Problems of representation of electrocardiograms in convolutional neural networks

Using electrocardiograms as an example, we demonstrate the characteristic problems that arise when modeling one-dimensional signals containing inaccurate repeating pattern by means of standard convolutional networks. We show that these problems are systemic in nature. They are due to how convolution...

Full description

Saved in:
Bibliographic Details
Main Authors: Sereda, Iana, Alekseev, Sergey, Koneva, Aleksandra, Khorkin, Alexey, Osipov, Grigory
Format: Conference Proceeding
Language:English
Subjects:
Control theory
Convolution
deep learning
ECG
Electrocardiography
Image reconstruction
Interpolation
Manifolds
representation learning
Task analysis
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Using electrocardiograms as an example, we demonstrate the characteristic problems that arise when modeling one-dimensional signals containing inaccurate repeating pattern by means of standard convolutional networks. We show that these problems are systemic in nature. They are due to how convolutional networks work with composite objects, parts of which are not fixed rigidly, but have significant mobility. We also demonstrate some counterintuitive effects related to generalization in deep networks.
ISSN:2161-4407
DOI:10.1109/IJCNN48605.2020.9206607