• Türkçe
    • English
  • Türkçe 
    • Türkçe
    • English
  • Giriş
Öğe Göster 
  •   Açık Erişim Ana Sayfası
  • Avesis
  • Dokümanı Olmayanlar
  • Makale
  • Öğe Göster
  •   Açık Erişim Ana Sayfası
  • Avesis
  • Dokümanı Olmayanlar
  • Makale
  • Öğe Göster
JavaScript is disabled for your browser. Some features of this site may not work without it.

Accurate Modeling of Frequency Selective Surfaces Using Fully-Connected Regression Model With Automated Architecture Determination and Parameter Selection Based on Bayesian Optimization

Yazar
ÇALIK, NURULLAH
Koziel, Slawomir
MAHOUTİ, Peyman
Belen, Mehmet Ali
Üst veri
Tüm öğe kaydını göster
Özet
Surrogate modeling has become an important tool in the design of high-frequency structures. Although full-wave electromagnetic (EM) simulation tools provide an accurate account for the circuit characteristics and performance, they entail considerable computational expenditures. Replacing EM analysis by fast surrogates provides a way to accelerate the design procedures. Unfortunately, modeling of microwave passives is a challenging task due to their highly-nonlinear outputs. Frequency selective surfaces (FSSs) constitute a representative example with their multi-resonant reflection and transmission responses that need to be represented over broad frequency ranges. Deep neural networks (DNNs) seem to be the promising techniques for handling such cases. However, a serious practical issue associated with their employment is an appropriate selection of the model parameters, including its architecture. A common practice is experience-driven setup, heavily based on trial and error, which does not guarantee the optimum model determination and may lead to multiple problems such as poor generalization or high variance of the model predictive power with respect to the training data set selection. This paper proposes a novel modeling framework, referred to as a fully-connected regression model (FCRM), where the crucial role is played by Bayesian Optimization (BO), incorporated to determine the DNN-based model setup, including both its architecture and the hyperparameter values, in a fully automated manner. For validation, FCRM is applied to construct the model of a Minkowski Fractal-Based FSS. The efficacy of the methodology is demonstrated through comparisons with several benchmark techniques, including the DNN surrogates established using the traditional methods as well as conventional regression models. The numerical results indicate that FCRM exhibits considerably improved prediction power and reduced sensitivity to the training sample assignment.
Bağlantı
http://hdl.handle.net/20.500.12627/171925
https://doi.org/10.1109/access.2021.3063523
Koleksiyonlar
  • Makale [92796]

Creative Commons Lisansı

İstanbul Üniversitesi Akademik Arşiv Sistemi (ilgili içerikte aksi belirtilmediği sürece) Creative Commons Alıntı-GayriTicari-Türetilemez 4.0 Uluslararası Lisansı ile lisanslanmıştır.

DSpace software copyright © 2002-2016  DuraSpace
İletişim | Geri Bildirim
Theme by 
Atmire NV
 

 


Hakkımızda
Açık Erişim PolitikasıVeri Giriş Rehberleriİletişim
sherpa/romeo
Dergi Adı/ISSN || Yayıncı

Exact phrase only All keywords Any

BaşlıkbaşlayaniçerenISSN

Göz at

Tüm DSpaceBölümler & KoleksiyonlarTarihe GöreYazara GöreBaşlığa GöreKonuya GöreTürlere GöreBu KoleksiyonTarihe GöreYazara GöreBaşlığa GöreKonuya GöreTürlere Göre

Hesabım

GirişKayıt

Creative Commons Lisansı

İstanbul Üniversitesi Akademik Arşiv Sistemi (ilgili içerikte aksi belirtilmediği sürece) Creative Commons Alıntı-GayriTicari-Türetilemez 4.0 Uluslararası Lisansı ile lisanslanmıştır.

DSpace software copyright © 2002-2016  DuraSpace
İletişim | Geri Bildirim
Theme by 
Atmire NV