Browse > Article

Comparisons of Experimental Designs and Modeling Approaches for Constructing War-game Meta-models  

Yoo, Kwon-Tae (한국과학기술원 산업공학과)
Yum, Bong-Jin (한국과학기술원 산업공학과)
Publication Information
Journal of the military operations research society of Korea / v.33, no.1, 2007 , pp. 59-74 More about this Journal
Abstract
Computer simulation models are in general quite complex and time-consuming to run, and therefore, a simpler meta-model is usually constructed for further analysis. In this paper, JANUS, a war-game simulator, is used to describe a certain tank combat situation. Then, second-order response surface and artificial neural network meta-models are developed using the data from eight different experimental designs. Relative performances of the developed meta-models are compared in terms of the mean squared error of prediction. Computational results indicate that, for the given problem, the second-order response surface meta-model generally performs better than the neural network, and the orthogonal array-based Latin hypercube design(LHD) or LHD using maximin distance criterion may be recommended.
Keywords
meta-model; Full Factorial Design; Central Composite Design; Latin Hypercube Design; Response Surface Methodology; Artificial Neural Network;
Citations & Related Records
연도 인용수 순위
  • Reference
1 김윤태, 고 원, 박혜련, '분석용 정밀 워게임 모형의 통계적 진단 및 활용', 2004 한국통계학회 추계 학술대회 논문집, 117-121, 2004
2 McKay, M. D., Beckman, R. J., and Conover, W. J., 'A Comparison of three methods for selecting values of input variables in the analysis of output from a computer code', Technometrics, 21(2), 239-245, 1979   DOI
3 Tang, B., 'Selecting Latin hypercubes using correlation criteria', Statistica Sinica, 8, 965-977, 1998
4 Allen, T. T., Kabiri-Bemshteyn, K., and Bamoradian, K. K, 'Constructing metamodels for computer experiments', Journal of Quality Technology, 35(3), 264-274, 2003   DOI
5 문형곤, 윤직석, 유승근, 01 육군 전투실험기술 지원 연구보고서, 한국국방연구원, 2001
6 Montgomery, D. C., Design and Analysis of Experiments, 6th. ed., Chapter 11, John Wiley & Sons Inc., New York, 2005
7 Joseph, V. R., Hung, Y., 'Orthogonalmaximin Latin hypercube designs', Statistica Sinica, to appear, 2006
8 Stein, M., 'Large sample properties of simulation using Latin hypercube sampling', Technometrics, 29, 143-151, 1987   DOI
9 Alam, F. M., McNaught, K. R., and Ringrose, T. J., 'A comparison of experimental designs in the development of a neural network simulation metamodel', Simulation Modelling Practice and Theory, 12, 559-578, 2004   DOI   ScienceOn
10 Davis, P. K., Bigelow, J. H., Motivated Metamodels, RAND, Santa Monica, CA, 2004
11 MATLAB v.7.0.1 Manual, Backpropagation in Neural Network Toolbox, 2004
12 Simpson, T. W, Peplinski, J. D, Koch, P. N. and Allen, J. K., 'Metamodels for computer-based engineering design: Survey and recommendations', Engineering with Computers, 17, 129-150, 2001   DOI   ScienceOn
13 SAS/STAT 9.1 User's Guide, 2004
14 Owen, A. B., 'Controlling correlations in Latin hypercube samples', Journal of the American Statistical Association, 89(428), 1515-1522, 1994
15 Barton, R. R., 'Metamodels for simulation input-output relations', Proceedings of the 1992 Winter Simulation Conference, 289-299, 1992
16 Box, G. E. P., Wilson, K. B., 'On the experimental attainment of optimum conditions', Journal of the Royal Statistic Society Ser. B(Methodological), 13(1), 1-45, 1951
17 Sacks, J., Welch, W. J., Mitchell, T. J. and Wynn, H. P., 'Design and analysis of computer experiments', Statistical Science, 4(4), 409-435, 1989   DOI   ScienceOn
18 Tang, B., 'Orthogonal array-based Latin hypercubes', Journal of the American Statistical Association, 88(424), 13921397, 1993
19 Lunani, M., Sudjianto, A., and Johnson, P. L., 'Generating efficient training samples for neural networks using Latin hypercube sampling', Intelligent Engineering Systems Through Artificial Neural Networks, 5, 209-214, 1995
20 Shewry, M. and Wynn, H., 'Maximum entropy sampling', Journal of Applied Statistics, 14, 409-435, 1987
21 Phadke, M. S., Quality Engineering Using Robust Design, p.293, PTR Prentice-Hall, Inc., Englewood Cliffs, New Jersey, 1989
22 Ye, K. Q., 'Orthogonal column latin hypercubes and their application in computer experiments', Journal of the American Statistical Association, 93(444), 1430-1439, 1998   DOI
23 Morris, M. D., Mitchell, T. J., 'Exploratory designs for computational experiments', Journal of Statistical Planning and Inference, 43, 381-402, 1995   DOI   ScienceOn