What's Your Current Stress Level? Detection of Stress Patterns from GSR Sensor Data

Abstract

The problem of job stress is generally recognized as one of the major factors leading to a spectrum of health problems. People with certain professions, like intensive care specialists or call-center operators, and people in certain phases of their lives, like working parents with young children, are at increased risk of getting overstressed. Stress management should start far before the stress start causing illnesses. The current state of sensor technology allows to develop systems measuring physical symptoms reflecting the stress level. In this paper we (1) formulate the problem of stress identification and categorization from the sensor data stream mining perspective, (2) consider a reductionist approach for arousal identification as a drift detection task, (3) highlight the major problems of dealing with GSR data, collected from a watch-style stress measurement device in normal (i.e. in non-lab) settings, and propose simple approaches how to deal with them, and (4) discuss the lessons learnt from the conducted experimental study on real GSR data collected during the recent field study.

An Investigation of Decision Analytic Methodologies for Stress Identification

“…Zhai and Barreto [30] monitored four kinds of physiological signals --GSR, BVP, Pupil Diameter (PD), and ST --in the computer users and used three machine learning approaches, NB, SVM and Decision Tree, to classify stress types. Bakker et al [5] used GSR sensor to detect changes in the stress level by both performance monitoring-based change detection with the non-parametric test and change detection based on raw data using adaptive windowing.…”

Expressive modeling for trusted big data analytics: techniques and applications in sentiment analysis

“…a weekly summary of total (sent and received) positive, objective and negative content by relating the identified sentiments and their summaries with other events potentially related to the occurrences of stress. Information on such related events is extracted from stress measuring devices (detecting arousal based on heart rate, voiced speech or galvanic skin response measurements [18]), voice analysis, calendar data or working agendas, and analysis of facial expressions captured with a videocamera. Fig.…”

Stress Modelling Using Transfer Learning in Presence of Scarce Data

“…However, capturing what is causing an emotion change that is influenced from work-related stressors and detect the onset of stress can be quite challenging. Current methods have tried to infer stress based on physiological signals, e.g., heart-rate variability, blood pressure, body temperatures and respiration [7]. Furthermore, recent work emphasize the importance of measuring physiological signals that would help providing short-term feedback to the users in everyday activities [8].…”