%0 Conference Paper
%A Muqeem, S.
%A Khamidi, M.F.
%A Idrus, A.
%A Zakaria, S.B.
%D 2011
%F scholars:1753
%K Artificial Neural Network; Common factors; Data collection; Estimation models; Historical records; Influencing factor; Labor productivity; Malaysia; Production rates; Project site; Site conditions; Work sampling, Construction industry; Mean square error; Neural networks; Productivity; Sampling; Sustainable development, Innovation
%R 10.1109/NatPC.2011.6136353
%T Development of construction labor productivity estimation model using artificial neural network
%U https://khub.utp.edu.my/scholars/1753/
%X Various models have been developed for the estimation of labor productivity but they do not provide reliable and accurate results, because of lack of valid and reliable information on production rates. Currently, production rates data is taken from the historical record, personal opinions and judgement. Also various factors influencing the labor productivity at sites are usually not analysed and formulated properly. Therefore, the objective of this study is to develop an estimation model for construction labor productivity that provides reliable production rates that also takes into account the influencing of the factors by using Artificial Neural Network (ANN). Labor production rates data for concreting of beam has been measured on project sites from different parts of Malaysia. From the literature, the most common factors influencing the labor productivity identified are weather, availability of material and equipment, location of project, site conditions and number of worker, these factors are recorded on the severity scale of 1 to 3 at the sites simultaneously during the data collection of production rates. Severity indexes (S.I) of the recorded influencing factors have been calculated, availability of material and equipment has been ranked as first whereas number of workers, site conditions, weather and location of project are ranked as second, third, fourth and fifth. Finally, the data has been used in ANN to develop an estimation model. Mean Square Error (MSE) calculated from the estimated rates and the results shows that the model has estimated the rates reliably with acceptable range of error and can be used in construction industry. © 2011 IEEE.
%Z cited By 2; Conference of 3rd National Postgraduate Conference - Energy and Sustainability: Exploring the Innovative Minds, NPC 2011 ; Conference Date: 19 September 2011 Through 20 September 2011; Conference Code:88531