relation: https://khub.utp.edu.my/scholars/10792/
title: An Artificial neural networks (ANN) model for evaluating construction project performance based on coordination factors
creator: Alaloul, W.S.
creator: Liew, M.S.
creator: Wan Zawawi, N.A.
creator: Mohammed, B.S.
creator: Adamu, M.
description: Construction projects are delivered in a multidisciplinary environment, which need continues coordination. The aim of this paper is to develop an ANN model to evaluate the influence of coordination factors on construction projects performance. For this purpose, the most effective 16 coordination factors impacting the construction projects performance have been identified. After that, through a questionnaire survey, the extent of coordination factors application and the corresponding project�s performance were collected. Three multilayer feed-forward networks with Back-Propagation and Elman-Propagation algorithms were adopted to train, validate, and test the cost, time and quality, as performance evaluation indicators. Consequently, the training process continues unit it reaches the pre-defined error or up to 1000 epochs. The results of Mean Square Error (MSE) confirmed the accuracy of the networks with an average value of 0.0231. Furthermore, the determination coefficient (R2) for the three networks of cost, time, and quality were obtained to be 0.77, 0.76 and 0.75, respectively. © 2018, © 2018 The Author(s). This open access article is distributed under a Creative Commons Attribution (CC-BY) 4.0 license.
publisher: Cogent OA
date: 2018
type: Article
type: PeerReviewed
identifier:   Alaloul, W.S. and Liew, M.S. and Wan Zawawi, N.A. and Mohammed, B.S. and Adamu, M.  (2018) An Artificial neural networks (ANN) model for evaluating construction project performance based on coordination factors.  Cogent Engineering, 5 (1).  pp. 1-18.  ISSN 23311916     
relation: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85052794565&doi=10.1080%2f23311916.2018.1507657&partnerID=40&md5=30781980ab2b347366f2444209e71a80
relation: 10.1080/23311916.2018.1507657
identifier: 10.1080/23311916.2018.1507657