Skip to content
Log in
Sponsored AI Networking Cookbook: Practical recipes for AI-assisted network automation and development AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Conference Open access

ECG Diagnosis Using a Novel Deep Learning Method Based on Multi-Scale Convolutional and Temporal Attention Networks

Indu Sekhar Samanta Ghanashyam Sahoo P. K. Rout
Sep 2026 · 2026 International Conference on Intelligent Computing and Sustainable Innovations in Technology (IC-SIT) · pp. 1-6 · 0 citations · 10 references

Abstract

Early detection and classification of heart diseases is much dependant upon ECG signal analysis. So conventional and classical machine dependent methods fails to lead up the discovering of many complex temporal dependencies as well as refinement morphological variations of the ECG signals. To this end, in this work, we present a novel deep learning structure for this task, based on the combination of Multi-Scale Convolutional Neural Network (MSCNN) and Temporal Attention Network (TAN), aiming to achieve better feature-representation capability, and prove a further pursuit of higher diagnosis accuracy on this task. This Model was validated on the MIT-BIH Arrhythmia Database to compare with other methods based on CNN and LSTM, obtaning higher accuracy of overall classifying arrhythmia—reaching a rate of 99.5%. The proposed framework can be applied in real-time ECG monitoring systems for accurate cardiac diagnosis.

DOI Semantic Scholar
Read PDF

Similar papers

Open access Sep 2026

A deep hybrid CNN–BiGRU model for inter-patient ECG beat classification

The study provides proof of concept for using hybrid deep learning architectures in automated ECG analysis and indicates that combining convolutional neural networks with bidirectional gated recurrent units improves the representation of both morphological and temporal ECG characteristics.

Iruvaram Sudhir Chaitanya Kumar, B. S. Naick · 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
Conference Open access Sep 2026

ECG-Based Cardiac Arrhythmia Detection Using a Lightweight Attention-Augmented CNN-BiLSTM Network

A lightweight Convolutional Neural Network and Bidirectional Long-Term Memory (CNN-BiLSTM) architecture is presented to help identify multi-class ECG arrhythmias and demonstrates clinically measurable QRS activation, paving the way for wearable monitoring platforms with interpretable and deployable cardiac AI.

Bersha Kumari, A. Dhaka, A. Sharma et al. · 0 citations
Open access Sep 2026

Hybrid Deep Learning Structure for Classifying ECG Signals Using CNN, MVO-Based Feature Selection, and SVM

A proposed hybrid framework that combines a convolutional neural network (CNN) with a support vector machine (SVM) with a support vector machine (SVM) for ECG signal classification outperformed existing techniques and significantly improved accuracy.

S. Ahmed, Serwan A. Mohammed, Ahmed Kh. Mohammed · 0 citations
Open access Sep 2026

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

Cardiovascular disease diagnosis requires accurate and timely analysis of electrocardiogram (ECG) signals to support reliable clinical decision-making. However, ECG signals are inherently non-stationary, exhibit substantial inter-patient variability, and may share similar morphological patterns across different cardiac...

Mohammed Alnusayri, Sara Mumtaz, Bader Aldughayfiq 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.