This paper investigates the use of Kriging in random simulation when the simulation output variances are not constant. Kriging gives a response surface or metamodel that can be used for interpolation. Because Ordinary Kriging assumes constant variances, this paper also applies Detrended Kriging to estimate a non-constant signal function, and then standardizes the residual noise through the hete...

This paper describes a combination approach of a digital finite element modeling technique and the Kriging method for structural optimization. Since the digital modeling technique includes some inaccuracies in a modeling process, applicability of the Kriging method to noisy data is investigated. An estimated surface generated by the conventional Kriging method will be wavy and not appropriate t...

The effectiveness of surrogate modeling of helicopter vibrations, and the use of the surrogates for optimization of helicopter vibration are studied. The accuracies of kriging, radial basis function interpolation, and polynomial regression surrogates are compared. In addition, the surrogates for the vibratory hub shears and moments are used to generate an objective function which is employed in...

PCA in a reproducing kernel Hilbert space is analysed as probabilistically optimal procedure of dimension reduction given a covariance structure by the reproducing kernel. It provides a unifying framework for various seemingly disparate and special techniques of dimension reduction applied to splines, in geostatistical “kriging” or in interpolation of data resulting from computer experiments. R...

This paper presents a method for finding the global maximum of a spatially varying field using a multi-agent system. A surrogate model of the field is determined via Kriging (Gaussian process regression) from a set of measurements collected by the agents. A criterion exploiting Kriging statistical properties is introduced for selecting new sampling points that each vehicle must rally. These new...

This paper discusses the opportunity of using Machine Learning techniques in an automatic environmental mapping context, as was the case for the SIC2004 exercise. First, the Machine Learning methodology is quickly described and compared to Geostatistics. From there, some clues about when to apply Machine Learning are proposed, and what outcomes can be expected from this choice. Finally, three w...