ITcon Vol. 16, pg. 713-726, http://www.itcon.org/2011/42

Construction labor production rates modeling using artificial neural network

published:June 2011
editor(s):Turk Ž.
authors:Sana Muqeem, Ph.D student
Civil Engineering Dept, Universiti Teknologi PETRONAS, Malaysia
sanamuqeem@yahoo.com

Arazi Idrus, Associate Professor
Civil Engineering Dept, Universiti Teknologi PETRONAS, Malaysia
arazi_idrus@petronas.com.my

M. Faris Khamidi, Lecturer
Civil Engineering Department, Universiti Teknologi PETRONAS, Malaysia
mfaris_khamidi@petronas.com.my

Jale Bin Ahmad, Lecturer
Computer Information Science Dept, Universiti Teknologi PETRONAS, Malaysia
jale_ahmad@petronas.com.my

Saiful Bin Zakaria, M.Sc. Student
Civil Engineering Dept, Universiti Teknologi PETRONAS, Malaysia
saifulsshi_sa@yahoo.com.my
summary:Construction productivity is constantly declining over a decade due to the lack of standardproductivity database system and the ignorance of impact of various factors influencing labor productivity.Prediction models developed earlier usually neglect the influencing factors which are subjective in nature suchas weather, site conditions etc. Many modeling techniques have been developed for predicting production ratesfor labor that incorporate the influence of various factors but artificial neural network (ANN) has been found tohave strong pattern recognition and learning capabilities to get reliable results. Therefore the objective of thisresearch is to develop a neural network prediction model for predicting labor production rates that takes intoaccount the factors which are in qualitative form. The objectives of the research have been achieved bycollecting production rates data for formwork of beams from different high rise concrete building structures bydirect observation. Reliable values of production rates have been successfully predicted by ANN. The averagevalue of 1.45xE-04 has been obtained for Mean Square Error (MSE) after testing the network . These resultsindicate that the ANN has predicted production rates values for beam formwork successfully with least range oferrors.
keywords:Production rates, influencing factors, work sampling, artificial neural network (ANN).
full text: (PDF file, 0.604 MB)
citation:Muqeem S, Idrus A, Khamidi M F, Ahmad J B, Zakaria S B (2011). Construction labor production rates modeling using artificial neural network, ITcon Vol. 16, pg. 713-726, http://www.itcon.org/2011/42