LDCNN: A new arrhythmia detection technique with ECG signals using a linear deep convolutional neural network
The Electrocardiogram (ECG) is an essential and widely used instrument for diagnosing cardiovascular diseases. It involves the recording of electrical signals produced by the heart using electrodes, which depict the activity of cardiac muscles during both the contraction and relaxation phases. ECG plays a crucial role in detecting irregular cardiac activity, myocardial infarctions, and various other cardiac conditions.
If you use this project please cite our paper: https://doi.org/10.14814/phy2.16182
In our research, we developed a novel one-dimensional deep neural network technique called LDCNN to identify arrhythmias from ECG signals.
In addition to the CNN model, we've implemented various machine learning techniques for the datasets.
The original datasets used are MIT-BIH Arrhythmia and PTB Diagnostic ECG that were preprocessed.
| Classes | Description | Count |
|---|---|---|
| N | Normal beat | 75011 |
| L | Left bundle branch block beat | 8071 |
| R | Right bundle branch block beat | 7255 |
| A | Atrial premature beat | 7129 |
| V | Premature ventricular contraction | 2546 |
| Classes | Description | Count |
|---|---|---|
| normal | Normal beat, Healthy controls | 4046 |
| abnormal | Myocardial infarction, Cardiomyopathy/Heart failure, Bundle branch block, Dysrhythmia, Myocardial hypertrophy, Valvular heart disease, Myocarditis, Miscellaneous | 10506 |
This project is licensed under the MIT License - see the LICENSE file for details.
© 2023 ALI BAYANI