Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Nov 12, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Automated ECG classification using a non-local convolutional block attention module.

Jikuo Wang¹, Xu Qiao¹, Changchun Liu¹

¹Department of Biomedical Engineering, School of Control Science and Engineering, Shandong University, Jinan 250061, China.

Computer Methods and Programs in Biomedicine

|March 18, 2021

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Synthesis and Optoelectronic Properties of Branched Polystyrene-<i>graft</i>-Polyfluorene Copolymers.

Micromachines·2026

Same author

Specific transformation of steviol at unactivated C-H sites by microorganism and mining of key P450 enzymes.

Natural product research·2026

Same author

Single-nucleotide variant profiling in liquid biopsy with RECO-Cas.

Science advances·2026

Same author

Age modulates estradiol's dual role in hepatocellular carcinoma recurrence after ablation: A prospective observational study.

iScience·2026

Same author

Synthesis, Electron Transport Behavior, and Enhanced Blue Light Stability of Polyfluorene-Poly(Methyl Methacrylate) Diblock Copolymers.

Micromachines·2026

Same author

SDS-CRISPR for Single-Nucleotide Variant Detection.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

This study introduces a new deep learning model for classifying electrocardiogram (ECG) heartbeats. The novel approach enhances accuracy by better utilizing spatial, channel, and temporal ECG signal features, improving diagnostic reliability.

Area of Science:

Cardiology
Artificial Intelligence
Signal Processing

Background:

Deep learning, particularly convolutional neural networks (CNNs) and recurrent neural networks (RNNs), has advanced ECG analysis.
Existing models often overlook the varying importance of local and global features and their inter-relationships within ECG signals.

Purpose of the Study:

To propose a novel deep learning model, the convolutional neural network with a non-local convolutional block attention module (NCBAM), for automated ECG heart classification.
To address limitations in current models by effectively integrating spatial, channel, and temporal ECG data features.

Main Methods:

A 33-layer CNN architecture was developed to extract initial spatial and channel features from preprocessed ECG signals.
A non-local attention module (NCBAM) was integrated to capture long-range dependencies across spatial and channel axes.

Keywords:

Cardiac arrhythmias, Cardiovascular diseases, Convolutional neural network, Attention mechanism, Non-local convolutional block attention module ECG

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Nov 12, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

A learned matrix was employed to fuse spatial, channel, and temporal information, optimizing the contribution of each feature type.

Main Results:

The proposed NCBAM model achieved a high average F1 score of 0.9664 on the MIT-BIH arrhythmia database.
On the PTB-XL ECG database, the model obtained an AUC of 0.9314 and an Fmax score of 0.8507.
Significant improvements were observed compared to state-of-the-art attention mechanisms in ECG heartbeat classification.

Conclusions:

The NCBAM model demonstrates superior performance in classifying ECG heartbeats.
The findings confirm the reliability and efficiency of the proposed method for automated ECG analysis.
This approach offers a promising advancement in leveraging deep learning for cardiovascular diagnostics.