Firefighter Stress Monitoring: Model Quality and Explainability
- Resource Type
- Conference
- Authors
- Buecher, Janik; Soujon, Mischa; Sierro, Nicolas; Weiss, Jonas; Michel, Bruno
- Source
- 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) Engineering in Medicine & Biology Society (EMBC), 2022 44th Annual International Conference of the IEEE. :4653-4657 Jul, 2022
- Subject
- Bioengineering
Training
Analytical models
Biological system modeling
Machine learning
Multilayer perceptrons
Feature extraction
Data models
- Language
- ISSN
- 2694-0604
A cognitive and physical stress co-classification effort started with acquisition of a training dataset and generation of machine learning models from 17 heart rate variability parameters. Accuracy was improved with multilayer perceptron models and tested on 85 firefighters in a cage maze. A specific platform acquired a dataset with better label accuracy providing a second model. Feature importance and model performance were assessed using the cage maze data. A SHAP analysis provided the basis for the model comparison and feature important assessment. Conclusions were drawn on best time windows, feature selection, and model hyperparameters.