Time Series Synthesis using Generative Adversarial Networks

Bachelor Thesis (2021)
Author(s)

J.M. Dannenberg (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

A. Kunar – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Y. Chen – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Z. Zhao – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)

D.M.J. Tax – Graduation committee member (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Faculty
Electrical Engineering, Mathematics and Computer Science
URL related publication
https://gitlab.com/JanMarkD/timegan
More Info
expand_more
Publication Year
2021
Language
English
Graduation Date
02-07-2021
Awarding Institution
Delft University of Technology
Project
CSE3000 Research Project
Programme
Computer Science and Engineering
Related content

Git repository containing code used for this research. 3 different TimeGAN implementations and proposed improvements.

https://gitlab.com/JanMarkD/timegan
Faculty
Electrical Engineering, Mathematics and Computer Science
Downloads counter
588
Collections
thesis
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Generative Adversarial Networks are widely used as a tool to generate synthetic data and have previously been applied directly to time-series data. However, relying solely on the binary adversarial loss is not sufficient to ensure the model learns the temporal dynamics of the data. TimeGAN [14] introduces an additional reconstruction and supervised loss to tackle this issue. We have been able to reproduce results similar to those of the original TimeGAN paper [14], after fixing several issues in the provided implementation by the authors of TimeGAN. Furthermore, we propose two novel improvements to the existing algorithm. Firstly we updated the implementation to Tensorflow 2 to ensure compatibility across systems. Secondly by scaling the epochs over the three training phases we are able to reduce the overall training time up to 29\% and produce results equal or better compared to the benchmark.

Files

Research_Paper_10.pdf
(pdf | 3.01 Mb)
License info not available