FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3133644787> ?p ?o ?g. }

• W3133644787 endingPage "38410" @default.
• W3133644787 startingPage "38396" @default.
• W3133644787 abstract "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." @default.
• W3133644787 created "2021-03-15" @default.
• W3133644787 creator A5025661679 @default.
• W3133644787 creator A5040400589 @default.
• W3133644787 creator A5048110175 @default.
• W3133644787 creator A5078029025 @default.
• W3133644787 date "2021-01-01" @default.
• W3133644787 modified "2023-10-16" @default.
• W3133644787 title "Accurate Modeling of Frequency Selective Surfaces Using Fully-Connected Regression Model With Automated Architecture Determination and Parameter Selection Based on Bayesian Optimization" @default.
• W3133644787 cites W1601448640 @default.
• W3133644787 cites W1643588265 @default.
• W3133644787 cites W1678356000 @default.
• W3133644787 cites W1964357740 @default.
• W3133644787 cites W1966154590 @default.
• W3133644787 cites W1969513389 @default.
• W3133644787 cites W1972403778 @default.
• W3133644787 cites W1988790447 @default.
• W3133644787 cites W1990245077 @default.
• W3133644787 cites W1990299300 @default.
• W3133644787 cites W1994808771 @default.
• W3133644787 cites W2006753895 @default.
• W3133644787 cites W2014094736 @default.
• W3133644787 cites W2024500182 @default.
• W3133644787 cites W2026697677 @default.
• W3133644787 cites W2033439576 @default.
• W3133644787 cites W2042538541 @default.
• W3133644787 cites W2043575154 @default.
• W3133644787 cites W2045850563 @default.
• W3133644787 cites W2047161049 @default.
• W3133644787 cites W2049475976 @default.
• W3133644787 cites W2056483754 @default.
• W3133644787 cites W2061665904 @default.
• W3133644787 cites W2075053184 @default.
• W3133644787 cites W2076139225 @default.
• W3133644787 cites W2082639035 @default.
• W3133644787 cites W2084715774 @default.
• W3133644787 cites W2088794999 @default.
• W3133644787 cites W2089097797 @default.
• W3133644787 cites W2098103715 @default.
• W3133644787 cites W2111456897 @default.
• W3133644787 cites W2121607567 @default.
• W3133644787 cites W2122765624 @default.
• W3133644787 cites W2124338373 @default.
• W3133644787 cites W2148482797 @default.
• W3133644787 cites W2149723649 @default.
• W3133644787 cites W2182772625 @default.
• W3133644787 cites W2185326129 @default.
• W3133644787 cites W2211722460 @default.
• W3133644787 cites W2292788343 @default.
• W3133644787 cites W2315411895 @default.
• W3133644787 cites W2342717714 @default.
• W3133644787 cites W2415594836 @default.
• W3133644787 cites W2477563955 @default.
• W3133644787 cites W2498714552 @default.
• W3133644787 cites W2547578938 @default.
• W3133644787 cites W2550246949 @default.
• W3133644787 cites W2551471669 @default.
• W3133644787 cites W2581581211 @default.
• W3133644787 cites W2616478507 @default.
• W3133644787 cites W2616617448 @default.
• W3133644787 cites W2616881109 @default.
• W3133644787 cites W2734777338 @default.
• W3133644787 cites W2754890795 @default.
• W3133644787 cites W2761685889 @default.
• W3133644787 cites W2767046001 @default.
• W3133644787 cites W2767406310 @default.
• W3133644787 cites W2767668368 @default.
• W3133644787 cites W2768264879 @default.
• W3133644787 cites W2772089072 @default.
• W3133644787 cites W2781475111 @default.
• W3133644787 cites W2789250272 @default.
• W3133644787 cites W2800471157 @default.
• W3133644787 cites W2883849272 @default.
• W3133644787 cites W2885733767 @default.
• W3133644787 cites W2892156163 @default.
• W3133644787 cites W2894120608 @default.
• W3133644787 cites W2905528277 @default.
• W3133644787 cites W2910112947 @default.
• W3133644787 cites W2914150517 @default.
• W3133644787 cites W2928285259 @default.
• W3133644787 cites W2940302004 @default.
• W3133644787 cites W2940764815 @default.
• W3133644787 cites W2942218624 @default.
• W3133644787 cites W2945024965 @default.
• W3133644787 cites W2947199931 @default.
• W3133644787 cites W2954277823 @default.
• W3133644787 cites W2954451442 @default.
• W3133644787 cites W2955304216 @default.
• W3133644787 cites W2964253307 @default.
• W3133644787 cites W2965161941 @default.
• W3133644787 cites W2968784654 @default.
• W3133644787 cites W2979230174 @default.
• W3133644787 cites W2980845540 @default.
• W3133644787 cites W3006108715 @default.
• W3133644787 cites W3023183603 @default.
• W3133644787 cites W3045004532 @default.
• W3133644787 cites W3098913817 @default.
• W3133644787 cites W3101647584 @default.

• next