Advertisement

Metamodelle

  • Karl Siebertz
  • David van Bebber
  • Thomas Hochkirchen
Chapter
Part of the VDI-Buch book series (VDI-BUCH)

Zusammenfassung

Die direkte Analyse und Optimierung komplexer Systeme ist schwierig und zeitaufwendig, so dass diese immer häufiger mit der Unterstützung von Metamodellen durchgeführt wird. Metamodelle bilden das zu untersuchende System auf Basis von Mess- oder Simulationsdaten mathematisch ab und können Systemantworten im Bereich von Millisekunden oder Sekunden vorhersagen. Der Einsatz von linearen Modellen oder Polynomen mit starrer Vorgabe der maximal abzubildenden Komplexität oder der Grundform von Zusammenhängen ist nicht zielführend. Gerade bei unbekannter und gleichzeitig hoher Komplexität des abzubildenden Systems führt dies zu falschen Folgerungen. Daher sind verschiedenste Modellverfahren entwickelt worden, die ohne feste Vorgabe von Systemzusammenhängen komplexe Systeme auf Basis von raumfüllenden Mess- oder Simulationsdaten abbilden. Dieses Kapitel stellt Grundlagen und Algorithmen verschiedener Verfahren sowie Methoden zur Qualitätskontrolle vor. Dabei startet es bei alt bekannten Verfahren, wie Regression oder Splines und entwickelt sich über verbreitete Verfahren, wie Kriging, Radiale Basisfunktionen oder Künstliche Neuronale Netze hin zu Support Vector Regression oder Gauß Prozess Modellen. Die Aufbereitung der Algorithmen ermöglicht eine gezielte Auswahl und den sicheren Einsatz der Verfahren in kommerziellen Softwarepaketen oder eine erste grundlegende Implementierung.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literaturverzeichnis

  1. 1. Akaike, H.: A new look at the statistical identification model. IEEE Transactions on Automatic Control 19, pp. 716–723 (1974) 236Google Scholar
  2. 2. An, J., Owen, A.: Quasi-regression. J. Complexity 17, pp. 588–607 (2001) 234Google Scholar
  3. 3. Bailey, T., Gatrell, A.: Interactive spatial data analysis. Longman Scientific & Technical (1995) 283Google Scholar
  4. 4. Barnes, R.J.: The variogram sill and the sample variance. Mathematical Geology 23(4), pp. 673–678 (1991) 277Google Scholar
  5. 5. Bartels, R.H., Beatty, J.C., Barsky, B.A.: An Introduction to Splines for Use in Computer Graphics and Geometric Modeling. Morgan Kaufmann (1987) 254Google Scholar
  6. 6. Bowman, A.W., Azzalini, A.: Applied smoothing techniques for data analysis: the Kernel approach with S-plus illustrations. Oxford Statistical Science Series. Clarendon Press, Oxford (2004) 247Google Scholar
  7. 7. Bozdogan, H.: Model Selection and Akaikes Information Criterion (AIC): The General Theory and its Analytical Extensions. Psychometrika 52, pp. 346–370 (1987) 236Google Scholar
  8. 8. Breiman, L.: Heuristics of instability and stabilization in model selection. The Annals of Statistics 24(6), pp. 2350–2383 (1996) 313Google Scholar
  9. 9. Breiman, L., Friedman, J., Stone, C.J., Olshen, R.A.: Classification and Regression Trees. Chapman and Hall/CRC (1984) 248, 249, 252Google Scholar
  10. 10. Brent, R.P.: Algorithms for Minimisation Without Derivatives. Prentice Hall (1973) 307Google Scholar
  11. 11. Carr, J.C., Beatson, R.K., Cherrie, J., Mitchell, T.J., Fright, W.R., McCallum, B.C., Evans, T.R.: Reconstruction and representation of 3D objects with radial basis functions. In: Proceedings of the 28th annual conference on Computer graphics and interactive techniques, pp. 67–76. ACM, New York (2001) 290Google Scholar
  12. 12. CDIAC: Atmospheric Concentrations of CO2 from Mauna Loa, Hawaii (2016). URL http://cdiac.ornl.gov/trends/co2/recent_mauna_loa_co2.html. (abgerufen 11/2016) 299
  13. 13. Cherkassky, V.S., Mulier, F.: Learning from Data: Concepts, Theory and Methods, 2nd edn. John Wiley & Sons, New York, USA (2007) 313Google Scholar
  14. 14. Cleveland, W.: Robust locally weighted regression and smoothing scatter plots. J. Amer. Stat. Assoc. 74, pp. 829–836 (1979) 245Google Scholar
  15. 15. Cressie, N.: Statistics for Spatial Data. Wiley, New York (1993) 277Google Scholar
  16. 16. Cristianini, N., Shawe-Taylor, J.: An introduction to Support Vector Machines and other kernel–based learning machines. Cambridge University Press, Cambridge (2000) 260, 262, 265, 266, 270, 271Google Scholar
  17. 17. David, M., Blais, R.A.: Geostatistical Ore Reserve Estimation. Developments in geomathematics. Elsevier Scientific Pub. Co. (1977) 277Google Scholar
  18. 18. Draper, N.R., Smith, H.: Applied Regression Analysis, 3rd edn. Wiley (1998) 238Google Scholar
  19. 19. Drucker, H., Burges, C., Kaufman, L., Smola, A., Vapnik, V.: Support Vector Regression Machines. Advances in Neural Information Processing Systems 9, p. 155–161 (1997) 258Google Scholar
  20. 20. Dumouchel, W., O’Brien, F.: Computing and graphics in statistics. In: A. Buja, P.A. Tukey (eds.) Computing and graphics in statistics, chap. Integrating a robust option into a multiple regression computing environment, pp. 41–48. Springer-Verlag New York (1991) 239Google Scholar
  21. 21. Duong, T., Hazelton, M.: Plug-in Bandwidth Selectors for Bivariate Kernel Density Estimation. Journal of Nonparametric Statistics 15, pp. 17–30 (2003) 247Google Scholar
  22. 22. Efron, B., Hastie, T., Johnstone, L., Tibshirani, R.: Least Angle Regression. Annals of Statistics 32, pp. 407–499 (2002). URL http://www-stat.stanford.edu/~tibs/ftp/LeastAngle_2002.pdf. (abgerufen 11/2016) 238
  23. 23. Efroymson, M.: Mathematical Methods for Digital Computers, chap. Multiple regression analysis. John Wiley & Sons Inc (1960) 236Google Scholar
  24. 24. Eilers, P.H.C., Rijnmond, D.M., Marx, B.D.: Flexible smoothing with B-splines and penalties. Statistical Science 11, pp. 89–121 (1996) 254Google Scholar
  25. 25. Fang, K.T., Li, R., Sudjianto, A.: Design and Modeling for Computer Experiments (Computer Science & Data Analysis). Chapman & Hall/CRC (2005) 192, 193, 194, 195, 197, 209, 210, 212, 213, 214, 219, 238, 254, 255, 417, 418, 419Google Scholar
  26. 26. Fletcher, R.: Practical Methods of Optimization, 2nd edn. Wiley (2000) 272Google Scholar
  27. 27. Fletcher, T.: Support Vector Machines Explained (2009). URL http://www.tristanfletcher.co.uk. (abgerufen 11/2016) 259, 260, 261, 262, 263, 264, 265, 266, 267, 269
  28. 28. Frank, I.E., Friedman, J.H.: A statistical view of some chemometrics regression tools. Technometrics 35, pp. 109–148 (1993) 238Google Scholar
  29. 29. Friedman, J.: Multivariate Adaptive Regression Splines (with discussion). Annals of Statistics 19, pp. 1–141 (1991) 256, 257, 258Google Scholar
  30. 30. Friedman, J.: Fast MARS. Tech. Rep. 110, Stanford University Department of Statistics (1993) 256, 257, 258Google Scholar
  31. 31. Graham, J.: Ordinary Kriging (2015). URL http://www.math.umt.edu/graham. (abgerufen 11/2016) 283
  32. 32. Graham, J.: Trend, Variation and Universal Kriging (2015). URL http://www.math.umt.edu/graham. (abgerufen 11/2016) 283
  33. 33. Gunn, S.R.: Support Vector Machines for Classification and Regression. Tech. rep., University of Southampton (1998). URL http://users.ecs.soton.ac.uk/srg/publications/pdf/SVM.pdf. (abgerufen 11/2016) 268, 400
  34. 34. Guyon, I.: An introduction to variable and feature selection. Journal of Machine Learning Research 3, pp. 1157–1182 (2003) 313Google Scholar
  35. 35. Härdle, W.: Applied Nonparametric Regression. Cambridge University Press (1990) 244Google Scholar
  36. 36. Hastie, T., Loader, C.: Local regression: automatic kernel carpentry (with discussion). Statistical Science 8, pp. 120–143 (1993) 245Google Scholar
  37. 37. Hastie, T., Tibshirani, R.: Generalized Additive Models. Chapman and Hall, London (1990) 235Google Scholar
  38. 38. Hengl, T.: Universal Kriging - Algorithm (2013). URL http://spatial-analyst.net/ILWIS/htm/ilwisapp/universal_kriging_algorithm.htm. (abgerufen 11/2016) 283
  39. 39. Hesterberg, T., Choi, N.H., Meier, L., Fraley, C.: Least angle and L1 penalized regression: A review. Statistics Surveys 2, pp. 61–93 (2008) 238Google Scholar
  40. 40. Hoerl, A.E., Kennard, R.W.: Ridge regression: Biased estimation for nonorthogonal problems. Technometrics 12, pp. 55–67 (1970) 238Google Scholar
  41. 41. Holland, P.W.,Welsch, R.E.: Robust Regression Using Iteratively Reweighted Least-Squares. Communications in Statistics: Theory and Methods A6, pp. 813–827 (1977) 239Google Scholar
  42. 42. Host, G.: Kriging by local polynomials. Computational Statistics and Data Analysis 29(3), pp. 295–312 (1999). URL http://ideas.repec.org/a/eee/csdana/v29y1999i3p295-312.html. (abgerufen 11/2016) 247
  43. 43. Huber, P., Ronchetti, E.M.: Robust Statistics. Wiley (2009) 239, 383Google Scholar
  44. 44. Huth, F.: Simulation eines Hochdruck-Benzineinspritzsystems. Master’s thesis, RWTH Aachen (2011) 191, 193, 287Google Scholar
  45. 45. Ishiguro, M., Sakamoto, Y., Kitagawa, G.: Bootstrapping log likelihood and EIC, an extension of AIC. Annals of the Institute of Statistical Mathematics 49, pp. 411–434 (1997) 236Google Scholar
  46. 46. Jekabsons, G.: Ensembling adaptively constructed polynomial regression models. International Journal of Intelligent Systems and Technologies (IJIST) 3(2), pp. 56–61 (2008) 242, 313Google Scholar
  47. 47. Jekabsons, G.: Machine Learning, chap. Adaptive Basis Function Construction: an approach for adaptive building of sparse polynomial regression models, pp. 127–156. InTech (2010) 235, 242, 313Google Scholar
  48. 48. JiSheng Hao, L.M., Wang, W.: IFIP International Federation for Information Processing, vol. 288, chap. An New Algorithm for Modeling Regression Curve, pp. 86–91. Springer (2009) 269Google Scholar
  49. 49. Jones, M., Marron, J., Sheather, S.: A Brief Survey of Bandwidth Selection for Density Estimation. Journal of the American Statistical Association 91, pp. 401–407 (1996) 247Google Scholar
  50. 50. Journel, A.G., Huijbregts, C.J.: Mining Geostatistics. Academic Press, London (1978) 277Google Scholar
  51. 51. King, M.L., Zhang, X., Hyndman, R.J.: Bandwidth Selection for Multivariate Kernel Density Estimation Using MCMC. Computational Statistics and Data Analysis 50, pp. 3009–3031 (2004) 247Google Scholar
  52. 52. Kohavi, R., John, G.H.: Wrappers for Feature Subset Selection. Artificial Intelligence 97, pp. 273–324 (1997) 313Google Scholar
  53. 53. Kotsiantis, S.B., Pintelas, P.E.: Combining Bagging and Boosting. International Journal of Mathematical, Computational, Physical, Electrical and Computer Engineering 1(8), pp. 372– 381 (2007) 313Google Scholar
  54. 54. Kürz, C.: Radiale-Basis-Funktionen. Seminararbeit, Fraunhofer-Institut für Algorithmen und Wissenschaftliches Rechnen (2008). (abgerufen 11/2016) 284, 287Google Scholar
  55. 55. Lichtenstern, A.: Kriging methods in spatial statistics. Master’s thesis, Technische Universität München (2013) 283Google Scholar
  56. 56. Loughrey, J., Cunningham, P.: Overfitting in Wrapper-Based Feature Subset Selection: The Harder You Try the Worse it Gets. In: M. Bramer, F. Coenen, T. Allen (eds.) SGAI Conf., pp.33–43. Springer (2004) 313Google Scholar
  57. 57. Mallows, C.: Some Comments on Cp. Technometrics 42, pp. 87–94 (2000) 236Google Scholar
  58. 58. Marron, J.S., Nolan, D.: Canonical kernels for density estimation. Statistics & Probability Letters 7(3), pp. 195–199 (1988). URL http://ideas.repec.org/a/eee/stapro/v7y1988i3p195-199.html. (abgerufen 11/2016) 244
  59. 59. Martinez, W.L., Martinez, A.R.: Computational Statistics Handbook with Matlab. Chapman & Hall/CRC (2002) 248, 249, 252Google Scholar
  60. 60. Masters, T.: Practical Neural Network Recipes in C++. Academic Press (1993) 303, 304, 307, 309Google Scholar
  61. 61. Mathworks: Matlab Dokumentation (2015). URL https://de.mathworks.com/help/matlab/. (abgerufen 03/2017) 236, 239, 240, 241, 384
  62. 62. Menzel, W., Zhang, J., Hendrich, N.: Algorithmisches Lernen - Support Vector Machines. Vorlesungsunterlagen (2009). URL http://tams-www.informatik.uni-hamburg.de/lectures/2009ss/vorlesung/Algorithmisches_Lernen/. (abgerufen 11/2016) 265
  63. 63. Miller, A.: Subset Selection in Regression. CRC Press Inc (2002) 238Google Scholar
  64. 64. Montgomery, D.C.: Design and Analysis of Experiments. John Wiley and Sons, Hoboken, NJ (2001/2009) 90, 129, 234Google Scholar
  65. 65. Nadaraya, E.: On Estimating Regression. Theory Probab. Appl. 9, pp. 141–142 (1964) 243Google Scholar
  66. 66. Nadaraya, E.: On Non-Parametric Estimates of Density Functions and Regression Curves. Theory Probab. Appl. 10, pp. 186–190 (1965) 243Google Scholar
  67. 67. Navratil, G.: Ausgleichsrechnung II. Vorlesungsunterlagen (2006). URL ftp://ftp.geoinfo.tuwien.ac.at/navratil/Ausgleich2.pdf. (abgerufen 11/2016) 276, 277, 283
  68. 68. Neal, R.M.: Bayesian Learning for Neural Networks. Springer-Verlag New York (1996) 300Google Scholar
  69. 69. Opitz, D., Maclin, R.: Popular Ensemble Methods: An Empirical Study. Journal of Artificial Intelligence Research 11, pp. 169–198 (1999) 313Google Scholar
  70. 70. Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipes: The Art of Scientific Computing. Cambridge University Press (2007) 199, 203, 220, 254, 265, 276, 277, 281, 285, 307, 334, 381, 398, 400Google Scholar
  71. 71. Pudil, P., Ferri, F., Novovicova, J., Kittler, J.: Floating search methods for feature selection with nonmonotonic criterion functions. In: Proceedings of International Conference on Pattern Recognition, vol. 2, pp. 279–283 (1994) 236Google Scholar
  72. 72. Rasmussen, C.E.: Solving Challenging Non-linear Regression Problems by Manipulating a Gaussian Distribution. Machine Learning Summer School, Cambridge (2009). URL http://mlg.eng.cam.ac.uk/mlss09/mlss_slides/Rasmussen_1.pdf. (abgerufen 11/2016) 296, 299, 301, 302
  73. 73. Rasmussen, C.E.: GPML: Gaussian Process for Machine Learning (Matlab Toolbox) (2013). URL http://www.gaussianprocess.org/gpml/code/matlab/doc/. (abgerufen 11/2016) 297, 301, 302
  74. 74. Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. The MIT Press (2006). URL http://www.gaussianprocess.org/gpml/. (abgerufen 11/2016) 291, 292, 293, 294, 295, 297, 300, 301, 302
  75. 75. Rathbun, S.: The universal kriging equations (1994). URL http://www.esapubs.org/archive/ecol/E079/001/kriging.htm. (abgerufen 11/2016) 283
  76. 76. Reunanen, J.: Overfitting in Making Comparisons Between Variable Selection Methods. Journal of Machine Learning Research 3, pp. 1371–1382 (2003). URL http://www.jmlr.org/papers/volume3/reunanen03a/reunanen03a.pdf. (abgerufen 11/2016) 313
  77. 77. Reunanen, J.: Feature extraction: foundations and applications, chap. Search strategies, pp. 119–137. Springer (2006) 235, 313Google Scholar
  78. 78. Rissanen, J.: Modelling by Shortest Data Description. Automatica 14, pp. 465–471 (1978) 236Google Scholar
  79. 79. Rodriguez, C.C.: The ABC of Model Selection: AIC, BIC and the New CIC. In: K.H. Knuth, A.E. Abbas, R.D. Morris, J.P. Castle (eds.) Bayesian Inference and Maximum Entropy Methods in Science and Engineering, American Institute of Physics Conference Series, vol. 803, pp. 80–87 (2005) 236Google Scholar
  80. 80. Runarsson, T.P., Sigurdsson, S.: Support Vector Machines. Vorlesungsunterlagen (2003). URL http://notendur.hi.is/~tpr/tutorials/svm/fyrirlestrar.html. (abgerufen 11/2016) 258, 259, 260, 261, 266, 268, 269, 271, 274
  81. 81. Runarsson, T.P., Sigurdsson, S.: Support Vector Machines - kernel-based learning methods, computational/statistical learning theory. University of Iceland (2003). URL https://notendur.hi.is/tpr/tutorials/svm/notes/. (abgerufen 11/2016) 269, 270
  82. 82. Sachs, L., Hedderich, J.: Angewandte Statistik, Methodensammlung mit R. Springer-Verlag Berlin Heidelberg (2009) 68, 234Google Scholar
  83. 83. Sain, S., Baggerly, K., Scott, D.: Cross-Validation of Multivariate Densities. Journal of the American Statistical Association 89, pp. 807–817 (1994) 247Google Scholar
  84. 84. SAS: SAS/STAT 9.2 User’s Guide - The Variogram Procedure (2009). URL http://support.sas.com/documentation/. (abgerufen 11/2016) 276, 277
  85. 85. Saunders, C., Gammerman, A., Vovk, V.: Ridge Regression Learning Algorithm in Dual Variables. In: 15th International Conference on Machine Learning (1998) 273Google Scholar
  86. 86. Schölkopf, B., Bartlett, P., Smola, A., Williamson, R.: Shrinking the Tube: A New Support Vector Regression Algorithm. In: Advances in Neural Information Processing Systems, vol. 11, pp. 330–336. MIT Press (1999) 269Google Scholar
  87. 87. Schwarz, G.: Estimating the Dimension of a Model. The Annals of Statistics 6, pp. 461–464 (1978) 236Google Scholar
  88. 88. Simpson, T., Lin, D., Chen, W.: Sampling strategies for computer experiments: design and analysis. International Journal of Reliability and Safety (IJRS) 2(3), pp. 209–240 (2001) 318Google Scholar
  89. 89. Smola, A.J., Schölkopf, B.: A Tutorial on Support Vector Regression. Statistics and Computing pp. 199–222 (2004) 258, 265Google Scholar
  90. 90. Söndergerath, D.: Multivariante Statistik. TU-Braunschweig (2007). Vorlesungsunterlagen 279Google Scholar
  91. 91. Spiegelhalter, D., Best, N., Carlin, B., van der Linde, A.: Bayesian Measures of Model Complexity and Fit (with Discussion). Journal of the Royal Statistical Society 64, pp. 583–616 (2002) 236Google Scholar
  92. 92. Stone, C.J., Hansen, M., Kooperberg, C., Truong, Y.K.: Polynomial splines and their tensor products in extended linear modeling. Ann. Statist 25, pp. 1371–1470 (1997) 254, 255Google Scholar
  93. 93. Street, J.O., Carroll, R.J., Ruppert, D.: A Note on Computing Robust Regression Estimates Via Iteratively Reweighted Least Squares. The American Statistician 42(2) (1988) 239Google Scholar
  94. 94. Suykens, J., Brabanter, K.D., Karsmakers, P., Ojeda, F., Alzate, C., Brabanter, J.D., Pelckmans, K., Moor, B.D., Vandewalle, J.: LS-SVMlab Toolbox User’s Guide. Technical report, Katholieke Universiteit Leuven (2011). URL http://www.esat.kuleuven.be/sista/lssvmlab/. (abgerufen 11/2016) 272
  95. 95. Suykens, J.A.K., Vandewalle, J.: Least Squares Support Vector Machine Classifiers. Neural Processing Letters 9(3), pp. 293–300 (1999) 272Google Scholar
  96. 96. T. Hastie, R.T., Friedman, J.: The Elements of Statistical Learning Data Mining, Inference and Prediction. Springer (2001) 256Google Scholar
  97. 97. Tibshirani, R.: Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society 58, pp. 267–288 (1996). URL http://www-stat.stanford.edu/~tibs/lasso/lasso.pdf. (abgerufen 11/2016) 238
  98. 98. Tibshirani, R.: The LASSO method for variable selection in the COX model. Statistics in medicine 16, pp. 385–395 (1997) 238Google Scholar
  99. 99. du Toit,W.: Radial Basis Function Interpolation. Master’s thesis, University of Stellenbosch (2008). URL http://scholar.sun.ac.za/handle/10019.1/2002. (abgerufen 11/2016) 284, 285
  100. 100. Vapnik, V., Cortes, C.: Support Vector Networks. Machine Learning 20, pp. 273–297 (1995). URL http://www.springerlink.com/content/k238jx04hm87j80g/. (abgerufen 11/2016) 258
  101. 101. Vapnik, V.N.: The Nature of statistical learning theory. Springer, New York (2000) 258Google Scholar
  102. 102. Venkataraman, P.: Applied Optimization with MATLAB Programming, 2nd edn. Wiley Publishing, Hoboken (2009) 261Google Scholar
  103. 103. Wackernagel, H.: Multivariate geostatistics - an introduction with applications, 2nd edn. Springer, Berlin (1998) 277Google Scholar
  104. 104. Wahba, G.: Splines Models for Observational Data. Series in Applied Mathematics 59 (1990) 254, 302Google Scholar
  105. 105. Wand, M., M.C.Jones: Multivariate Plug-in Bandwidth Selection. Computational Statistics 9, pp. 97–116 (1994) 247Google Scholar
  106. 106. Watson, G.: Smooth regression analysis. Sankhaya: The Indian Journal of Statistics A 26, pp. 359–372 (1964) 243Google Scholar
  107. 107. Welling, M.: Kernel Ridge Regression. Paper (2005) 273Google Scholar
  108. 108. Wendt, H.: Support Vector Machines for Regression Estimation and their Application to Chaotic Time Series Prediction. Master’s thesis, Technische Universität Wien (2005) 266, 267Google Scholar
  109. 109. Wermuth, N.: Beobachtungen zur Ridge-Regression. Jahrbücher für Nationalökonomie und Statistik 189, pp. 300–307 (1975) 238Google Scholar
  110. 110. Williams, C.K.I., Rasmussen, C.E.: Gaussian Processes for Regression. In: Advances in Neural Information Processing Systems, vol. 8, pp. 514–520 (1996). URL http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.25.8841. (abgerufen 11/2016) 300
  111. 111. Wilson, A.G., Adams, R.P.: Gaussian process kernels for pattern discovery and extrapolation (2013) 297Google Scholar

Copyright information

© Springer-Verlag GmbH Deutschland 2017

Authors and Affiliations

  • Karl Siebertz
    • 1
  • David van Bebber
    • 2
  • Thomas Hochkirchen
    • 3
  1. 1.AldenhovenDeutschland
  2. 2.AachenDeutschland
  3. 3.VaalsNiederlande

Personalised recommendations