Dynamic simulation metamodeling using MARS: A case of radar simulation

Date

2016-06-01

Author

Bozagac, Doruk
Batmaz, İnci
Oğuztüzün, Mehmet Halit S.

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

191
views

0
downloads

Dynamic system simulations require relating the inputs to the multivariate output which can be a function of time space coordinates. In this work, we propose a methodology for the metamodeling of dynamic simulation models via Multivariate Adaptive Regression Splines (MARS). To handle incomplete output processes, where the simulation model does not produce an output in some steps due to missing inputs, we have devised a two-stage metamodeling scheme. The methodology is demonstrated on a dynamic radar simulation model. The prediction performance of the resulting metamodel is tested with four different sampling techniques (i.e., designs) and 16 sample sizes. We also investigate the effect of alternative coordinate system representations on the metamodeling performance. The results suggest that MARS is an effective method for metamodeling dynamic simulations, particularly, when expert judgment is not readily available. Results also show that there are interactions between the coordinate systems and sampling techniques, and some design-representation-size combinations are very promising in the metamodeling of radar simulations. (C) 2016 International Association for Mathematics and Computers in Simulation (IMACS). Published by Elsevier B.V. All rights reserved.

Subject Keywords

Simulation, Metamodeling, Dynamic simulation model, MARS, Statistical design of experiments

URI

https://hdl.handle.net/11511/39812

Journal

MATHEMATICS AND COMPUTERS IN SIMULATION

DOI

https://doi.org/10.1016/j.matcom.2016.01.005

Collections

Department of Statistics, Article

Suggestions

OpenMETU
Core

Linear parameter varying control for autonomous systems: methods and application examples Çalış, Fatih; Schmidt, Klaus Verner; Department of Electrical and Electronics Engineering (2022-8-24) Linear parameter varying (LPV) systems are nonlinear systems which can be modelled as linear systems whose parameters change as a function of different "scheduling parameters". In other words, the dynamics of the LPV systems change during the operation hence they require a parameter dependent controller. Although classical gain-scheduling approaches satisfy some performance criteria for constant dynamics, they don't guarantee stability while the scheduling parameter is changing. On the other hand, H∞-norm b...
Model-driven engineering framework for replicable simulation experiments Dayıbaş, Orçu; Oğuztüzün, Halil.; Department of Computer Engineering (2019) Simulation experiments allow the user to capture the specific variability of multiple interdependent processes. The use of simulation models is widely accepted by practitioners from diverse areas of applied sciences. Therefore, simulation experiments are an essential part of computational science and engineering. Nevertheless, simulations are rarely replicated due to reuse and maintenance challenges related to models and data. In this respect, it is proposed that some crucial and labor intensive parts of th...
Hypothesis-driven simulation experiments with an extension to SED-ML Cam, S.; Oğuztüzün, Mehmet Halit S.; Yilmaz, L. (2022-03-01) Most of the frameworks or assistance systems for experiment specification do not provide a process explicitly based on formally specified hypotheses. This deficiency leads to inaccurate or insufficient record of an experiment, decreasing the trustworthiness and reproducibility of the experiment. Moreover, the wide variety of models, metamodels, tools, and data for experimentation requires Global Model Management (GMM) that is utilizing Model-Driven Engineering techniques, facilitates documentation, sharing,...
Stochastic modeling of biochemical systems with filtering and smoothing Haksever, Merve; Uğur, Ömür; Department of Scientific Computing (2019) Deterministic modeling approach is the traditional way of analyzing the dynamical behavior of a reaction network. However, this approach ignores the discrete and stochastic nature of biochemical processes. In this study, modeling approaches, stochastic simulation algorithms and their relationships to each other are investigated. Then, stochastic and deterministic modeling approaches are applied to biological systems, Lotka-Volterra prey-predator model, Michaelis-Menten enzyme kinetics and JACK-STAT signalin...
Dynamical systems and Poisson structures Guerses, Metin; Guseinov, Gusein Sh; Zheltukhın, Kostyantyn (AIP Publishing, 2009-11-01) We first consider the Hamiltonian formulation of n=3 systems, in general, and show that all dynamical systems in R-3 are locally bi-Hamiltonian. An algorithm is introduced to obtain Poisson structures of a given dynamical system. The construction of the Poisson structures is based on solving an associated first order linear partial differential equations. We find the Poisson structures of a dynamical system recently given by Bender et al. [J. Phys. A: Math. Theor. 40, F793 (2007)]. Secondly, we show that al...

Citation Formats

D. Bozagac, İ. Batmaz, and M. H. S. Oğuztüzün, “Dynamic simulation metamodeling using MARS: A case of radar simulation,” MATHEMATICS AND COMPUTERS IN SIMULATION, pp. 69–86, 2016, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/39812.