2012
DOI: 10.1002/mmce.20687
|View full text |Cite
|
Sign up to set email alerts
|

Application of data mining methods to efficient microwave active device modeling

Abstract: In this work, the signal and noise behaviors of a microwave transistor within its operation domain (CT,V DS , IDS , f ) are modeled by the Artificial Neural Network (ANN) and Fuzzy Logic System (FLS) without using any information on the microwave circuit theory . A worked example is presented where the same data is employed for both models selected from the manufacturer's data sheets. Performances of the FLS and ANN models are compared and conclusions are drawn.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
10
0

Year Published

2012
2012
2020
2020

Publication Types

Select...
4

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(10 citation statements)
references
References 27 publications
0
10
0
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%
See 1 more Smart Citation
“…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%
“…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%
“…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%