NEURAL NETWORK APPLICATION FOR BUILDING PROJECTS COST ESTIMATION
Main Article Content
Abstract
This work presents a neural network based cost estimating method, developed for the generation
of conceptual cost estimates for total building and electromechanical systems in building project,
by using eight parameters available at the early design phase. This model establishes a
methodology that can provide an economical and rapid means of cost estimating. Eighteen ligh
rise building projects, built between 1996 and 2009 in Middle East countries used in this study.
The performance of developed cost models was tested against costs incurred by projects not used
in training of those models. Results show the mean absolute percentage errors (MAPE) are
between 1.51% and 4.771 % for the five networks, and the maximum/minimum deviation of the
cost estimation is 10.2/0.17. These figures considered good cost estimation at the early design
stage.
Article Details
How to Cite
Publication Dates
References
Amr S. Ayed "Parametric Cost Estimating of Highway Projects using Neural Networks". M.Sc. Thesis, Newfoundland, Canada.
CII. "Improving Early Estimates". Construction industry Institute. University of Texas at Austin. Austin, TX, USA. 1998
D.K. Evans 1, Dr J.D. Lanham1, Dr R. Marsh "Cost estimation method selection: matching user requirement and knowledge availability to methods". University of West of England, Bristol. UK. 2007
ENR Engineering News-Record."2006 global construction sourcebook." 2006.
FIDIC (international federation of consultant engineer). www.fidic.org/2007
Flood, L., and Kartam N. "Neural networks in civil engineering 1: Principles and Understanding, and II: Systems and application." Journal of Computing in Civil Engineering. ASCE. 8(Z). 131-162. 1994
Kellogg & Kimsey, Inc website. www.kelloggkimsey.com/.2008.
Lowe, D. J. Experiential learning in design cost estimati rig. Ph.D. thesis, UMIST. 1996