• Home
  • Search
  • Effective Data Augmentation, Filters, and Automation Techniques for Automatic 12-Lead ECG Classification Using Deep Residual Neural Networks.
  • Cite Icon12
  • https://doi.org/10.1109/embc48229.2022.9871654Copy DOI Icon

Effective Data Augmentation, Filters, and Automation Techniques for Automatic 12-Lead ECG Classification Using Deep Residual Neural Networks.

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Automatic electrocardiogram (ECG) analysis plays a critical role in early detection and diagnosis of cardiac abnormalities and diseases. Data augmentation and automation strategies have been proposed to enhance the robustness of the machine and deep learning model for the classification of cardiac abnormalities. Here we propose 15 data augmentation and 6 filters, and an automation method using an end-to-end deep residual neural network (ResNet) model for automatic cardiac abnormalities detection from 12-lead ECG recordings. We evaluate the effectiveness of data augmentation/filtering and automation techniques using the proposed ResNet-based model on the China Physiological Signal Challenge (CPSC) dataset consisting of 9 diagnostic classes. The average F1 scores across 9 classes on the CPSC dataset trained with three data augmentation (baseline wander addition, dropout, and scaling) and a filter (sigmoid compression) were significantly higher than that without using augmentation/filters (baseline). The highest average F1 score with sigmoid compression method was significantly higher (relative improvement of 2.04 %) than the baseline while horizontal and vertical flipping augmentations were detrimental to the classification performance. Additionally, the results show that the random combination of four selected data augmentation and filter using the modified RandAugment technique provided a significantly higher average F1 score (relative improvement of 2.54 %) compared to the baseline. The proposed data augmentation, filters, and automation techniques provide an effective solution to improve the classification performance of the end-to-end deep learning model from ECG recordings without changing the model hyperparameters and structure.

Similar Papers
  • PDF
  • Research Article
  • Citations13

Data Augmentation for Deep Learning Algorithms that Perform Driver Drowsiness Detection

  • Jan 01, 2023
  • International Journal of Advanced Computer Science and Applications
  • Ghulam Masudh Mohamed +2
  • PDF
  • Research Article
  • Citations50

Rock image classification using deep residual neural network with transfer learning

  • Jan 16, 2023
  • Frontiers in Earth Science
  • Weihao Chen +3
  • Research Article
  • Citations48

Effective time-series Data Augmentation with Analytic Wavelets for bearing fault diagnosis

  • Feb 19, 2024
  • Expert Systems with Applications
  • Delanyo Kwame Bensah Kulevome +4
  • Book Chapter
  • Citations49

Data Augmentation in Training Deep Learning Models for Medical Image Analysis

  • Jan 01, 2020
  • Behnaz Abdollahi +2
  • Research Article

A simple interpolation-based data augmentation method for implicit sentiment identification

  • Jul 08, 2025
  • Scientific Reports
  • Yuxia Zhao +3
  • Research Article
  • Citations68

Effective Data Augmentation and Training Techniques for Improving Deep Learning in Plant Leaf Disease Recognition

  • Jan 25, 2021
  • Applied Science and Engineering Progress
  • Prem Enkvetchakul +1
  • Research Article
  • Citations1

Urdu Word Sense Disambiguation: Leveraging Contextual Stacked Embedding, Siamese Transformer Encoder 1DCNN-BiLSTM, and Gloss Data Augmentation

  • Apr 23, 2025
  • ACM Transactions on Asian and Low-Resource Language Information Processing
  • Anil Ahmed +3
  • Research Article
  • Citations1

Data augmentation and transfer learning efficientnetv2-s on rice leaf disease classification

  • Feb 01, 2025
  • IOP Conference Series: Earth and Environmental Science
  • Dedy Abdianto Nggego +2
  • PDF
  • Research Article
  • Citations17

Data Augmentation for Time-Series Classification: An Extensive Empirical Study and Comprehensive Survey

  • Jun 30, 2025
  • Journal of Artificial Intelligence Research
  • Zijun Gao +2
  • Research Article
  • Citations5

Guide for the application of the data augmentation approach on sets of texts in Spanish for sentiment and emotion analysis

  • Sep 26, 2024
  • PLOS ONE
  • Rodrigo Gutiérrez Benítez +3
  • Preprint Article

A Systematic Framework for Data Augmentation for Tropical Cyclone Intensity Estimation Using Deep Learning

  • Nov 27, 2024
  • Guido Ascenso +4
  • Research Article
  • Citations26

Improving the prediction of extreme wind speed events with generative data augmentation techniques

  • Nov 30, 2023
  • Renewable Energy
  • M Vega-Bayo +3
  • PDF
  • Research Article
  • Citations74

Evaluation of Data Augmentation Techniques for Facial Expression Recognition Systems

  • Nov 11, 2020
  • Electronics
  • Simone Porcu +2
  • PDF
  • Research Article

Generalizing Clustering Inferences with ML Augmentation of Ordinal Survey Data

  • Jan 22, 2024
  • Computer Science
  • Bhupendera Kumar +1
  • PDF
  • Supplementary Content
  • Citations57

Data Augmentation Techniques for Machine Learning Applied to Optical Spectroscopy Datasets in Agrifood Applications: A Comprehensive Review

  • Oct 18, 2023
  • Sensors (Basel, Switzerland)
  • Ander Gracia Moisés +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.