loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Domen Kavran ; Borut Žalik and Niko Lukač

Affiliation: Faculty of Electrical Engineering and Computer Science, University of Maribor, Koroška ulica 46, Maribor, Slovenia

Keyword(s): Time Series, Augmentation, Classification, Variational Autoencoder, Beta-VAE.

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 benchmarki ng the proposed augmentation method with the 1-nearest neighbor algorithm. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.210.143.119

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
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; ISSN 2184-433X, SciTePress, pages 15-23. DOI: 10.5220/0010749200003116

@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},
issn={2184-433X},
}

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
IS - 2184-433X
AU - Kavran, D.
AU - Žalik, B.
AU - Lukač, N.
PY - 2022
SP - 15
EP - 23
DO - 10.5220/0010749200003116
PB - SciTePress