Effect of the principal component on the PCA-based neural network model for HFO2 thin film characteristics

Young Don Ko, Moon Ho Ham, Jae Min Myoung, Ilgu Yun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Principal component analysis (PCA) based neural network models for the HfO2 thin film characteristics, such as the accumulation capacitance and the hysteresis index, grown by metal organic molecular beam epitaxy are presented. Considering the number of the principal components, the various input parameters are applied to the neural network modeling. In order to build the process model, the error back-propagation neural networks are carried out and the X-ray diffraction data are used to analyze the characteristic variation for the different process conditions and predict the response models for the characteristics. PCA is selected to reduce the dimension of the data sets. The compressed data are then used in the neural networks and those initial weights and biases are selected by Latin Hypercube sampling method. From this analysis, the effects of the principal components on the neural network models are examined.

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2007
Pages232-237
Number of pages6
Publication statusPublished - 2007 Dec 1
EventIASTED International Conference on Artificial Intelligence and Applications, AIA 2007 - Innsbruck, Austria
Duration: 2007 Feb 122007 Feb 14

Other

OtherIASTED International Conference on Artificial Intelligence and Applications, AIA 2007
CountryAustria
CityInnsbruck
Period07/2/1207/2/14

Fingerprint

Principal component analysis
Neural networks
Thin films
Backpropagation
Molecular beam epitaxy
Hysteresis
Capacitance
Sampling
X ray diffraction
Metals

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications

Cite this

Ko, Y. D., Ham, M. H., Myoung, J. M., & Yun, I. (2007). Effect of the principal component on the PCA-based neural network model for HFO2 thin film characteristics. In Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2007 (pp. 232-237)
Ko, Young Don ; Ham, Moon Ho ; Myoung, Jae Min ; Yun, Ilgu. / Effect of the principal component on the PCA-based neural network model for HFO2 thin film characteristics. Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2007. 2007. pp. 232-237
@inproceedings{95cb4238f7ca4d1088d44f6f3d1cc4b4,
title = "Effect of the principal component on the PCA-based neural network model for HFO2 thin film characteristics",
abstract = "Principal component analysis (PCA) based neural network models for the HfO2 thin film characteristics, such as the accumulation capacitance and the hysteresis index, grown by metal organic molecular beam epitaxy are presented. Considering the number of the principal components, the various input parameters are applied to the neural network modeling. In order to build the process model, the error back-propagation neural networks are carried out and the X-ray diffraction data are used to analyze the characteristic variation for the different process conditions and predict the response models for the characteristics. PCA is selected to reduce the dimension of the data sets. The compressed data are then used in the neural networks and those initial weights and biases are selected by Latin Hypercube sampling method. From this analysis, the effects of the principal components on the neural network models are examined.",
author = "Ko, {Young Don} and Ham, {Moon Ho} and Myoung, {Jae Min} and Ilgu Yun",
year = "2007",
month = "12",
day = "1",
language = "English",
isbn = "9780889866317",
pages = "232--237",
booktitle = "Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2007",

}

Ko, YD, Ham, MH, Myoung, JM & Yun, I 2007, Effect of the principal component on the PCA-based neural network model for HFO2 thin film characteristics. in Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2007. pp. 232-237, IASTED International Conference on Artificial Intelligence and Applications, AIA 2007, Innsbruck, Austria, 07/2/12.

Effect of the principal component on the PCA-based neural network model for HFO2 thin film characteristics. / Ko, Young Don; Ham, Moon Ho; Myoung, Jae Min; Yun, Ilgu.

Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2007. 2007. p. 232-237.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Effect of the principal component on the PCA-based neural network model for HFO2 thin film characteristics

AU - Ko, Young Don

AU - Ham, Moon Ho

AU - Myoung, Jae Min

AU - Yun, Ilgu

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Principal component analysis (PCA) based neural network models for the HfO2 thin film characteristics, such as the accumulation capacitance and the hysteresis index, grown by metal organic molecular beam epitaxy are presented. Considering the number of the principal components, the various input parameters are applied to the neural network modeling. In order to build the process model, the error back-propagation neural networks are carried out and the X-ray diffraction data are used to analyze the characteristic variation for the different process conditions and predict the response models for the characteristics. PCA is selected to reduce the dimension of the data sets. The compressed data are then used in the neural networks and those initial weights and biases are selected by Latin Hypercube sampling method. From this analysis, the effects of the principal components on the neural network models are examined.

AB - Principal component analysis (PCA) based neural network models for the HfO2 thin film characteristics, such as the accumulation capacitance and the hysteresis index, grown by metal organic molecular beam epitaxy are presented. Considering the number of the principal components, the various input parameters are applied to the neural network modeling. In order to build the process model, the error back-propagation neural networks are carried out and the X-ray diffraction data are used to analyze the characteristic variation for the different process conditions and predict the response models for the characteristics. PCA is selected to reduce the dimension of the data sets. The compressed data are then used in the neural networks and those initial weights and biases are selected by Latin Hypercube sampling method. From this analysis, the effects of the principal components on the neural network models are examined.

UR - http://www.scopus.com/inward/record.url?scp=38349183687&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38349183687&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:38349183687

SN - 9780889866317

SP - 232

EP - 237

BT - Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2007

ER -

Ko YD, Ham MH, Myoung JM, Yun I. Effect of the principal component on the PCA-based neural network model for HFO2 thin film characteristics. In Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2007. 2007. p. 232-237