Abstract
This work aims to develop a new High Dimensional Model Representation (HDMR) based method which can construct an analytical structure for a given multivariate data modelling problem. Modelling multivariate data through a divide-and-conquer method stands for multivariate data partitioning process in which we deal with a number of less variate data sets instead of a single N dimensional problem. Generalized HDMR is one of these methods used to model a multivariate data set which has a number of scattered nodes with associated function values. However, Generalized HDMR includes a linear equation system with huge number of unknowns and equations to be solved. This equation sometimes has linearly dependent equations in it and this is an undesirable situation. This work offers a new method named Piecewise Generalized HDMR method which bypasses this disadvantage as well as reducing the mathematical complexity and CPU time needed to complete the algorithm of the previous method. Our new method splits the given problem domain into subdomains, applies the Generalized HDMR philosophy to each subdomain and superpositions the information coming from these subdomains. The algorithm of this new method and a number of numerical implementations are given in this paper.
Similar content being viewed by others
References
Sobol I.M.: Sensitivity estimates for nonlinear mathematical models. Math. Model. Comput. Exp. (MMCE) 1, 407–414 (1993)
Rabitz H., Alış Ö.F., Shorter J., Shim K.: Efficient input-output model representations. Comput. Phys. Commun. 117, 11–20 (1999)
Rabitz H., AlışÖ.: General foundations of high dimensional model representations. J. Math. Chem. 25, 197–233 (1999)
Li G., Wang S.-W., Rabitz H.: Practical approaches to construct RS-HDMR component functions. J. Phys. Chem. A 106, 8721–8733 (2002)
Demiralp M.: High dimensional model representation and its application varieties. Math. Res. 9, 146–159 (2003)
Tunga B., Demiralp M.: Hybrid high dimensional model representation approximants and their utilization in applications. Math. Res. 9, 438–446 (2003)
Demiralp M.: Illustrative implementations to show how logarithm based high dimensional model representation works for various function structures. WSEAS Trans. Comput. 5, 1339–1344 (2006)
Yaman İ., Demiralp M.: A new rational approximation technique based on transformational high dimensional model representation. Numer. Algorithms 52, 385–407 (2009)
Tunga B., Demiralp M.: Constancy maximization based weight optimization in high dimensional model representation. Numer. Algorithms 52, 435–459 (2009)
Tunga M.A., Demiralp M.: A factorized high dimensional model representation on the partitioned random discrete data. Appl. Numer. Anal. Comp. Math. 1, 231–241 (2004)
Ziehn T., Tomlin A.S.: A global sensitivity study of sulfur chemistry in a premixed methane flame model using HDMR. Int. J. Chem. Kinet. 40, 742–753 (2008)
Ziehn T., Tomlin A.S.: GUI-HDMR—a software tool for global sensitivity analysis of complex models. Environ. Model. Softw. 24, 775–785 (2009)
Sridharan J., Chen T.: Modeling multiple input switching of CMOS gates in DSM technology using HDMR. Proc. Des. Autom. Test Eur. 1(3), 624–629 (2006)
Rao B.N., Chowdhury R.: Probabilistic analysis using high dimensional model representation and fast fourier transform. Int. J. Comput. Methods Eng. Sci. Mech. 9, 342–357 (2008)
Chowdhury R., Rao B.N.: Hybrid high dimensional model representation for reliability analysis. Comput. Methods Appl. Mech. Eng. 198, 753–765 (2009)
Gomez M.C., Tchijov V., Leon F., Aguilar A.: A tool to improve the execution time of air quality models. Environ. Model. Softw. 23, 27–34 (2008)
Banerjee I., Ierapetritou M.G.: Design optimization under parameter uncertainty for general black-box models. Ind. Eng. Chem. Res. 41, 6687–6697 (2002)
Banerjee I., Ierapetritou M.G.: Parametric process synthesis for general nonlinear models. Comput. Chem. Eng. 27, 1499–1512 (2003)
Banerjee I., Ierapetritou M.G.: Model independent parametric decision making. Ann. Oper. Res. 132, 135–155 (2004)
Shan S., Wang G.G.: Survey of modeling and optimization strategies to solve high-dimensional design problems with computationally-expensive black-box functions. Struct. Multidiscip. Optim. 41, 219–241 (2010)
Tunga M.A., Demiralp M.: A new approach for data partitioning through high dimensional model representation. Int. J. Comput. Math. 85, 1779–1792 (2008)
Tunga M.A., Demiralp M.: Data partitioning via generalized high dimensional model representation (GHDMR) and multivariate interpolative applications. Math. Res. 9, 447–462 (2003)
M.A. Tunga, M. Demiralp, Data Partitioning Through Piecewise Based Generalized GHDMR: Univariate Case, the 2nd International Symposium on Computing in Science and Engineering (ISCSE 2011), June 1–4, 2011 (Kuşadas Aydın, Turkey, 2011), pp. 128–133
Tunga M.A.: An approximation method to model multivariate interpolation problems: indexing HDMR. Math. Comput. Model. 53(9–10), 1970–1982 (2011)
Tunga M.A.: A matrix based indexing HDMR method for multivariate data modelling. J. Math. Chem. 49(5), 1092–1114 (2011)
Oevel W., Postel F., Wehmeier S., Gerhard J.: The MuPAD Tutorial. Springer, New York (2000)
Deitel H.M., Deitel P.J., Nieto T.R., McPhie D.C.: How to Program Perl. Prentice Hall, New Jersey (2001)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Tunga, M.A., Demiralp, M. Multivariate data modelling through Piecewise generalized HDMR method. J Math Chem 50, 1711–1726 (2012). https://doi.org/10.1007/s10910-012-0001-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10910-012-0001-2