Application of data mining methods to efficient microwave active device modeling

Cengiz, Yavuz

doi:10.1002/mmce.20687

Cited by 4 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table presents a further comparison of the DRN model with other regression algorithms used in literature such as support vector regression machines, instance‐based learning (IBK), decision table, random tree, random forest, and Kstar . Similarly to the case studies, the data given in Table have been divided into two randomly distributed data sets and then given to the selected algorithms.…”

Section: Case Studymentioning

confidence: 99%

“…Table 5 presents a further comparison of the DRN model with other regression algorithms used in literature such as support vector regression machines, 40,84 instance-based learning (IBK), 85 decision table, random tree, random forest, and Kstar. 86,87 Similarly to the case studies, the data given in Table 1 have been divided into two randomly distributed FIGURE 11 Performance results of deep regression network (DRN) and multilayer perceptron (MLP) algorithms for (A) ϵ r =1, H=0.5 mm, (B) ϵ r =3.5, H=10 mm, (C) ϵ r =5, H=15 mm, (D) H=5 mm, at 10 GHz, (E) H=10 mm, at 10 GHz, (F) H=15 mm, at 10 GHz, (G) ϵ r =3.5, at 8 GHz, (H) ϵ r =3.5, at 10 GHz, and (I) ϵ r =3.5, at 12 GHz data sets and then given to the selected algorithms. As can be seen from Table 5, the DRN model achieves far more accurate performance result compared with the mentioned commonly used machine learning and data mining regression methods.…”

Section: Comparison Of Drn and Mlp Regression Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Application of artificial intelligence algorithms on modeling of reflection phase characteristics of a nonuniform reflectarray element

Mahoutı

2019

Int J Numerical Modelling

View full text Add to dashboard Cite

Reflectarray antennas (RAs) have the ability to combine the advantages of both traditional parabolic reflector and phased array antennas without the need for feed network designs. Microstrip reflectarrays (MRAs) have the advantages of being small size, light weighted, easy to prototyped, high gain, low side-lobe level, and a predetermined radiation pattern. These can be achieved by precise calculation of reflection phase at each RA unit independently with a phase compensation proportional to the distance from the feed. The challenging problem is to have a fast and high accurate unit element to be used in multidimension, multiobjective design optimization. Herein, artificial intelligence algorithms (AIAs) have been used for prediction of reflection phase characterization of an X band MRA unit element with respect to the geometrical design parameters. Firstly, a nonuniform unit RA has been designed in 3D electromagnetic (EM) simulation tool for creating the training validation data sets. Then, the data sets are given to the different types of AIA regression models such as multilayer perceptron, symbolic regression, and convolutional neural network. From the results of the validation data set, it can be concluded that the proposed models have sufficient accuracy that can be used in a computationally efficient design optimization process of a large-scale RA design.

show abstract

Section: Case Studymentioning

confidence: 99%

Section: Comparison Of Drn and Mlp Regression Modelsmentioning

confidence: 99%

Application of artificial intelligence algorithms on modeling of reflection phase characteristics of a nonuniform reflectarray element

Mahoutı

2019

Int J Numerical Modelling

View full text Add to dashboard Cite

show abstract

“…In the next section, GRNN will be used as a nonlinear both extrapolator and interpolator to model scattering and noise parameters of microwave transistor BFP640 and at the same time, the MLP modeling will also be presented for the purpose of comparison between the generalization capabilities of both competitive black‐box modeling methods. Furthermore, a need for the GRNN extrapolator has arisen to implement to a second transistor, ATF‐551M4, for the comparison of the recently emerging 10 ‘data mining’ modeling methods . All of these will be given in the following section in details.…”

Section: General Regression Neural Networkmentioning

confidence: 99%

“…In this section, for the purpose of comparison, the generalization abilities of the GRNN and the novel data methods given in , GRNN is developed using the same training and test data as used in for modeling S‐parameter and N‐parameter of ATF‐551M4 , and all the resulted performance criteria take place in Tables . Also, in Tables and , a more detailed performance analysis of the GRNN model for the selected transistor is presented.…”

Section: Worked Examplesmentioning

confidence: 99%

Cost‐effective GRNN‐based modeling of microwave transistors with a reduced number of measurements

Güneş

Mahoutı

Demi̇rel

et al. 2015

Int J Numerical Modelling

View full text Add to dashboard Cite

In this article, a simple, accurate, fast, and reliable black-box modeling is proposed for the scattering (S)-parameters and noise (N)-parameters of microwave transistors using the general regression neural network (GRNN) with the substantially reduced measurements and computational cost. In this modeling method, GRNN is employed as a nonlinear extrapolator to generalize the S-data and N-data belonging to only a single bias voltage in the middle region into the entire device operation domain of the bias condition (V DS /V CE , I DS /I C , f) within the shortened human effort. The proposed method is implemented to the modeling of the two transistors BFP640 and ATF-551 M4 as study cases. Thus, comparisons are made with the multilayer perceptrons, trained by the two standard backward propagation algorithms, which are the Levenberg-Marquardt, Bayesian regularization and the 10 data mining methods recently published in the literature using the chosen training data sets in both ınterpolation and extrapolation types of generalization. All the comparisons are achieved using four criteria commonly used in the literature. It can be concluded that GRNN is found to be a fast and accurate modeling method that extrapolates the reduced amount of training data consisting of measured S-parameters and N-parameters at the typical currents of the middle bias voltage to the wide operating range.

show abstract

“…Neural networks have been applied in modeling of either active devices or passive components, in microwave circuit analysis and design, etc. It has been proposed in microwave, MESFET and HEMT transistor signal and noise performance modeling [6]- [8]. In this paper, Adaptive Neuro-fuzzy inference System (ANFIS) for HEMT transistor noise modeling is proposed.…”

Section: Introductionmentioning

confidence: 99%

Application of Adaptive Neuro-Fuzzy Inference System for Predictaion of HEMT Transistor Noise Parameters

Hayati¹,

Rezaei²

2012

IJMO

View full text Add to dashboard Cite

In this paper, simulation of HEMT Transistor Noise Parameters such as minimum noise figure, normalized equivalent resistance , magnitude of optimum reflection coefficient and angle of optimum reflection coefficient dependence on bias conditions such as dc drain-to-source voltage, dc drain-to-source current, frequency and Sparameters using ANFIS model is carried out. This model can accurately predict transistor noise parameters in a wide frequency ranges for all bias points from the operating range including transistor S-parameters. The proposed models can be used as efficient tools for noise modeling of HEMT transistor.Index Terms-HEMT transistor, adaptive neuro-fuzzy inference system, high electron mobility transistor, sparameter, noise modeling. He has published more than 85 papers in international journals and conferences. His current research interests include application of computational intelligence, artificial neural networks, fuzzy system, neuro-fuzzy systems and electronic circuit synthesis, modeling and simulations, microwave and millimeter wave devices and circuits.Abbas Rezaei received the B.S. and M.S. in electronics engineering from Razi University, Kermanshah, Iran, in 2005 and 2009, respectively. He was with the

show abstract

Application of data mining methods to efficient microwave active device modeling

Cited by 4 publications

References 27 publications

Application of artificial intelligence algorithms on modeling of reflection phase characteristics of a nonuniform reflectarray element

Application of artificial intelligence algorithms on modeling of reflection phase characteristics of a nonuniform reflectarray element

Cost‐effective GRNN‐based modeling of microwave transistors with a reduced number of measurements

Application of Adaptive Neuro-Fuzzy Inference System for Predictaion of HEMT Transistor Noise Parameters

Contact Info

Product

Resources

About