HYBRID CNN–XCEPTION MODEL FOR IMPROVED ECG IMAGE ANALYSIS IN HEART DISEASE DETECTION
DOI:
https://doi.org/10.62643/Keywords:
Cardiovascular diseases, ECG images, Xception, feature extraction, deep learning, convolutional neural networks (CNN), SqueezeNet, AlexNet, machine learning, Naïve Bayes, support vector machine, K-nearest neighbors, decision tree, random forest, Flask framework, SQLite, healthcare, early detection, precision, sensitivityAbstract
Cardiovascular diseases remain a major global health concern, requiring early and accurate detection for effective treatment. ECG images serve as a reliable diagnostic source, and the extended system enhances prediction accuracy by integrating advanced deep learning techniques. In this extension, the Xception model is incorporated alongside CNN, SqueezeNet, and AlexNet to achieve superior feature extraction and improved sensitivity in identifying intricate ECG patterns. Machine learning algorithms further strengthen classification based on extracted features. A user-friendly Flask framework with SQLite enables secure signup, signin, and test result retrieval, making the system more accessible for medical professionals and patients. This integrated extension significantly elevates diagnostic precision, automation, and usability in cardiovascular disease detection.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
