Wearable affect and stress recognition: A review

Schmidt, Philip; Reiss, Attila; Duerichen, Robert; Laerhoven, Kristof Van

doi:10.48550/arxiv.1811.08854

Cited by 13 publications

(15 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inertial sensors such as accelerometer and gyroscope are commonly used in human activity recognition [ 63 ]. In HTC Vive set, spatial localization is possible using two IR base stations, which beam signals to the headset and controllers.…”

Section: Methods and Analysismentioning

confidence: 99%

Usability Testing of Virtual Reality Applications—The Pilot Study

Kamińska

Zwoliński

Laska-Leśniewicz

2022

Sensors

View full text Add to dashboard Cite

The need for objective data-driven usability testing of VR applications is becoming more tangible with the rapid development of numerous VR applications and their increased accessibility. Traditional methods of testing are too time and resource consuming and might provide results that are highly subjective. Thus, the aim of this article is to explore the possibility of automation of usability testing of VR applications by using objective features such as HMD built-in head and hands tracking, EEG sensor, video recording, and other measurable parameters in addition to automated analysis of subjective data provided in questionnaires. For this purpose, a simple VR application was created which comprised relatively easy tasks that did not generate stress for the users. Fourteen volunteers took part in the study and their signals were monitored to acquire objective automated data. At the same time the observer was taking notes of subjects’ behaviour, and their subjective opinions about the experience were recorded in a post-experiment questionnaire. The results acquired from signal monitoring and questionnaires were juxtaposed with observation and post-interview results to confirm the validity and efficacy of automated usability testing. The results were very promising, proving that automated usability testing of VR applications is potentially achievable.

show abstract

Section: Methods and Analysismentioning

confidence: 99%

Usability Testing of Virtual Reality Applications—The Pilot Study

Kamińska

Zwoliński

Laska-Leśniewicz

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The use of sensors, software tools, and signal processing methods to explore complex biological signals related to stress has increased with recent advances in computational methods and concurrent, widespread adoption of consumer electronics. 62 Although a broad range of systems influence cardiac performance and functions, the ANS is the most prominent. 63 Like some of the aforementioned biomarkers, pulse and heart rate variability (HRV) can be used as proxies for fluctuations in the ANS in response to external and internal stressors.…”

Section: Digital Measurement Of Biomarkersmentioning

confidence: 99%

Measurement of Human Stress: A Multidimensional Approach

Dorsey¹,

Scherer²,

Eckhoff³

et al. 2022

View full text Add to dashboard Cite

Stress is a multidimensional construct that comprises exposure to events, perceptions of stress, and physiological responses to stress. Research consistently demonstrates a strong association between stress and a myriad of physical and mental health concerns, resulting in a pervasive and interdisciplinary agreement on the importance of investigating the relationship between stress and health. Developing a holistic understanding of stress requires assessment of the three domains vital to the study of stress: (1) the presence of environmental stressors, (2) psychological and biological reactions to stressors, and (3) the length of time over which the stressor or stress response occurs. Research into all three domains requires multiple methods. Self-reports allow for subjective evaluations of stress that illuminate the duration and severity of the psychological response to stressors. Biomarkers, in turn, capture a more-objective measure of stress and create a deeper understanding of the biological response to chronic and acute stress. Finally, the use of digital biomarkers allows for further exploration of the physiological fluctuations caused by stress by measuring the changes occurring at the same time as the stressor. Future research on stress and health should favor a multidimensional approach that creates a triangulated picture of stress, drawing from each of the three aforementioned method groups.

show abstract

“…This study measured EDA, heart rate and eye-blink rate using biofeedback sensors as subtle physiological cues are known to indicate a change in stress states [13]. EDA data was collected through the monitoring device, and heart rate was recorded through the chest-strap monitor.…”

Section: E Physiology-based Stress Classification and Predictionmentioning

confidence: 99%

“…Physiological signals exhibit unique characteristics during stress, hence the extraction of features and classification of stress levels from signals are gaining enormous popularity and importance currently. Sharma and Gedeon [13] investigated the binary classification of stress based on EDA signals via an artificial neural network (ANN) model, with a similar modeling structure implemented using EDA, ECG and respiration rate as parameters for ANN input [33]. Machine learning algorithms are also developed with automatic feature selection procedures to recognize complex patterns behind physiological signals [34].…”

Section: Introductionmentioning

confidence: 99%

“…Support Vector Machines (SVMs) with non-linear kernels in combination with physiological signals identify emotional states in emotional rooms [35], museums [36]and racing games [37] via VR techniques. Other classifiers, such as k-Nearest Neighbor (kNN), Random Forest (RF) and Linear Discriminant Analysis (LDA) are also applied to detect stress levels, through either binary classification or multi-class classification [13], [31], [38], [39].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Stress Recognition Using Supervised Learning Classifiers by Interactive Virtual Reality Scenes

Tao

Huang

Shen

et al. 2022

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Virtual reality (VR) technology offers a great opportunity to explore stress disorder therapies. We created a VR stress training system, which incorporates three highly interactive stressful scenes to elicit stress, and demonstrate the concurrent variations between physiological data (heart rate, electrodermal activity and eye-blink rate) and self-reported stress ratings through a self-designed customized perceived stress questionnaire (SSAI) and wearable devices. Several supervised learning models were rigorously applied to automate stress recognition. Our findings include the evaluations of the VR system by computing Cronbach's alpha (α=0.72) and Kaiser-Meyer-Olkin (KMO) coefficient (η=0.78) through a retrospective survey, which were subsequently confirmed as reliable on four aspects (sense of presence, sense of space, sense of immersion and sense of reality) via factor analysis. Additionally, we demonstrate the effectiveness of physiology-based stress level classification (no stress, low stress and high stress) and continuous SSAI score prediction, with accuracy reaching 0.742 by bagging ensemble learning model and goodness-of-fit reaching 0.44 via multivariate stepwise regression. This study provides detailed insight regarding the effect of objective physiological measures on the validation of subjective self-ratings under a novel complex VR stress training system, which stimulates the further investigations of stress disorder recognition and treatment.

show abstract

Wearable affect and stress recognition: A review

Cited by 13 publications

References 0 publications

Usability Testing of Virtual Reality Applications—The Pilot Study

Usability Testing of Virtual Reality Applications—The Pilot Study

Measurement of Human Stress: A Multidimensional Approach

Automated Stress Recognition Using Supervised Learning Classifiers by Interactive Virtual Reality Scenes

Contact Info

Product

Resources

About