PPG-Based Denoising (DEN-PPG-TCN-SM)
Overview
Section titled “Overview”The following table provides the latest pre-trained model for PPG-based denoising. Below we also provide additional details including training configuration, performance metrics, and downloads.
| NAME | DATASET | FS | DURATION | MODEL | PARAMS | FLOPS | METRIC |
|---|---|---|---|---|---|---|---|
| DEN-PPG-TCN-SM | Synthetic | 100Hz | 2.5s | TCN | 3.5K | 1.1M | 92.1% COS |
The model is trained on 5-second, raw PPG frames sampled at 100 Hz.
- Sensor: PPG
- Location: Wrist
- Sampling Rate: 100 Hz
- Frame Size: 5 seconds
Datasets
Section titled “Datasets”The model is trained on synthetic PPG data.
Model Performance
Section titled “Model Performance”The following table provides the performance metrics for the PPG denoising model.
| Metric | Value |
|---|---|
| MAE | 11.0% |
| MSE | 2.2% |
| COSSIM | 92.1% |
Downloads
Section titled “Downloads”| Asset | Description |
|---|---|
| configuration.json | Configuration file |
| model.keras | Keras Model file |
| model.tflite | TFLite Model file |
| metrics.json | Metrics file |