학술논문
ECG Signal Classification Using a CNN-LSTM Hybrid Network
Document Type
Conference
Source
2023 2nd International Conference on Ambient Intelligence in Health Care (ICAIHC) Ambient Intelligence in Health Care (ICAIHC), 2023 2nd International Conference on. :1-6 Nov, 2023
Subject
Language
Abstract
Analysing and classifying Electrocardiogram (ECG) data can be used to diagnose cardiovascular disorders. In this regard, classification of the ECG is one of the primary topics of research in this discipline which has been increasingly supported by modern machine learning-based methods. A hybrid deep neural network was created in this study to automatically classify main ECG signals using ECG Arrythmia dataset from the MIT- BIH database. The dataset was divided into training, and test sets in proportions of 80% and 20%, respectively. The test results indicate that the proposed model shows an accuracy of 99.27% and outperformed several other popular methods found in literature.