Özet:
Estimation at completion (EAC) is a manager's projection of a project's total cost at
its completion. It is an important tool for monitoring a project's performance and
risk. Executives usually make high-level decisions on a project, but they may have
gaps in the technical knowledge which may cause errors in their decisions. In this
current study, the authors implemented new coupled intelligence models, namely
global harmony search (GHS) and brute force (BF) integrated with extreme learning
machine (ELM) for modeling the project construction estimation at completion. GHS
and BF were used to abstract the substantial influential attributes toward the EAC
dependent variable, whereas the effectiveness of ELM as a novel predictive model
for the investigated application was demonstrated. As a benchmark model, a
classical artificial neural network (ANN) was developed to validate the new ELM
model in terms of the prediction accuracy. The predictive models were applied using
historical information related to construction projects gathered from the United
Arab Emirates (UAE). The study investigated the application of the proposed
coupled model in determining the EAC and calculated the tendency of a change in
the forecast model monitor. The main goal of the investigated model was to produce
a reliable trend of EAC estimates which can aid project managers in improving the
effectiveness of project costs control. The results demonstrated a noticeable
implementation of the GHS-ELM and BF-ELM over the classical and hybridized ANN
models.
