2-Stage PPG Segmentation (SEG-PPG-2-TCN-SM)
Overview
The following table provides the latest pre-trained model for 2-stage PPG segmentation. Below we also provide additional details including training configuration, performance metrics, and downloads.
| NAME | DATASET | FS | DURATION | # CLASSES | MODEL | PARAMS | FLOPS | METRIC |
|---|---|---|---|---|---|---|---|---|
| SEG-PPG-2-TCN-SM | Synthetic | 100Hz | 2.5s | 2 | TCN | 4K | 1.43M | 98.6% F1 |
Input
The model is trained on 2.5-second, raw ECG frames sampled at 100 Hz.
- Sensor: PPG
- Location: Wrist
- Sampling Rate: 100 Hz
- Frame Size: 2.5 seconds
Class Mapping
The model is able to segment PPG Signals into systolic and diastolic phases. The class mapping is as follows:
| Base Class | Target Class | Label |
|---|---|---|
| 6-SYSTOLIC | 0 | SYS |
| 7-DIASTOLIC | 1 | DIA |
Datasets
The model is trained on the following datasets:
Model Performance
The confusion matrix for the model is depicted below.
Downloads
| Asset | Description |
|---|---|
| configuration.json | Configuration file |
| model.keras | Keras Model file |
| model.tflite | TFLite Model file |
| metrics.json | Metrics file |