https://doi.org/10.1108/ECAM-01-2018-0016
  • Abstract:
    The purpose of this paper is to introduce a decision support aid for deciding an overseas construction project (OCP) using an adaptive neuro fuzzy inference system (ANFIS). Design/methodology/approach This study presents an ANFIS approach as a decision support aid for assessment of OCPs. The processing data were derived from 110 simulation cases of OCPs. In total, 21 international factors observed from a Delphi survey were determined as assessment variables to examine the cases. The experts were involved to evaluate and judge whether the company should Go or Not Go for an OCP, based on the different parameter scenarios given. To measure the performance of the ANFIS model, root mean square error (RMSE) and coefficient of correlation (R) were employed. Findings The result shows that optimum ANFIS model indicating RMSE and R scores adequately near between 0 and 1, respectively, was obtained from parameter set of network algorithm with two input membership functions, Gaussian type of membership function and hybrid optimization method. When the model tested to nine real OCPs data, the result indicates 88.89 percent accurate. Research limitations/implications The use of simulation cases as data set in development the model has several advantages. This technique can be replicated to generate other case scenarios which are not available publicly or limited in terms of quantity. Originality/value This study evidences that the developed ANFIS model can predict the decision satisfactorily. Therefore, it can help companies’ management to make preliminary assessment of an OCP.