Univariate Time Series missing data Imputation using Pix2Pix GAN

The use of data is essential for the supply of business, scientific and other processes. Often the consumption of these data is hampered when there are sample losses. Aiming to recover values representative of these losses, there are several approaches for filling them. In this paper, we propose a n...

Full description

Saved in:
Bibliographic Details
Published in:Revista IEEE América Latina 2023-03, Vol.21 (3), p.505-512
Main Authors: Morais Almeida, Mauricio, Sousa de Almeida, Joao Dallyson, Braz Junior, Geraldo, Correa Silva, Aristofanes, Cardoso de Paiva, Anselmo
Format: Article
Language:eng ; por
Subjects:
cGAN
Generative adversarial networks
Imputation
Missing data
Nanoelectromechanical systems
Recurrent neural networks
Rede Pix2Pix
Splines (mathematics)
Time Series
Time series analysis
Transforms
Visualization
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The use of data is essential for the supply of business, scientific and other processes. Often the consumption of these data is hampered when there are sample losses. Aiming to recover values representative of these losses, there are several approaches for filling them. In this paper, we propose a new method for imputation of missing data that transforms time series into an image and thus performs imputation using the conditional generative adversarial network (cGAN) pix2pix GAN. The results of ASMAPE and MAE show that the network outperforms all methods in 50% of the datasets. It was also revealed that the proposed network can learn time series features and retain some advantages over traditional methods, such as imputing the data in its entirety and exploiting spatial and temporal features for imputation.
ISSN:1548-0992
1548-0992
DOI:10.1109/TLA.2023.10068853