QASIS: a QoC aware stress identification system using machine learning approach

Abstract

Stress is a serious health problem that affects a large part of humanity. Early stress detection helps preventing stress-related health problems. The Internet of Things (IoT) plays an important role in healthcare monitoring. In this paper, we present an automatic stress detection system (QASIS), to increases the effectiveness and efficiency of healthcare system providing services. QASIS benefits of emerging wearable physiological sensors, specifically, electromyograph (EMG), electrocardiogram (ECG), and nasal/oral airow, to monitors physical, cognitive and emotional stress. Our system uses an Extra Trees Classifier to achieve expected results in the areas like car driving. We also illustrate how the reliability of the contextual information represented by QoC metrics, can enhance the accuracy of the stress detection system. We conducted a stress detection experiment with twenty-six subjects. We confirmed that the proposed system could effectively detect stress, based on the measured breathing rate and the electrical activity of the heart and the muscles.