Adapting Transfer Learning for Accurate ECG-Based Heart Disease Classification
Journal Title: International Journal of Innovations in Science and Technology - Year 2024, Vol 6, Issue 7
Abstract
ECG signals are widely used for analyzing heart rhythms and detecting abnormalities. This study presents an experimental evaluation of a Deep CNN model for classifying ECG scalograms. Using publicly available datasets containing records from 242 patients, the study aims to classify three different cardiovascular diseases: Congestive Heart Failure (CHF), Myocardial Infarction (MI), and Coronary Artery Disease (CAD). The raw ECG signals undergo several preprocessing steps, including up-sampling, removal of noise and artifacts, and conversion into 2D images. Continuous Wavelet Transform (CWT) is applied to represent the ECG signals as 2D scalograms. The experiments in this work are conducted using a Deep CNN model and the pre-trained Inception V3 model, which achieved accuracies of 96.87% and 90.11%, respectively, on the CWT scalograms of the ECG datasets. The results were thoroughly analyzed, and the model’s performance was compared with other existing studies in the field.
Authors and Affiliations
Sania Urooj, Humera Farooq, Muhammad Farrukh Shahid
Keywords
Related Articles
- EP ID EP761766
- DOI -
- Views 17
- Downloads 0
Investigation of Feminism Trends Through Sentiment Analysis Using Machine Learning and Natural Language Processing
Introduction/Importance of Study: One of the recent changes seen in Pakistan is the growing awareness among people, to end gender discrimination and bring equality, across various spheres. “Aurat March”, is a series o...
Physio-Mechanical and Petrographic Characteristics of Granitic Rocks from the Demote Valley, Gilgit, Pakistan: Implications for Strength and Bearing Capacity
The granitic rocks of the Damote Valley (Juglote Group, Kohistan Batholith) were evaluated for their physio-mechanical and petrographic properties to assess their suitability for construction, particularly as dimension...
Advanced AI Mechanics in Unity 3D for Immersive Gameplay.A Study on Finite State Machines & Artificial Intelligence
his research explores the history and operationalization of cutting-edge AI technologies, developed for the Unity 3D video engine, in particular how Artificial Intelligence (AI), animation, and FSMs have been used in v...
A ReviewBased on Active Research Areas in Mining Software Bug Repositories: Limitations and Possible Future Trends
Introduction/ Importance of Study: Bug repository mining is a crucial research area in software engineering, analyzing software change trends, defect prediction, and evolution. It involves developing methods and tools...
Analysis of MLP, CNN,and Transfer Learning Using VGG-16 for CIFAR-10 Dataset
Artificial Neural Networks (ANN) are becoming the core domain of Artificial Intelligence. Generally, Machine learning and specifically, deep learning gained popularity in problemsolving by virtue of Multi-Layer Perceptr...