Surface Roughness Determination Using Spectral Correlations of Scattered Intensities and an Artificial Neural Network Technique

Kuniaki Yoshitomi, Akira Ishimaru, Jeng Neng Hwang, Jei Shuan Chen

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

An artificial neural network (ANN) technique is applied to the determination of the rms height and the correlation distance of one-dimensional rough surfaces. The surface is illuminated by a beam wave, and the intensity correlations of the scattered wave at two wavelengths in the specular and backward directions are used to determine the roughness parameters. Scattered intensity correlations calculated by Monte Carlo simulations are used to train the ANN, and two methods, the explicit inversion method and the iterative constrained inversion method, are used to perform the inversion. The inversion values are compared with the target values, and the iterative constrained method is shown to give smaller errors, but requires longer computer CPU time.

Original languageEnglish
Pages (from-to)498-502
Number of pages5
JournalIEEE Transactions on Antennas and Propagation
Volume41
Issue number4
DOIs
Publication statusPublished - Jan 1 1993

Fingerprint

Surface roughness
Neural networks
Program processors
Wavelength
Monte Carlo simulation

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Surface Roughness Determination Using Spectral Correlations of Scattered Intensities and an Artificial Neural Network Technique. / Yoshitomi, Kuniaki; Ishimaru, Akira; Hwang, Jeng Neng; Chen, Jei Shuan.

In: IEEE Transactions on Antennas and Propagation, Vol. 41, No. 4, 01.01.1993, p. 498-502.

Research output: Contribution to journalArticle

@article{eef4402943fa441585bebd2ffa89cc2b,
title = "Surface Roughness Determination Using Spectral Correlations of Scattered Intensities and an Artificial Neural Network Technique",
abstract = "An artificial neural network (ANN) technique is applied to the determination of the rms height and the correlation distance of one-dimensional rough surfaces. The surface is illuminated by a beam wave, and the intensity correlations of the scattered wave at two wavelengths in the specular and backward directions are used to determine the roughness parameters. Scattered intensity correlations calculated by Monte Carlo simulations are used to train the ANN, and two methods, the explicit inversion method and the iterative constrained inversion method, are used to perform the inversion. The inversion values are compared with the target values, and the iterative constrained method is shown to give smaller errors, but requires longer computer CPU time.",
author = "Kuniaki Yoshitomi and Akira Ishimaru and Hwang, {Jeng Neng} and Chen, {Jei Shuan}",
year = "1993",
month = "1",
day = "1",
doi = "10.1109/8.220983",
language = "English",
volume = "41",
pages = "498--502",
journal = "IEEE Transactions on Antennas and Propagation",
issn = "0018-926X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Surface Roughness Determination Using Spectral Correlations of Scattered Intensities and an Artificial Neural Network Technique

AU - Yoshitomi, Kuniaki

AU - Ishimaru, Akira

AU - Hwang, Jeng Neng

AU - Chen, Jei Shuan

PY - 1993/1/1

Y1 - 1993/1/1

N2 - An artificial neural network (ANN) technique is applied to the determination of the rms height and the correlation distance of one-dimensional rough surfaces. The surface is illuminated by a beam wave, and the intensity correlations of the scattered wave at two wavelengths in the specular and backward directions are used to determine the roughness parameters. Scattered intensity correlations calculated by Monte Carlo simulations are used to train the ANN, and two methods, the explicit inversion method and the iterative constrained inversion method, are used to perform the inversion. The inversion values are compared with the target values, and the iterative constrained method is shown to give smaller errors, but requires longer computer CPU time.

AB - An artificial neural network (ANN) technique is applied to the determination of the rms height and the correlation distance of one-dimensional rough surfaces. The surface is illuminated by a beam wave, and the intensity correlations of the scattered wave at two wavelengths in the specular and backward directions are used to determine the roughness parameters. Scattered intensity correlations calculated by Monte Carlo simulations are used to train the ANN, and two methods, the explicit inversion method and the iterative constrained inversion method, are used to perform the inversion. The inversion values are compared with the target values, and the iterative constrained method is shown to give smaller errors, but requires longer computer CPU time.

UR - http://www.scopus.com/inward/record.url?scp=0027577324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027577324&partnerID=8YFLogxK

U2 - 10.1109/8.220983

DO - 10.1109/8.220983

M3 - Article

AN - SCOPUS:0027577324

VL - 41

SP - 498

EP - 502

JO - IEEE Transactions on Antennas and Propagation

JF - IEEE Transactions on Antennas and Propagation

SN - 0018-926X

IS - 4

ER -