Classification of ECG signals using deep neural networks

The electrocardiogram (ECG) is an essential tool in the field of cardiology, as it enables electrical activity heart to be measured. It involves placing electrodes on patient's skin, facilitating measurement and analysis cardiac rhythms. This non-invasive painless test provides information about heart's function helps diagnosing various conditions. classification ECG signals using deep learning techniques has garnered substantial interest recent years; tasks have exhibited promising outcomes with application models, particularly convolutional neural networks (CNNs). GoogleNet, AlexNet, ResNet Deep-CNN models are proposed this study reliable methods for accurately classifying diseases data. primary objective these predict classify prevalent ailments, encompassing arrhythmia (ARR), congestive failure (CHF), normal sinus rhythm (NSR). To achieve classification, 2D Scalogram images obtained through continuous wavelet transform (CWT) utilized input models. study's findings demonstrate that AlexNet Resnet impressive accuracy rate 96%, 95,33% 92,66%, predicting associated conditions, respectively. Overall, integration techniques, such holds promise enhancing efficiency diseases, potentially leading improved patient care outcomes.