UC Irvine

Monitoring stress levels has become an important part of healthcare systems for physical and mental illnesses. However, current stress monitoring systems have failed to gather personal data in an everyday context. The current state of sensor technology allows us to develop systems measuring the physiological signals, which reflect stress by wearable devices. Therefore, we propose a stress monitoring system that provides an objective daily healthcare based on personal physiological signals: electrocardiogram (ECG), photoplethysmogram (PPG), and galvanic skin response (GSR). We use the wearable devices, Shimmer3 ECG, Shimmer3 GSR+ and Empatica E4 Wristband, to monitor stress ubiquitously. We perform controlled stress experiments on 17 participants and the system successfully detects stress with a 94.55% accuracy for 10-fold cross-validation and an 85.71% accuracy for subject-wise cross-validation. In everyday settings, the system assesses stress with an 81.82% accuracy. We also examine whether motion artifacts affect stress assessment.