Two-dimensional Motif Extraction from Images: A Study using an Electrocardiogram

Hanadi Aldosari, Hanadi Aldosari, Frans Coenen, Gregory Y. H. Lip, Yalin Zheng, Yalin Zheng

2022

Abstract

A mechanism using the concept of 2D motifs to classify Electrocardiogram (ECG) data is presented. The motivation is that existing techniques typically first transform ECG data into a 1D signal (waveform) format and then extract a small number of features from this format for classification purposes. The transformation into the waveform format introduces an approximation of the data, and the consequent feature selection means that only a small part of the coarsened signal is utilised. The proposed approach works directly with the image format, no transformation takes place, features (motifs) are selected by considering the entire ECG image. It is argued that this produces a better classification than that which can be achieve using the waveform format. The proposed 2D Motif extraction approach is fully described and evaluated. Good results are returned, a best accuracy 85% in comparison with a best accuracy of 70% using a comparable 1D waveform approach. An analysis is also presented with respect to the augmentation of 2D motifs with 2D discords.

Paper Citation

in Harvard Style

Aldosari H., Coenen F., Lip G. and Zheng Y. (2022). Two-dimensional Motif Extraction from Images: A Study using an Electrocardiogram. In Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2022) - Volume 1: KDIR; ISBN 978-989-758-614-9, SciTePress, pages 19-28. DOI: 10.5220/0011380500003335

in Bibtex Style

@conference{kdir22,
author={Hanadi Aldosari and Frans Coenen and Gregory Y. H. Lip and Yalin Zheng},
title={Two-dimensional Motif Extraction from Images: A Study using an Electrocardiogram},
booktitle={Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2022) - Volume 1: KDIR},
year={2022},
pages={19-28},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011380500003335},
isbn={978-989-758-614-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2022) - Volume 1: KDIR
TI - Two-dimensional Motif Extraction from Images: A Study using an Electrocardiogram
SN - 978-989-758-614-9
AU - Aldosari H.
AU - Coenen F.
AU - Lip G.
AU - Zheng Y.
PY - 2022
SP - 19
EP - 28
DO - 10.5220/0011380500003335
PB - SciTePress