Stress Detection On Non-Eeg Physiolog Data

Abstract

Stress detection based on Non-EEG physiological data can be useful for monitoring drivers, pilots, workers, and other subjects, where standard EEG monitoring is unsuitable. This work uses Non-EEG database freely available from Physionet. The database contains records of heart rate, saturation of blood oxygen, motion, a conductance of skin and temperature. Model for automatic detection of stress was learned on these data. Best results were reached using a model of a decision tree with 25 features. The accuracy of the resulting model is approximately 93 %.