Sabri Kaya

NEURAL MODELS FOR COPLANAR STRIP LINE SYNTHESIS

Simple and accurate models based on artificial neural networks (ANNs) are presented to accurately determine the physical dimensions of coplanar strip lines (CPSs). Five learning algorithms, Levenberg-Marquardt (LM), bayesian regularization (BR), quasiNewton (QN), conjugate gradient with Fletcher (CGF), and scaled conjugate gradient (SCG), are used to train the neural models. The neural results are compared with the results of the quasi-static analysis and the synthesis formulas available in the literature. The accuracy of the neural model trained by LM algorithm is found to be better than 0.24% for 10614 CPS samples.

Artificial Neural Networks for Calculating the Characteristic Impedance of Air-Suspended Trapezoidal and Rectangular-Shaped Microshield Lines

Neural models for calculating the characteristic impedance of air-suspended trapezoidal and rectangular-shaped microshield lines, based on the multilayered perceptrons (MLPs), are presented. Six learning algorithms, bayesian regulation (BR), Levenberg-Marquardt (LM), quasi-Newton (QN), scaled conjugate gradient (SCG), resilient propagation (RP), and conjugate gradient of Fletcher-Powell (CGF), are used to train the MLPs. The characteristic impedance results obtained by using neural models are in very good agreement with the results available in the literature. When the performances of neural models are compared with each other, the best test result is obtained from the MLPs trained by the BR algorithm.

Neural Models for the Elliptic- and Circular-Shaped Microshield Lines

This article presents a new approach based on artificial neural networks (ANNs) to calculate the characteristic parameters of elliptic and circular-shaped microshield lines. Six learning algorithms, bayesian regularization (BR), Levenberg-Marquardt (LM), quasi- Newton (QN), scaled conjugate gradient (SCG), resilient propagation (RP), and conjugate gradient of Fletcher-Reeves (CGF), are used to train the ANNs. The neural results are in very good agreement with the results reported elsewhere. When the performances of neural models are compared with each other, the best and worst results are obtained from the ANNs trained by the BR and CGF algorithms, respectively.

ADAPTIVE NEURO-FUZZY MODELS FOR CONVENTIONAL COPLANAR WAVEGUIDES

In this work a new method based on the adaptive neuro-fuzzy inference system (ANFIS) was successfully introduced to determine the characteristic parameters, effective permittivities and characteristic impedances, of conventional coplanar waveguides. The ANFIS has the advantages of expert knowledge of fuzzy inference system and learning capability of neural networks. A hybrid-learning algorithm, which combines least-square method and backpropagation algorithm, is used to identify the parameters of ANFIS. There are very good agreement between the results of ANFIS models, experimental works, conformal mapping technique, spectral domain approach and a commercial electromagnetic simulator, MMICTL.

SYNTHESIS FORMULAS FOR MULTILAYER HOMOGENEOUS COUPLING STRUCTURE WITH GROUND SHIELDING

This paper presents new and accurate synthesis formulas for the multilayer homogeneous coupling structure with ground shielding (MHCS-WGS). The synthesis formulas are obtained by means of a differential evolution algorithm (DEA), and are useful to microwave engineers for accurately calculating the physical dimensions of MHCS-WGS. The average percentage error is calculated to be 0.8% for 13614 MHCS-WGS samples having different electrical parameters and physical dimensions, as compared with the results of quasi-static analysis.

COMPARISON OF ADAPTIVE-NETWORK-BASED FUZZY INFERENCE SYSTEM MODELS FOR ANALYSIS OF CONDUCTOR-BACKED ASYMMETRIC COPLANAR WAVEGUIDES

A method based on adaptive-network-based fuzzy infer- ence system (ANFIS) is presented for the analysis of conductor- backed asymmetric coplanar waveguides (CPWs). Four optimization algorithms, hybrid learning, simulated annealing, genetic, and least- squares, are used to determine optimally the design parameters of the ANFIS. The results of ANFIS models are compared with the results of conformal mapping technique, a commercial electromagnetic simula- tor IE3D, and the experimental works realized in this study. There is very good agreement among the results of ANFIS models, quasi-static method, IE3D, and experimental works. The proposed ANFIS models are not only valid for conductor-backed asymmetric CPWs but also valid for conductor-backed symmetric CPWs.

ANFIS MODELS FOR SYNTHESIS OF OPEN SUPPORTED COPLANAR WAVEGUIDES

Simple and accurate models based on adaptive-network-based fuzzy inference system (ANFIS) to compute the physical dimensions of open supported coplanar waveguides are presented. The ANFIS is a class of adaptive networks which are functionally equivalent to fuzzy inference systems. Four optimization algorithms, hybrid learning, simulated annealing, least-squares, and genetic, are used to determine optimally the design parameters of the ANFIS. When the per- formances of ANFIS models are compared with each other, the best results are obtained from the ANFIS models trained by the hybrid learning algorithm. The results of ANFIS are compared with the results of the conformal mapping tech- nique, the rigorous spectral-domain hybrid mode analysis, the improved spectral domain approach, the synthesis formulas, a full-wave electromagnetic simulator IE3D, and experimental works realized in this study.

Effects of dielectric spacer on absorption characteristics of double-headed arrow shaped perfect absorber

In this study, effects of dielectric spacer on absorption characteristics of double-headed arrow shaped perfect absorber (PA) are investigated. The PA nanoantenna array is analyzed by using the FDTD (Finite Difference Time Domain) method. Also the electric field distributions of PA array are obtained for different dielectric layers. To analyze the refractive index sensing capability of the PA array, the sensitivity characteristics are investigated by loading different refractive indexed dielectric cladding media. Owing to the dual-band spectral response, enhanced electric fields, and refractive index sensitivity, the double-headed arrow PA nanoantenna array can be used for bio-sensing applications in infrared regime.

Accurate Synthesis Formulas Obtained by Using a Differential Evolution Algorithm for Conductor-Backed Coplanar Waveguides

In this paper, accurate synthesis formulas obtained by using a difierential evolution (DE) algorithm for conductor-backed coplanar waveguides (CBCPWs) are presented. The synthesis formulas are useful to microwave engineers for accurately calculating the physical dimensions of CBCPWs. The results of the synthesis formulas are compared with the theoretical and experimental results available in the literature. A full-wave electromagnetic simulator IE3D and experimental results are obtained in this work. The average percentage error of the synthesis formulas obtained by using DE algorithm is computed as 0.67% for 1086 CBCPW samples having difierent electrical parameters and physical dimensions, as compared with the results of quasi-static analysis.