Alternative data representations are powerful tools that augment the performance of downstream models. However, there is an abundance of such representations within the machine learning toolbox, and the field lacks a comparative understanding of the suitability of each representation method. In this paper, we propose artifact detection and classification within EEG data as a testbed for profiling image-based data representations of time series data. We then evaluate eleven popular deep learning architectures on each of six commonly-used representation methods. We find that, while the choice of representation entails a choice within the tradeoff between bias and variance, certain representations are practically more effective in highlighting features which increase the signal-to-noise ratio of the data. We present our results on EEG data, and open-source our testing framework to enable future comparative analyses in this vein.
@article{arxiv.2401.05409,
title = {Image-based Data Representations of Time Series: A Comparative Analysis in EEG Artifact Detection},
author = {Aaron Maiwald and Leon Ackermann and Maximilian Kalcher and Daniel J. Wu},
journal= {arXiv preprint arXiv:2401.05409},
year = {2024}
}