Abstracts – Browse Results

Search or browse again.

Click on the titles below to expand the information about each abstract.
Viewing 7 results ...

Elhag, T M S and Boussabaine, A H (2001) Tender price estimation using artificial neural networks. Journal of Financial Management of Property and Construction, 6(03), 193–208.

Fortune, C (2001) Exploring the model selection process in the formulation of building project advice. Journal of Financial Management of Property and Construction, 6(03), 167–77.

Kaka, A P (2001) Turnover forecasting for contracting companies based on published information. Journal of Financial Management of Property and Construction, 6(03), 217–29.

Kenley, R (2001) In-project end-date forecasting: an idiographic, deterministic approach, using cash-flow modelling. Journal of Financial Management of Property and Construction, 6(03), 209–16.

Lo, H P and Lam, M-L (2001) A bidding strategy using multivariate distribution. Journal of Financial Management of Property and Construction, 6(03), 155–65.

Ogunlana, S O, Bhokha, S and Pinnemitr, N (2001) Application of artifical neural network (ANN) to forecast construction cost of buildings at the pre-design stage. Journal of Financial Management of Property and Construction, 6(03), 179–92.

  • Type: Journal Article
  • Keywords: artificial neural network (ANN); back-propagation; cost estimating; Generalised Data Rule (GDR); pre-design stage; supervised training and testing
  • ISBN/ISSN: 1366-4387
  • URL: http://www.emeraldinsight.com/journals.htm?issn=1366-4387
  • Abstract:
    The application of artifical neural network (ANN) to forecast the construction cost of buildings at the pre-design stage is described in the paper. A three-layered back-propagation (BP) network consisting of 12 input nodes has been developed. Ten binary input nodes represent basic building features and two real-value inputs represent price indices of major construction materials. The input nodes are fully connectred to three output nodes through hidden nodes. The network was implemented on a Pentium-150 based microcomputer using a neuro-computer program written in the C++ language. Generalised Data Rule (GDR) was used as the learning algorithm. One hundred and thiry-six buildings built during the period 1987-1995 in the Greater Banhkok area were used to train and test the network; the sample being split into two equal parts for training and testing. 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 learning rate of 0.6, and null momentum. It was trained for 25,970 epochs within 668 seconds such that the mean squared error (MSE) of the training and test samples were reduced to 9.13 x 10(power -6), and 4.35 x 10(power -5), respectively. The network can forecast construction cost at the pre-design stage with an average error of 4.4%.

Skitmore, M (2001) Raftery curves for tender price forecasting: Empirical probabilities and pooling. Journal of Financial Management of Property and Construction, 6(03), 141–54.