Towards a Minimalistic Stress Classification Method Based on HRV
Roswitha Duwenbeck, Elsa Andrea Kirchner
In The Sixteenth International Conference on Advances in Human-oriented and Personalized Mechanisms, Technologies, and Services CENTRIC 2023, (CENTRIC-2023), 13.11.-17.11.2023, Valencia, ThinkMind, Nov/2023.

Abstract :

Stress is a feeling of emotional and physical tension, that poses as a risk factor in many diseases, for example the nervous, musculoskeletal, cardiovascular or gastrointestinal system. Fast and easy detection could be a first step in order to help people manage their stress-levels. This paper depicts an ongoing work in the domain of stress prediction with Heart Rate Variability related features by classifying two different levels on the Stress-Predict Dataset. The performance of different clas- sifiers was tested with Leave-One-Subject-Out Cross Validation and compared to each other. The best performance was reached with the Aggregated Mondrian Forest Classifier and a mean balanced accuracy of 97.87%.

Keywords :

Heart rate variability; stress prediction; Machine Learning

Files:

2023_-_Towards_a_Minimalistic_Stress_Classification_Method_based_on_HRV.pdf

Links:

https://www.thinkmind.org/index.php?view=article&articleid=centric_2023_2_30_30022
https://www.iaria.org/conferences2023/ProgramCENTRIC23.html
http://


© DFKI GmbH
last updated 28.02.2023
to top