Abstracts – Browse Results
Click on the titles below to expand the information about each abstract.
Viewing 11 results ...
Abraham, D M and Yeh, M H J (1999) Breakwater construction: an effective method for industrial waste utilization. Engineering, Construction and Architectural Management, 6(02), 145–54.
Al-Tabtabai, H and Alex, A P (1999) Using genetic algorithms to solve optimization problems in construction. Engineering, Construction and Architectural Management, 6(02), 121–32.
Alshawi, M and Hassan, Z (1999) Integrated models for construction planning: object flow and relationship. Engineering, Construction and Architectural Management, 6(02), 197–212.
Bhokha, S and Ogunlana, S O (1999) Application of artificial neural network to forecast construction duration of buildings at the pre-design stage. Engineering, Construction and Architectural Management, 6(02), 133–44.
- Type: Journal Article
- Keywords: artificial neural network (ANN); back-propagation; duration estimation; Generalized Delta Rule (GDR); predesign stage; supervised training and testing
- ISBN/ISSN: 0969-9988
- URL: http://www.ingentaconnect.com/content/bsc/ecam/1999/00000006/00000002/art00087
- Abstract:
The application of an artificial neural network (ANN) to forecast the construction duration of buildings at the predesign stage is described in this paper. A three-layered back-propagation (BP) network consisting of 11 input nodes has been constructed. Ten binary input nodes represent basic information on building features (i.e. building function, structural system, foundation, height, exterior finishing, quality of interior decorating, and accessibility to the site), and one real-value input represents functional area. The input nodes are fully connected to one output node through hidden nodes. The network was implemented on a Pentium-150 based microcomputer using a neurocomputer program written in C++. The Generalized Delta Rule (GDR) was used as learning algorithm. One hundred and thirty-six buildings built during the period 1987-95 in the Greater Bangkok area were used for training and testing the network. The determination of the optimum number of hidden nodes, learning rate, and momentum were based on trial-and-error. The best network was found to consist of six hidden nodes, with a learning rate of 0.6, and null momentum. It was trained for 44 700 epochs within 943 s such that the mean squared error (judgement) of training and test samples were reduced to 1.17×10 -7 and 3.10×10?6, respectively. The network can forecast construction duration at the predesign stage with an average error of 13.6%.
Bowen, P A, Pearl, R G and Edwards, P J (1999) Client briefing processes and procurement method selection: a South African study. Engineering, Construction and Architectural Management, 6(02), 91–104.
Emmitt, S (1999) Architectural management: an evolving field. Engineering, Construction and Architectural Management, 6(02), 188–96.
Liu, A M-M (1999) A research model of project complexity and goal commitment effects on project outcome. Engineering, Construction and Architectural Management, 6(02), 105–11.
Ndekugri, I and McDonnell, B (1999) Differing site conditions risks: a FIDIC/engineering and construction contract comparison. Engineering, Construction and Architectural Management, 6(02), 177–87.
Ng, S T, Skitmore, M R and Smith, N J (1999) Decision-makers' perceptions in the formulation of pre-qualification criteria. Engineering, Construction and Architectural Management, 6(02), 155–65.
Walker, A and Wing, C K (1999) The relationship between construction project management theory and transaction cost economics. Engineering, Construction and Architectural Management, 6(02), 166–76.
Wantanakorn, D, Mawdesley, M J and Askew, W H (1999) Management errors in construction. Engineering, Construction and Architectural Management, 6(02), 112–20.