Comparative Analysis of Machine Learning Algorithms With Advanced Feature Extraction for ECG Signal Classification

In this project, we conducted a comparative analysis of machine learning algorithms for ECG signal classification, leveraging advanced feature extraction techniques. The dataset comprises 175,729 records with features including QRS morphology, intervals, and peak measurements. We evaluated various algorithms, including Decision Trees (DT), Random Forests (RF), Logistic Regression (LR), Support Vector Machines (SVM) with Polynomial and Radial Basis Function (RBF) kernels, and K-Nearest Neighbors (KNN). Additionally, we proposed and tested advanced methods such as XGBoost and a Stacking Classifier. The results demonstrated high classification accuracy across these algorithms, with XGBoost and the Stacking Classifier achieving the highest accuracy of 0.99. This analysis highlights the effectiveness of incorporating advanced machine learning techniques and feature extraction in improving ECG signal classification, providing valuable insights for enhancing diagnostic accuracy and efficiency in cardiovascular health assessments.

Keywords: ECG Classification, machine learning algorithms, Feature Extraction, Decision Tree, Random Forest, Logistic Regression, Support Vector Machines, K Nearest Neighbors, XGBoost, Stacking Classifier.