Skip to content

Multiclass electrocardiogram signal classification using deep learning and two-dimensional time-frequency codification

Oct 2026 · Optical Engineering + Applications · Vol 14216, pp. 142160B - 142160B-6 · 0 citations · 6 references
Engineering

TL;DR

This work presents a novel deep learning framework for multi-class arrhythmia classification based on a dual ResNet-18 architecture and confirms that the dual time-frequency codification with temporal attention works as a robust and reliable alternative for automated ECG signal classification.

Abstract

The automated classification of cardiac arrhythmias in electrocardiogram (ECG) signals is critical for cardiovascular diagnosis. Several studies focus on the classification of ECG rhythms. However this task remains a challenge, as is often affected by significant class imbalances, long-term temporal dependencies and fine morphological features. Supervised deep learning methods have shown potential for signal classification due to high performance and scalability. This work presents a novel deep learning framework for multi-class arrhythmia classification based on a dual ResNet-18 architecture. The proposed method transforms ECG segments into two-dimensional time-frequency representations using Short-Time Fourier Transform (STFT) and Continuous Wavelet Transform (CWT) processed to extract spatial features and sequential temporal self-attention mechanism. Furthermore, to mitigate class imbalance Focal Loss objective function and weighted random sampler were integrated during optimization. Experimental validation using PhysioNet MIT-BIH Arrhythmia Database demostrates effectiveness, achieving an overall classification accuracy of 97.39 % and Macro-F1 score of 0.954 across the four classes. These results confirm that the dual time-frequency codification with temporal attention works as a robust and reliable alternative for automated ECG signal classification.

View source

Similar papers

Open access Sep 2026

Hybrid Multi-Domain ECG Feature Learning with mRMR and CNN–Transformer for Cardiac Disease Classification

It is shown that multi-domain biomedical feature learning combined with attention-based deep learning can provide an effective and robust strategy for automated ECG-based cardiac disease classification, highlighting the potential of machine learning for intelligent biomedical signal analysis and computer-aided clinical...

Mohammed Alnusayri, Sara Mumtaz, Bader Aldughayfiq et al. · 0 citations
Conference Open access Sep 2026

Multi-Class Arrhythmia Classification from ECG Signals Using Deep Learning

Arrhythmias pose a serious health risk, and healthcare professionals require reliable, immediate methods to detect irregular heartbeats. This study evaluates the capacity of machine learning models—specifically Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and k-Nearest Neighbors (k-NN)—to rec...

Suraj Sharma, S. Gupta · 0 citations
Open access 2026

Advanced ECG Signal Analysis Using AM-RNN and Optimized Feature Selection for Improved Cardiac Diagnosis

This work presents novel approach for ECG signal classification through an integrated Deep Learning (DL) framework that incorporates adaptable filters that adjust based on input data resulting in superior performance in classifying numerous cardiac conditions.

K. Rema, C. P. Maheswaran, A. Anitha · 0 citations
Open access Sep 2026

A deep learning framework for arrhythmia classification: mitigating data leakage and class imbalance in ECG analysis.

Accurate and timely identification of cardiac abnormalities remains essential for reducing mortality associated with life-threatening cardiac arrhythmias. However, automated diagnostic systems often struggle with imbalanced clinical data and limited generalizability. In this work, we propose an efficient deep learning...

Sudeshna Sani, Dipra Mitra, Pallab Banerjee et al. · 0 citations
Open access Dec 2026

Classification of cardiac ECG signals using quadratic discriminant analysis for atrial fibrillation

Accurate and timely detection of atrial fibrillation (AF) is a crucial issue in avoiding the risk of serious cardiovascular complications such as stroke and heart failure. This study proposed a machine learning-based system used for automated electrocardiogram (ECG) signal classification using features derived from spe...

Wameedh Raad Fathel, Marwah Nabeel Ibrahim Al-Siraj, Maysaloon Abed Qasim et al. · 0 citations
Review Open access Sep 2026

Deep Learning for Automated Electrocardiogram Analysis: Real-Time Arrhythmia Classification Using 1D-CNN

Cardiac arrhythmias serve as important biomarkers of cardiovascular disease and therefore require continuous, accurate and timely monitoring to enable clinical intervention. Ambulatory electrocardiogram (ECG) recordings produce large volumes of data, making manual review for diagnosis labor-intensive and subject to fat...

Md. Moshiur Rahman, Md. jahangir Alam, Azalfa Zainab et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.