Regularization with radial basis functions is an effective method in many machine learning applications. In recent years classes of radial basis functions with compact support have been proposed in the approximation theory literature and have become more and more popular due to their computational advantages. In this paper we study the statistical properties of the method of regularization with...

Frequency response analysis (FRA) is a sensitive ‎method established for testing the mechanical integrity of ‎transformers. However, interpretation of FRA signature still ‎needs expert opinions and there is no FRA interpretation code ‎generally accepted. Various mechanical faults with different ‎extents on power transformers are required to aid FRA ‎interpretation. To address this challenge, in...

Introduction:MAMMI is a dedicated PET based on high resolution detectors placed close to the breast. In this study, we presented a GATE model for the simulation of MAMMI scanner and model its performance of the MAMMI based on an adaptation of the NU 4-2008 NEMA standard.  Methods:A detailed of geometry MAMMI system that uses scintillation crystals coupled...

In the South Yellow Sea off the Jiangsu coast, there exists a special type of sand bodies, which are known as radial sand ridge field (RSRF). One of the characteristics of this area is the distinctive radial tidal current field. Although many studies have focused on the hydrodynamic environment around radial sand ridges, the knowledge on the genesis of the radial tidal current is still in a ver...

In this paper, we are interested to determine the carbon dioxide pressure in the arterial blood through radial velocity difference. The blood was modeled as a two phase mixture (an aqueous carbon dioxide solution with carbon dioxide gas) by Drift flux model and the Young-Laplace equation. The distributions of mixture velocities determined from the considered model permitted the calculation of t...

This paper introduces a novel ensemble learning approach based on recurrent radial basis function networks (RRBFN) for time series prediction with the aim of increasing the prediction accuracy. Standing for the base learner in this ensemble, the adaptive recurrent network proposed is based on the nonlinear autoregressive with exogenous input model (NARX) and works according to a multi-step (MS)...

Transformer model; Load flow analysis; Symmetrical components; Distribution systems Abstract This paper presents an efficient approach for developing three-phase transformer admittance matrices in the radial power-flow analysis. The proposed transformer model overcomes the singularity problem of the nodal admittance submatrices of ungrounded transformer configurations. This has been achieved by...

A hybrid and contextual radial basis function networklhidden Markov model off-line handwritten word recognition system is presented. The task assigned to the radial basis function networks is the estimation of emission probabilities associated to Markov states. The model is contextual because the estimation of emission probabilities takes into account the left context of the current image segme...

In this article, axisymmetric buckling behavior of piezoelectric fiber reinforced polymeric composite (PFRPC) annular plate subjected to electro-thermo-mechanical field is presented utilizing principle of minimum potential energy. Boron-nitride nanotubes (BNNTs) are used as fibers. Full coupling between electrical, mechanical and thermal fields are considered according to a representative volum...

Dust particles charging in a stratified positive column of a low-pressure DC glow discharge was investigated theoretically. The presented model consists of (i) previously developed 1D selfconsistent model for discharge parameters on the tube axis; (ii) ambipolar approximation for radial electric potential distribution and the assumption that the electron energy distribution function in radial d...