A novel machine-learning-based framework to evaluate the effect of design parameters affected by epistemic uncertainty on the performance of textile antennas is presented in this letter. In particular, epistemic variations are characterized in the framework of possibility theory, which is combined with Bayesian optimization to accurately and efficiently perform uncertainty quantification. A suitable application example validates the proposed method.
A Machine-Learning-Based Epistemic Modeling Framework for Textile Antenna Design
Grassi F.;
2019-01-01
Abstract
A novel machine-learning-based framework to evaluate the effect of design parameters affected by epistemic uncertainty on the performance of textile antennas is presented in this letter. In particular, epistemic variations are characterized in the framework of possibility theory, which is combined with Bayesian optimization to accurately and efficiently perform uncertainty quantification. A suitable application example validates the proposed method.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
08788631.pdf
Accesso riservato
Descrizione: Articolo principale
:
Publisher’s version
Dimensione
563.71 kB
Formato
Adobe PDF
|
563.71 kB | Adobe PDF | Visualizza/Apri |
Duygu_Kan_Manuscript _Revised.pdf
accesso aperto
Descrizione: Articolo principale
:
Pre-Print (o Pre-Refereeing)
Dimensione
328.13 kB
Formato
Adobe PDF
|
328.13 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.