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)