Enhancing Project Evaluation and Review Technique Simulation through Artificial Neural Network-based Input Modeling
Publication: Journal of Construction Engineering and Management
Volume 128, Issue 5
Abstract
Although a stochastic simulation study can eliminate the merge event bias in the project evaluation and review technique (PERT), the errors due to calculating the statistical descriptors of beta distributions with the three-point time estimates of PERT may still make the simulation results suspect. In order to enhance PERT simulation in terms of input modeling, this paper presents an artificial neural network (ANN)-based approach to estimate the true properties of the beta distributions from statistical sampling of actual data combined with subjective information. The minimum and maximum values along with the lower and upper quartiles are four time estimates used to uniquely define a beta distribution. The effects of shape parameters of beta distributions are closely examined, and the working range of shape parameters is defined. To construct an ANN model, data are prepared using random sampling techniques and Excel functions. Through exploring the training data provided, the ANN model has found the patterns between the inputs and the outputs, namely, the interactions and nonlinear relationships among the lower and upper quartiles and the shape parameters of the beta distributions. The ANN model was tested, validated, and compared with other packages for fitting beta distributions such as BetaFit, VIBES, and BestFit. The developed ANN-based input modeling method attempts to embed artificial intelligence into simulation and finds a new way to fit statistical distributions for activity duration in construction simulation, as demonstrated in a sample application.
Get full access to this article
View all available purchase options and get full access to this article.
References
AbouRizk, S. M. (1990). “Input modeling for construction simulation.” PhD thesis, Purdue Univ., West Lafayette, Ind.
AbouRizk, S. M., Halpin, D. W., and Wilson, J. R.(1991). “Visual interactive fitting of beta distributions.” J. Constr. Eng. Manage., 117(4), 589–605.
AbouRizk, S. M., Halpin, D. W., and Wilson, J. R.(1994). “Fitting beta distributions based on sample data.” J. Constr. Eng. Manage., 120(2), 288–305.
Ahuja, H., Dozzi, S. P., and AbouRizk, S. M. (1994). Project management techniques in planning and controlling construction projects, 2nd Ed., Wiley, New York.
Back, W. E., Boles, W. W., and Fry, G. T.(2000). “Defining triangular probability distributions from historical cost data.” J. Constr. Eng. Manage., 126(1), 29–37.
Benjamin, J. R., and Cornell, C. A. (1970). Probability, statistics, and decision for civil engineers, McGraw-Hill, New York.
Decision making tools: @Risk, BestFit. (1997). Palisade Corp., New York.
Cottrell, W. D.(1999). “Simplified program evaluation and review technique (PERT).” J. Constr. Eng. Manage., 125(1), 16–22.
Fente, J., Schexnayder, C., and Knutson, K.(2000). “Defining a probability distribution function for construction simulation.” J. Constr. Eng. Manage., 126(3), 234–241.
Kohonen, T. (1995). Self-organizing maps, Springer, London.
Lichtenstein, S., Fischhoff, B., and Phillips, L. D. (1977). “Calibration of probabilities: The state of the art to 1980.” Judgment under uncertainty: Heuristics and biases, Cambridge University Press, U.K., 306–334.
Lu, M. (2001). “Productivity studies using advanced ANN models.” PhD thesis, Univ. of Alberta, Edmonton, Alberta, Canada.
Lu, M., and AbouRizk, S. M.(2000). “Simplified CPM/PERT simulation model.” J. Constr. Eng. Manage., 126(3), 219–226.
Maio, C., Schexnayder, C., Knutson, K., and Weber, S.(2000). “Probability distribution function for construction simulation.” J. Constr. Eng. Manage., 126(4), 285–292.
Orvis, W. J. (1996), Excel for scientists and engineers, 2nd Ed., Sybex, San Francisco.
Widman, L. E., and Loparo, K. A. (1989). “Artificial intelligence, simulation, and modeling: A critical survey.” Artificial intelligence, simulation, and modeling, L. E. Widman, K. A. Loparo, and N. R. Nielsen, eds., Wiley, New York, 1–45.
Information & Authors
Information
Published In
Copyright
Copyright © 2002 American Society of Civil Engineers.
History
Received: Jan 23, 2001
Accepted: Jul 18, 2001
Published online: Sep 13, 2002
Published in print: Oct 2002
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.