Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 3, 2025Engineering Research Express

Arrhythmias Detection using ECG with Deep Learning and Superlet Transform

View Full Paper
Ask AI
Bookmark
Share

Authors

RSRaghuwansh SinghVRVivek RanjanAGAnindita Ganguly

Discussion

Loading...

Member takes

Overview

This analysis demonstrates enhanced arrhythmia classification in patients using deep learning and time-frequency representations, suggesting strong robustness in various conditions.

Key Points

  • The VGG16 model achieved the highest accuracy of 98.73% in detecting arrhythmias, showcasing excellent performance across multiple categories.
  • Three deep learning architectures, including MobileNet, InceptionV3, and VGG16, were employed with data augmentation to address class imbalance in the dataset.
  • Superlet transform converted ECG signals into time-frequency representations, facilitating effective training of the Convolutional Neural Networks.
  • These findings highlight the potential of integrating advanced transformations and deep learning for improving arrhythmia detection in clinical settings.

Cite This Study

Singh et al. (2025) studied this question.

synapsesocial.com/papers/68e034f7f0e39f13e7fa30ddhttps://doi.org/10.1088/2631-8695/ae0f05
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Multilevel Classification and Detection of Cardiac Arrhythmias With High-Resolution Superlet Transform and Deep Convolution Neural Network2022 · 62 citations
  2. 2Cardiac arrhythmia detection using deep learning approach and time frequency representation of ECG signals2023 · 111 citations
  3. 3GSMD-SRST: Group Sparse Mode Decomposition and Superlet-Transform-Based Technique for Multilevel Classification of Cardiac Arrhythmia2024 · 27 citations
  4. 4Generalizable Hybrid Wavelet–Deep Learning Architecture for Robust Arrhythmia Detection in Wearable ECG Monitoring2025 · 4 citations
  5. 5Classification of Arrhythmia by Using Deep Learning with 2-D ECG Spectral Image Representation2020 · 241 citations