Time Series Augmentation based on Beta-VAE to Improve Classification Performance

Domen Kavran, Borut Žalik, Niko Lukač

2022

Abstract

Classification models that provide good generalization are trained with sufficiently large datasets, but these are often not available due to restrictions and limited resources. A novel augmentation method is presented for generating synthetic time series with Beta-VAE variational autoencoder, which has ResNet-18 inspired architecture. The proposed augmentation method was tested on benchmark univariate time series datasets. For each dataset, multiple variational autoencoders were used to generate different amounts of synthetic time series samples. These were then used, along with the original train set samples, to train MiniRocket classification models. By using the proposed augmentation method, a maximum increase of 1,22% in classification accuracy was achieved on the tested datasets in comparison to baseline results, which were obtained by training only with original train sets. An increase of up to 0,81% in accuracy of simple machine learning classifiers was observed by benchmarking the proposed augmentation method with the 1-nearest neighbor algorithm.

Paper Citation

in Harvard Style

Kavran D., Žalik B. and Lukač N. (2022). Time Series Augmentation based on Beta-VAE to Improve Classification Performance. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-547-0, pages 15-23. DOI: 10.5220/0010749200003116

in Bibtex Style

@conference{icaart22,
author={Domen Kavran and Borut Žalik and Niko Lukač},
title={Time Series Augmentation based on Beta-VAE to Improve Classification Performance},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2022},
pages={15-23},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010749200003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Time Series Augmentation based on Beta-VAE to Improve Classification Performance
SN - 978-989-758-547-0
AU - Kavran D.
AU - Žalik B.
AU - Lukač N.
PY - 2022
SP - 15
EP - 23
DO - 10.5220/0010749200003116