Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 26, 2026

BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals
08:22

BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals

Published on: April 26, 2024

CaReS-BiNet: A multi-scale deep learning framework for ECG arrhythmia classification.

Manisha1, Karunakar A Kotegar2, Shavantrevva Bilakeri3

  • 1School of Computer Science and Engineering, REVA University, Bengaluru, Karnataka, 560064, India.

Scientific Reports
|June 23, 2026
PubMed
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

Crystallite Size Dependent Polaron Dynamics in α-Fe<sub>2</sub>O<sub>3</sub>.

The journal of physical chemistry letters·2026
Same author

Integrated epidemiology and multi-assay evidence of anthelmintic resistance in ovine gastrointestinal nematodes of Northern India.

Scientific reports·2026
Same author

Equation-of-motion coupled-cluster methods for doubly ionized and doubly electron-attached states with single, double, and triple substitutions: Theory, implementation, and benchmarks.

The Journal of chemical physics·2026
Same author

Cattle tick control in India: Current strategies and future directions.

Veterinary parasitology, regional studies and reports·2026
Same author

Comparative Study on Demographic Profile and Health Condition among Transgender and Cisgender Residing in Divergent Sectors of Urban Varanasi.

Indian journal of public health·2026
Same author

Recent advancements in magnesium-mediated organic transformations.

Chemical communications (Cambridge, England)·2026
Same journal

Correction: A method for supervoxel-wise association studies of age and other non-imaging variables from coronary computed tomography angiograms.

Scientific reports·2026
Same journal

Poly(bromophenol blue)/CoSn(OH)<sub>6</sub> cubic particles modified pencil graphite electrode for electrochemical determination of diphenhydramine.

Scientific reports·2026
Same journal

Dietary Chlorella, Spirulina, and acidifier modulate jejunal cytokine-related gene expression in broiler chickens.

Scientific reports·2026
Same journal

Perceived physical activity barriers in university students: associations with fatigue and eating behaviours.

Scientific reports·2026
Same journal

Refuge limitation structures habitat use in agricultural landscapes: evidence from Sunda pangolins.

Scientific reports·2026
Same journal

Lightweight stateless transaction verification with outsourced witness updates for UTXO blockchains.

Scientific reports·2026
See all related articles

A new deep learning model, CaReS-BiNet, effectively classifies electrocardiogram (ECG) arrhythmias by learning local and temporal features. This advanced framework demonstrates high accuracy and robustness across diverse datasets, improving automated arrhythmia detection.

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence in Medicine
  • Cardiology

Background:

  • Automated electrocardiogram (ECG) arrhythmia classification faces challenges including complex heart rhythms, imbalanced data, and poor generalization across different clinical conditions.
  • Existing methods struggle with the intricate morphological patterns and temporal dependencies inherent in ECG signals.

Purpose of the Study:

  • To develop an advanced deep learning framework, CaReS-BiNet, for robust and accurate automated ECG arrhythmia classification.
  • To address limitations in current models regarding morphological complexity, class imbalance, and cross-dataset generalization.

Main Methods:

  • Proposed CaReS-BiNet: a Convolutional and Residual Squeeze-and-Excitation Bidirectional-LSTM Network.
  • Integrated parallel multi-scale 1D convolutional branches, residual connections, Squeeze-and-Excitation channel attention, and bidirectional LSTM for joint local and temporal feature learning.

Related Experiment Videos

Last Updated: Jun 26, 2026

BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals
08:22

BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals

Published on: April 26, 2024

  • Employed Gaussian noise injection to enhance robustness against class imbalance and signal variability.

    • Main Results:

    • Achieved 98.74% accuracy, 98.73% recall, and 98.71% F1-score on the MIT-BIH Arrhythmia Database (AAMI EC57 protocol).
    • Demonstrated superior performance on the PTB Diagnostic ECG Database with 99.31% accuracy and 0.999 AUC.
    • Showcased consistent high performance (98.08% accuracy) on an additional heterogeneous ECG dataset and improved SVEB detection precision (97.99%).

    Conclusions:

    • CaReS-BiNet effectively addresses challenges in automated ECG arrhythmia classification.
    • The proposed framework exhibits superior performance, robustness, and generalization capabilities across diverse ECG datasets.
    • CaReS-BiNet represents a significant advancement for reliable automated arrhythmia detection in clinical practice.