Microwave Devices and Antennas Modelling by Support Vector Regression Machines

Angiulli, Giovanni; Cacciola, Matteo; Versaci, Mario

doi:10.1109/tmag.2007.892480

Cited by 123 publications

(54 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Theoretically SIW resonances are the complex frequencies f for which Equation 2 (Angiulli, 2007;Angiulli et al, 2007;2009…”

Section: Ajasmentioning

confidence: 99%

Design of Square Substrate Integrated Waveguide Cavity Resonators: Compensation of Modelling Errors by Support Vector Regression Machines

Angiulli¹

2012

American Journal of Applied Sciences

View full text Add to dashboard Cite

The design of Substrate Integrated Waveguide (SIW) resonators is usually a cumbersome process, especially due to the length "trial and error" procedure involved in this task. In this study Support Vector Regression Machines (SVRMs) are employed to compensate the modeling errors associated to the design of SIW rectangular cavity resonators. To validate the proposed approach, we have compared the design outputs provided by our method with the results provided by commercial full wave software. The comparison between our predictions and the full wave simulations validate the effectiveness of the proposed approach.

show abstract

“…Theoretically SIW resonances are the complex frequencies f for which Equation 2 (Angiulli, 2007;Angiulli et al, 2007;2009…”

Section: Ajasmentioning

confidence: 99%

Design of Square Substrate Integrated Waveguide Cavity Resonators: Compensation of Modelling Errors by Support Vector Regression Machines

Angiulli¹

2012

American Journal of Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Higher-level properties of input characteristics have also been modelled. Such studies have dealt with resonant frequency modelling by neural-network-based methods [7,8] and GPR [9]; resonant input impedance modelling using support vector machines [10]; and impedance bandwidth modelling by neural networks (e.g. [11]).…”

Section: Introductionmentioning

confidence: 99%

“…Even so, it appears as if there have been hardly any attempts to formally construct surrogate models that can account for such effects (e.g. none of [2][3][4][5][6][7][8][9][10][11][12] included substrate/ground-plane dimensions as model input variables; in [17] however, a neural network was used to model self-and mutual-admittances of a monopole array as they varied with ground-plane dimensions, amongst other variables).…”

Section: Introductionmentioning

confidence: 99%

Characterisation by Gaussian processes of finite substrate size effects on gain patterns of microstrip antennas

Jacobs

2016

IET Microwaves, Antennas & Propagation

View full text Add to dashboard Cite

A procedure is presented for characterising the effects of varying finite substrate/ground plane size on the gain properties of microstrip antennas by means of Gaussian process regression (GPR). Two kinds of microstrip antenna were considered, namely a probe-fed patch antenna on both thin and thick dielectric substrates, and an L-probe-fed patch on a thick air substrate. CST Microwave Studio was used to generate training and test data for the GPR models. Frontal E and Hplane gain patterns could be predicted with normalised root-mean-square errors (RMSEs) of <1.8% for the thin-substrate probe-fed patch and the L-probe-fed patch; for the thick-substrate probe-fed patch, RMSEs were 2.1 and 2.8% for the two principal plane gain patterns, respectively. Furthermore, the GPR models could predict patterns at least two orders of magnitude faster than it took to obtain them via direct simulation in CST. Such models are expected to be useful in CAD-based environments for rapidly obtaining estimates of substrate/ground-plane size effects on gain characteristics in lieu of time-consuming full-wave simulations.

show abstract

“…Even for the multilayer perceptron (MLP), which is ubiquitous in its application to supervised learning problems, the number of hidden units that should be chosen often is an open question, relying for a solution on a trial-and-error approach or experience [12,13]. While adaptive techniques have been proposed for deleting or adding hidden units to a neural network during training [14], this adds further complexity to the modeling process.…”

Section: Introductionmentioning

confidence: 99%

“…One reason is that a Gaussian process model requires training of far fewer parameters (in the order of the dimension of the input vectors) than, e.g., a MLP with one hidden layer, where the number of weights to be learned typically is in the order of N i ×N h +N h ×N o , with N i , N h , and N o the number of input, hidden, and output nodes respectively. A Gaussian process is an instance of a so-called kernel machine; it is differentiated by its probablistic basis from the support vector regression machine (SVRM), another kernel machine that has very recently found application in antenna-related problems (e.g., [13]). …”

Section: Introductionmentioning

confidence: 99%

Gaussian Process Modeling of CPW-Fed Slot Antennas

Villiers¹,

Jacobs²

2009

PIER

View full text Add to dashboard Cite

Abstract-Gaussian process (GP) regression is proposed as a structured supervised learning alternative to neural networks for the modeling of CPW-fed slot antenna input characteristics. A Gaussian process is a stochastic process and entails the generalization of the Gaussian probability distribution to functions. Standard GP regression is applied to modeling S 11 against frequency of a CPW-fed secondresonant slot dipole, while an approximate method for large datasets is applied to an ultrawideband (UWB) slot with U-shaped tuning stub -A challenging problem given the highly non-linear underlying function that maps tunable geometry variables and frequency to S 11 / input impedance. Predictions using large test data sets yielded results of an accuracy comparable to the target moment-method-based full-wave simulations, with normalized root mean squared errors of 0.50% for the slot dipole, and below 1.8% for the UWB antenna. The GP methodology has various inherent benefits, including the need to learn only a handful of (hyper) parameters, and training errors that are effectively zero for noise-free observations. GP regression would be eminently suitable for integration in antenna design algorithms as a fast substitute for computationally intensive full-wave analysis.

show abstract

Microwave Devices and Antennas Modelling by Support Vector Regression Machines

Cited by 123 publications

References 9 publications

Design of Square Substrate Integrated Waveguide Cavity Resonators: Compensation of Modelling Errors by Support Vector Regression Machines

Design of Square Substrate Integrated Waveguide Cavity Resonators: Compensation of Modelling Errors by Support Vector Regression Machines

Characterisation by Gaussian processes of finite substrate size effects on gain patterns of microstrip antennas

Gaussian Process Modeling of CPW-Fed Slot Antennas

Contact Info

Product

Resources

About