Analysis of support vector regression for approximation of complex engineering analyses

By Stella M. Clarke, Jan Griebsch, Timothy W. Simpson. Design Automation Conference, 2005

632 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/40669ea48223d8595361e5edc24aea61662d54b3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Information Systems

In Management Science and Operations Research

Citations in the corpus

A survey of adaptive sampling for global metamodeling in support of simulation-based complex engineering design (2017, background): “Various types of metamodeling techniques, e.g., Kriging (also known as Gaussian process, GP) (Cressie 1988; Rasmussen 2006), radial basis functions (RBF) (Dyn et al. 1986), polynomial response (PR) and support vector regression (SVR) (Clarke et al. 2005), have been continuously developed.”
Forecasting municipal solid waste generation using artificial intelligence modelling approaches. (2016, methodology): “For forecasting purpose, e-type support vector regression method was employed in this study (Clarke et al., 2005).”
An efficient method for reliability analysis under epistemic uncertainty based on evidence theory and support vector regression (2015, methodology): “Support vector regression SVR is a particular implementation of support vector machines, and it was used as a metamodelling technique to construct the approximation of complex engineering analyses (Clarke, Griebsch, and Simpson 2005).”
A review of the-state-of-the-art in data-driven approaches for building energy prediction (2020, background): “17 The advantages of SVR are: (1) It has the ability to solve global minima instead of local minima[75]; (2) Its computational complexity is not determined by the dimensionality of feature space[76]; and (3) Its prediction performance is not sensitive to the noisy data.”
Comparison study on the accuracy of metamodeling technique for non-convex functions (2009, methodology): “( ) ( )* 1 . l i i i f bα α = = − ⋅ +∑ ix x x (8) The Gaussian kernel function, which is widely used in SVR, is defined by Eq.”
Polynomial-Chaos-based Kriging (2015, neutral): “…modeling (also called Kriging) Sacks et al. (1989); Rasmussen and Williams (2006); Santner et al. (2003); Stein (1999), and support vector machines Gunn (1998); Smola and Sch¨olkopf (2006); Vazquez and Walter (2003); Clarke et al. (2003), which have been extensively investigated in the last decade.”
Reliability-Based Design Optimization of Nonlinear Aeroelasticity Problems (2010, methodology): “The reliability index is then approximated by support vector regression [27].”
Multiple surrogates: how cross-validation errors can help us to obtain the best predictor (2009, methodology): “…1993; Cheng and Titterington 1994), kriging models (Sacks et al. 1989; Lophaven et al. 2002) support vector regression (Smola and Scholkopf 2004; Clarke et al. 2005) that require optimization in the fitting process, increasingly replace the traditional polynomial response surfaces (Box et al.…”
Managing computational complexity using surrogate models: a critical review (2020, neutral): “As shown in Table 2, (Barton 1994; Clarke et al. 2004; Turner 2005; Chen et al. 2006; Fang et al. 2017) review the most commonly used SMs, compare them, and provide recommendations for the choice of SMs.”
Support vector machine in structural reliability analysis: A review (2023, neutral): “Clarke et al. [16] investigated the performance of SVR in comparison to four commonly used metamodeling techniques namely, RSM, Kriging, RBFN, and MARS for approximating responses of complex engineering systems.”
Physics-Informed Multi-LSTM Networks for Metamodeling of Nonlinear Structures (2020, methodology): “A review of application of these methods for metamodeling of some engineering systems can be found in [22].”
Incremental modeling of a new high-order polynomial surrogate model (2016, background): “(MARS) [8], support vector regression (SVR) [9, 10], high dimensional model representation (HDMR)”