Uncertainty analysis on FDTD computation with artificial neural networkCitation formats

  • Authors:
  • Runze Hu
  • Vikass Monebhurrun
  • Ryutaro Himeno
  • Hideo Yokota
  • Fumie Costen

Standard

Uncertainty analysis on FDTD computation with artificial neural network. / Hu, Runze; Monebhurrun, Vikass; Himeno, Ryutaro; Yokota, Hideo; Costen, Fumie.

In: IEEE Antennas and Propagation Magazine, 17.10.2021.

Research output: Contribution to journalArticlepeer-review

Harvard

Hu, R, Monebhurrun, V, Himeno, R, Yokota, H & Costen, F 2021, 'Uncertainty analysis on FDTD computation with artificial neural network', IEEE Antennas and Propagation Magazine.

APA

Hu, R., Monebhurrun, V., Himeno, R., Yokota, H., & Costen, F. (Accepted/In press). Uncertainty analysis on FDTD computation with artificial neural network. IEEE Antennas and Propagation Magazine.

Vancouver

Hu R, Monebhurrun V, Himeno R, Yokota H, Costen F. Uncertainty analysis on FDTD computation with artificial neural network. IEEE Antennas and Propagation Magazine. 2021 Oct 17.

Author

Hu, Runze ; Monebhurrun, Vikass ; Himeno, Ryutaro ; Yokota, Hideo ; Costen, Fumie. / Uncertainty analysis on FDTD computation with artificial neural network. In: IEEE Antennas and Propagation Magazine. 2021.

Bibtex

@article{b2cbe8f83f7d4be6ae46735d162d76eb,
title = "Uncertainty analysis on FDTD computation with artificial neural network",
abstract = "The artificial neural network (ANN) has appeared as a potential alternative for uncertainty quantification (UQ) in the finite difference time domain (FDTD) computation. It is applied to build a surrogate model for the compute-intensive FDTD simulation and to bypass the numerous simulations required for UQ. However, when the surrogate model utilizes the ANN, a considerable number of data is generally required for high accuracy and generating such large quantities of data becomes computationally prohibitive. To address this drawback, a number of adaptations for ANN are proposed which additionally improves the accuracy of the ANN in UQ for the FDTD computation while maintaining a low computational cost. The proposed algorithm is tested for application in bioelectromagnetics and considerable speed-up, as well as improved accuracy of UQ, is observed compared to traditional methods such as the non-intrusive polynomial chaos method.",
author = "Runze Hu and Vikass Monebhurrun and Ryutaro Himeno and Hideo Yokota and Fumie Costen",
year = "2021",
month = oct,
day = "17",
language = "English",
journal = "IEEE Antennas and Propagation Magazine",
issn = "1045-9243",
publisher = "IEEE Computer Society ",

}

RIS

TY - JOUR

T1 - Uncertainty analysis on FDTD computation with artificial neural network

AU - Hu, Runze

AU - Monebhurrun, Vikass

AU - Himeno, Ryutaro

AU - Yokota, Hideo

AU - Costen, Fumie

PY - 2021/10/17

Y1 - 2021/10/17

N2 - The artificial neural network (ANN) has appeared as a potential alternative for uncertainty quantification (UQ) in the finite difference time domain (FDTD) computation. It is applied to build a surrogate model for the compute-intensive FDTD simulation and to bypass the numerous simulations required for UQ. However, when the surrogate model utilizes the ANN, a considerable number of data is generally required for high accuracy and generating such large quantities of data becomes computationally prohibitive. To address this drawback, a number of adaptations for ANN are proposed which additionally improves the accuracy of the ANN in UQ for the FDTD computation while maintaining a low computational cost. The proposed algorithm is tested for application in bioelectromagnetics and considerable speed-up, as well as improved accuracy of UQ, is observed compared to traditional methods such as the non-intrusive polynomial chaos method.

AB - The artificial neural network (ANN) has appeared as a potential alternative for uncertainty quantification (UQ) in the finite difference time domain (FDTD) computation. It is applied to build a surrogate model for the compute-intensive FDTD simulation and to bypass the numerous simulations required for UQ. However, when the surrogate model utilizes the ANN, a considerable number of data is generally required for high accuracy and generating such large quantities of data becomes computationally prohibitive. To address this drawback, a number of adaptations for ANN are proposed which additionally improves the accuracy of the ANN in UQ for the FDTD computation while maintaining a low computational cost. The proposed algorithm is tested for application in bioelectromagnetics and considerable speed-up, as well as improved accuracy of UQ, is observed compared to traditional methods such as the non-intrusive polynomial chaos method.

M3 - Article

JO - IEEE Antennas and Propagation Magazine

JF - IEEE Antennas and Propagation Magazine

SN - 1045-9243

ER -