ECG_based Denoising (DEN-TCN-LG)
Overview
The following table provides the latest pre-trained model for ECG-based denoising. Below we also provide additional details including training configuration, performance metrics, and downloads.
| NAME | DATASET | FS | DURATION | MODEL | PARAMS | FLOPS | METRIC |
|---|---|---|---|---|---|---|---|
| DEN-TCN-LG | Synthetic, PTB-XL | 100Hz | 2.5s | TCN | 6.3K | 1.8M | 19.5 SNR |
Input
The model is trained on 5-second, raw ECG frames sampled at 100 Hz.
- Sensor: ECG
- Location: Wrist
- Sampling Rate: 100 Hz
- Frame Size: 5 seconds
Datasets
The model is trained on the following datasets:
Model Performance
The following table provides the performance metrics for the ECG-based denoising model.
| Metric | Value |
|---|---|
| MAE | 5.0% |
| MSE | 0.8% |
| COSSIM | 87.9% |
Downloads
| Asset | Description |
|---|---|
| configuration.json | Configuration file |
| model.keras | Keras Model file |
| model.tflite | TFLite Model file |
| metrics.json | Metrics file |