Activity-Aware Mental Stress Detection Using Physiological Sensors

Abstract

Abstract. Continuous stress monitoring may help users better understand their stress patterns and provide physicians with more reliable data for interventions. Previously, studies on mental stress detection were limited to a laboratory environment where participants generally rested in a sedentary position. However, it is impractical to exclude the effects of physical activity while developing a pervasive stress monitoring application for everyday use. The physiological responses caused by mental stress can be masked by variations due to physical activity. We present an activity-aware mental stress detection scheme. Electrocardiogram (ECG), galvanic skin response (GSR), and accelerometer data were gathered from 20 participants across three activities: sitting, standing, and walking. For each activity, we gathered baseline physiological measurements and measurements while users were subjected to mental stressors. The activity information derived from the accelerometer enabled us to achieve 92.4% accuracy of mental stress classification for 10-fold cross validation and 80.9% accuracy for between-subjects classification.

Stress Detection Using Wearable Physiological Sensors

“…Stress is a natural reaction of the human body to an outside perturbing factor. The physiological responses to stress are correlated with variations in heart rate, blood volume pulse, skin temperature, pupil dilation, electro-dermal activity [18,17,13]. Stress may have beneficial effects on fighting the stress factor, like increasing reflexes, but it was determined that long term stress is correlated with various health problems like depression and premature ageing [16], [9].…”

Fine-Grained Prediction of Cognitive Workload in a Modern Working Environment by Utilizing Short-Term Physiological Parameters

“…As emphasized by (Sun et al, 2012) care has to be taken if heart rate is chosen as a predictor, because it is possibly influenced by means of physical activity. However, during our experiment the subjects were monitored by the experimenter, thus we can exclude physical activity as confounding factor.…”

“…Additionally, (Sun et al, 2012) focused on short term signal processing, which enables the detection of short term stress events. They presented remarkable results with a classification accuracy of up to 95 %.…”

“…With this compromise, we fit with the classification accuracies and keep the window size short at the same time. Nevertheless, due to the overlap, we obtain a new estimate every 10 s. The chosen window length is by 20 s smaller compared to related work from (Sun et al, 2012) or (Karthikeyan et al, 2013).…”

Enabling Real-Time In-Situ Processing of Ubiquitous Mobile-Application Workflows

“…Applications employ these tasks at different stages of their workflows (the dataprocessing chain) so to extract actionable knowledge from the raw data acquired in the field. Stress detection and stress-level rating: Figure 2(b) depicts the workflow for stress detection and stress-level rating [14], [15], which uses vital-sign data acquired from biomedical as well as kinematic sensors. Stage 1 of this workflow is purely composed of data-analysis tasks, whereas Stages 2 and 3 are composed of data-manipulation or decisionmaking tasks.…”