ECG signal analysis has prime importance in the detection and diagnosis of several cardiac anomalies. The present work proposes an automated scheme for ECG classification via a One-Dimensional Convolutional Neural Network (1D CNN), which can help efficiently and reliably diagnose heart conditions. The dataset stored in the pickle (.pk1) format consisted of raw ECG waveforms, which have undergone preprocessing and were used for training and evaluation. The 1D CNN model extracts significant temporal features from the ECG signals, allowing it to differentiate normal and abnormal heart rhythms, including arrhythmias. The increase in diagnostic accuracy provided by the deep learning approach is due to convolutional layers being used for feature extraction and classification. Our results show that the proposed model can classify the ECGs with high accuracy and thus can be considered as a possible tool for real-time monitoring of the heart and early detection of cardiovascular diseases. This work helps facilitate AI-driven medical diagnostics and serves as a dependable and automated approach to the ECG signal analysis.
Keywords: component, formatting, style, styling
