A Pilot Study on the Use of Generative Adversarial Networks for Data Augmentation of Time Series

Morizet, Nicolas; Rizzato, Matteo; Grimbert, David; Luta, George

doi:10.3390/ai3040047

Open AccessBrief Report

A Pilot Study on the Use of Generative Adversarial Networks for Data Augmentation of Time Series

by

Nicolas Morizet

^1,†,

Matteo Rizzato

^1,†,

David Grimbert

¹ and

George Luta

^2,*

¹

Advestis, 69 Boulevard Haussmann, 75008 Paris, France

²

Department of Biostatistics, Bioinformatics and Biomathematics, Georgetown University, 4000 Reservoir Rd NW, Washington, DC 20057, USA

^*

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

AI 2022, 3(4), 789-795; https://doi.org/10.3390/ai3040047

Submission received: 29 July 2022 / Revised: 11 September 2022 / Accepted: 20 September 2022 / Published: 26 September 2022

(This article belongs to the Special Issue Feature Papers for AI)

Download

Browse Figure

Versions Notes

Abstract

Data augmentation is needed to use Deep Learning methods for the typically small time series datasets. There is limited literature on the evaluation of the performance of the use of Generative Adversarial Networks for time series data augmentation. We describe and discuss the results of a pilot study that extends a recent evaluation study of two families of data augmentation methods for time series (i.e., transformation-based methods and pattern-mixing methods), and provide recommendations for future work in this important area of research.

Keywords: data augmentation; deep learning; generative adversarial networks; time series

Share and Cite

MDPI and ACS Style

Morizet, N.; Rizzato, M.; Grimbert, D.; Luta, G. A Pilot Study on the Use of Generative Adversarial Networks for Data Augmentation of Time Series. AI 2022, 3, 789-795. https://doi.org/10.3390/ai3040047

AMA Style

Morizet N, Rizzato M, Grimbert D, Luta G. A Pilot Study on the Use of Generative Adversarial Networks for Data Augmentation of Time Series. AI. 2022; 3(4):789-795. https://doi.org/10.3390/ai3040047

Chicago/Turabian Style

Morizet, Nicolas, Matteo Rizzato, David Grimbert, and George Luta. 2022. "A Pilot Study on the Use of Generative Adversarial Networks for Data Augmentation of Time Series" AI 3, no. 4: 789-795. https://doi.org/10.3390/ai3040047

APA Style

Morizet, N., Rizzato, M., Grimbert, D., & Luta, G. (2022). A Pilot Study on the Use of Generative Adversarial Networks for Data Augmentation of Time Series. AI, 3(4), 789-795. https://doi.org/10.3390/ai3040047

Article Menu

A Pilot Study on the Use of Generative Adversarial Networks for Data Augmentation of Time Series

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI