Neural network based modeling of HfO2 thin film characteristics using Latin Hypercube Sampling

Kyoung Eun Kweon, Jung Hwan Lee, Young Don Ko, Min Chang Jeong, Jae Min Myoung, Ilgu Yun

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In this paper, the neural network based modeling for electrical characteristics of the HfO2 thin films grown by metal organic molecular beam epitaxy was investigated. The accumulation capacitance and the hysteresis index are extracted to be the main responses to examine the characteristics of the HfO2 dielectric films. The input process parameters were extracted by analyzing the process conditions and the characterization of the films. X-ray diffraction was used to analyze the characteristic variation for the different process conditions. In order to build the process model, the neural network model using the error back-propagation algorithm was carried out and those initial weights and biases are selected by Latin Hypercube Sampling method. This modeling methodology can allow us to optimize the process recipes and improve the manufacturability.

Original languageEnglish
Pages (from-to)358-363
Number of pages6
JournalExpert Systems with Applications
Volume32
Issue number2
DOIs
Publication statusPublished - 2007 Feb 1

Fingerprint

Sampling
Neural networks
Thin films
Dielectric films
Backpropagation algorithms
Molecular beam epitaxy
Hysteresis
Capacitance
X ray diffraction
Metals

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Kweon, Kyoung Eun ; Lee, Jung Hwan ; Ko, Young Don ; Jeong, Min Chang ; Myoung, Jae Min ; Yun, Ilgu. / Neural network based modeling of HfO2 thin film characteristics using Latin Hypercube Sampling. In: Expert Systems with Applications. 2007 ; Vol. 32, No. 2. pp. 358-363.
@article{923456c44a24413bba0ae41a089254d2,
title = "Neural network based modeling of HfO2 thin film characteristics using Latin Hypercube Sampling",
abstract = "In this paper, the neural network based modeling for electrical characteristics of the HfO2 thin films grown by metal organic molecular beam epitaxy was investigated. The accumulation capacitance and the hysteresis index are extracted to be the main responses to examine the characteristics of the HfO2 dielectric films. The input process parameters were extracted by analyzing the process conditions and the characterization of the films. X-ray diffraction was used to analyze the characteristic variation for the different process conditions. In order to build the process model, the neural network model using the error back-propagation algorithm was carried out and those initial weights and biases are selected by Latin Hypercube Sampling method. This modeling methodology can allow us to optimize the process recipes and improve the manufacturability.",
author = "Kweon, {Kyoung Eun} and Lee, {Jung Hwan} and Ko, {Young Don} and Jeong, {Min Chang} and Myoung, {Jae Min} and Ilgu Yun",
year = "2007",
month = "2",
day = "1",
doi = "10.1016/j.eswa.2005.11.032",
language = "English",
volume = "32",
pages = "358--363",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "2",

}

Neural network based modeling of HfO2 thin film characteristics using Latin Hypercube Sampling. / Kweon, Kyoung Eun; Lee, Jung Hwan; Ko, Young Don; Jeong, Min Chang; Myoung, Jae Min; Yun, Ilgu.

In: Expert Systems with Applications, Vol. 32, No. 2, 01.02.2007, p. 358-363.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neural network based modeling of HfO2 thin film characteristics using Latin Hypercube Sampling

AU - Kweon, Kyoung Eun

AU - Lee, Jung Hwan

AU - Ko, Young Don

AU - Jeong, Min Chang

AU - Myoung, Jae Min

AU - Yun, Ilgu

PY - 2007/2/1

Y1 - 2007/2/1

N2 - In this paper, the neural network based modeling for electrical characteristics of the HfO2 thin films grown by metal organic molecular beam epitaxy was investigated. The accumulation capacitance and the hysteresis index are extracted to be the main responses to examine the characteristics of the HfO2 dielectric films. The input process parameters were extracted by analyzing the process conditions and the characterization of the films. X-ray diffraction was used to analyze the characteristic variation for the different process conditions. In order to build the process model, the neural network model using the error back-propagation algorithm was carried out and those initial weights and biases are selected by Latin Hypercube Sampling method. This modeling methodology can allow us to optimize the process recipes and improve the manufacturability.

AB - In this paper, the neural network based modeling for electrical characteristics of the HfO2 thin films grown by metal organic molecular beam epitaxy was investigated. The accumulation capacitance and the hysteresis index are extracted to be the main responses to examine the characteristics of the HfO2 dielectric films. The input process parameters were extracted by analyzing the process conditions and the characterization of the films. X-ray diffraction was used to analyze the characteristic variation for the different process conditions. In order to build the process model, the neural network model using the error back-propagation algorithm was carried out and those initial weights and biases are selected by Latin Hypercube Sampling method. This modeling methodology can allow us to optimize the process recipes and improve the manufacturability.

UR - http://www.scopus.com/inward/record.url?scp=33750435158&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750435158&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2005.11.032

DO - 10.1016/j.eswa.2005.11.032

M3 - Article

AN - SCOPUS:33750435158

VL - 32

SP - 358

EP - 363

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 2

ER -