YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Stress Detection Pipeline
Binary stress classifier trained on the WESAD dataset.
Model Details
- Algorithm: Random Forest / XGBoost / LightGBM
- Input: HRV, EDA, and skin temperature features
- Output: Stress probability (0.0 – 1.0)
- Dataset: WESAD (wrist signals — BVP, EDA, TEMP)
- Validation: Leave-One-Subject-Out cross-validation
Features Used
BVP → mean_hr, std_hr, rmssd, sdnn, nn50, pnn50 EDA → mean_eda, std_eda, slope_eda, peak_count, min_eda, max_eda TEMP → mean_temp, std_temp, slope_temp
Usage
This model is served via a FastAPI microservice. Input: raw sensor windows from MAX30102, GSR, and temperature sensors.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support