The ECG Heartbeat Categorization Dataset consists of two collections of heartbeat signals obtained from well-known datasets: the MIT-BIH Arrhythmia Dataset and the PTB Diagnostic ECG Database. This dataset is commonly used for heartbeat classification tasks and is suitable for training deep neural networks.
The dataset contains preprocessed and segmented electrocardiogram (ECG) signals representing different types of heartbeats, including normal cases and those affected by arrhythmias and myocardial infarction. It has been widely utilized to explore the capabilities of deep neural network architectures and investigate transfer learning techniques.
- Number of Samples: 109,446
- Number of Categories: 5
- Sampling Frequency: 125Hz
- Data Source: Physionet's MIT-BIH Arrhythmia Dataset
- Classes: ['N': 0, 'S': 1, 'V': 2, 'F': 3, 'Q': 4]
- Number of Samples: 14,552
- Number of Categories: 2
- Sampling Frequency: 125Hz
- Data Source: Physionet's PTB Diagnostic Database
Please note that the dataset is labeled, and each segment corresponds to a specific heartbeat.
If you would like more information or to access the original data sources, you can refer to Physionet's MIT-BIH Arrhythmia Dataset and PTB Diagnostic Database.
Disclaimer: The dataset description provided here is based on the information available and might not be exhaustive.
- The project is available as a notebook file in .ipynb format
- The project is available in .py format
you can clone to this repository and pull the project into your own system.
Note: Feel free to contribute to this project.
Reach me at Linkedin and Instagram: My LinkedIn Profile My Instagram Profile