Efficient Learning Dataset Generation and Data Selection Using Generative Adversarial Network and GSVD-Based Linear Discriminant Analysis 


Vol. 45,  No. 7, pp. 1166-1173, Jul.  2020
10.7840/kics.2020.45.7.1166


PDF
  Abstract

In this paper, we propose a dataset generation and screening method through generative adversarial neural networks (GAN) and GSVD based linear discriminant analysis (LDA) in situations where a large amount of learning datasets are required for the deep learning applications. We first generate the fake dataset through the GAN and include them to the unified training dataset together with real measurement data samples. To reduce the dimension of the unified dataset, GSVD based LDA is applied and the data samples are selected in the reduced-dimensional space to train the deep neural network. We develop the deep neural network for the character recognition and evaluate the recognition accuracy to verify the validity of the proposed dataset generation and data selection methods.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

Y. Yang, Y. Hong, J. Park, "Efficient Learning Dataset Generation and Data Selection Using Generative Adversarial Network and GSVD-Based Linear Discriminant Analysis," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 7, pp. 1166-1173, 2020. DOI: 10.7840/kics.2020.45.7.1166.

[ACM Style]

Yunji Yang, Yong-gi Hong, and Jaehyun Park. 2020. Efficient Learning Dataset Generation and Data Selection Using Generative Adversarial Network and GSVD-Based Linear Discriminant Analysis. The Journal of Korean Institute of Communications and Information Sciences, 45, 7, (2020), 1166-1173. DOI: 10.7840/kics.2020.45.7.1166.

[KICS Style]

Yunji Yang, Yong-gi Hong, Jaehyun Park, "Efficient Learning Dataset Generation and Data Selection Using Generative Adversarial Network and GSVD-Based Linear Discriminant Analysis," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 7, pp. 1166-1173, 7. 2020. (https://doi.org/10.7840/kics.2020.45.7.1166)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880