Graph Neural Networks for Topological Feature Extraction in ECG Classification
Applications of Artificial Intelligence and Neural Systems to Data Science, Smart Innovation, Systems and Technologies, Springer, pages 17-27 (proceedings of WIRN 2022)
Published online on , 20 citations on Google Scholar
In short
The paper proposes three ways to extract topological features from ECG signals and classify heartbeats with a graph isomorphism network, a type of graph neural network. On the PTB Diagnostic dataset the three methods reached 99.38%, 98.76% and 91.93% accuracy.
Cite
@inbook{Zeinalipour_2023,
title={Graph Neural Networks for Topological Feature Extraction in ECG Classification},
ISBN={9789819935925},
ISSN={2190-3026},
url={http://dx.doi.org/10.1007/978-981-99-3592-5_2},
DOI={10.1007/978-981-99-3592-5_2},
booktitle={Applications of Artificial Intelligence and Neural Systems to Data Science},
publisher={Springer Nature Singapore},
author={Zeinalipour, Kamyar and Gori, Marco},
year={2023},
pages={17–27}
}