Mobile Stress Recognition and Relaxation Support with SmartCoping: User-Adaptive Interpretation of Physiological Stress Parameters

Reimer, Ulrich; Laurenzi, Emanuele; Maier, Edith; Ulmer, Tom Florian

doi:10.24251/hicss.2017.435

Cited by 12 publications

(3 citation statements)

References 45 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stress detection, by means of classifying these physiological responses into levels of stress via machine learning, continues to evolve and is motivated by the potential utility of continuously monitoring stress levels in real-time [12,21]. Stress detection systems have been developed for drivers in semi-urban scenarios [22,23], patients undergoing virtual reality therapy [24], individuals in working environments [25], and people that need help managing daily stress [21,[26][27][28][29][30]. Stress detection can also be applied to a variety of humanmachine interfaces (HMIs) which may monitor stress, but also infer the cognitive state of the user to adapt system functionality [31].…”

Section: B Stress Detectionmentioning

confidence: 99%

Real-Time Personalized Physiologically Based Stress Detection for Hazardous Operations

et al. 2023

View full text Add to dashboard Cite

When training for hazardous operations, real-time stress detection is an asset for optimizing task performance and reducing stress. Stress detection systems train a machine-learning model with physiological signals to classify stress levels of unseen data. Unfortunately, individual differences and the time-series nature of physiological signals limit the effectiveness of generalized models and hinder both posthoc stress detection and real-time monitoring. This study evaluated a personalized stress detection system that selects a personalized subset of features for model training. The system was evaluated post-hoc for realtime deployment. Further, traditional classifiers were assessed for error caused by indirect approximations against a benchmark, optimal probability classifier (Approximate Bayes; ABayes). Healthy participants completed a task with three levels of stressors (low, medium, high), either a complex task in virtual reality (responding to spaceflight emergency fires, n=27) or a simple laboratory-based task (N-back, n=14). Heart rate, blood pressure, electrodermal activity, and respiration were assessed. Personalized features and different interval window sizes were compared. Classification performance was compared for ABayes, support vector machine, decision tree, and random forest. The results demonstrate that a personalized model with time series intervals can classify three stress levels with high accuracy better than a generalized model. However, crossvalidation and holdout performance varied for traditional classifiers vs. ABayes, suggesting error from indirect approximations. The selected features changed with windows size and differed between tasks, but blood pressure contributed to the most prominent features. The capability to account for individual difference is a prominent advantage of personalized models, and will likely have a growing presence in future detection systems.

show abstract

Section: B Stress Detectionmentioning

confidence: 99%

Real-Time Personalized Physiologically Based Stress Detection for Hazardous Operations

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Smets et al (2018) propose the use of automatic stress detection data in combination with stress control interventions. Reimer et al (2017) consider the use of these devices relevant for the treatment of craving in patients with chemical dependency. However, as far as we could verify, we did not find any studies applying such proposals and investigating the complete cycle from stress detection, during continuous monitoring, to intervention proposals, which is a path for our research (Can et al, 2019).…”

Section: Notementioning

confidence: 99%

Dispositivos Vestíveis para monitoramento psicofisiológico do estresse: uma revisão narrativa

Rodrigues¹,

Armiliato²,

Gonçalves³

et al. 2022

RBTC

View full text Add to dashboard Cite

Wearable devices use sensors that continuously capture physiological signals and, once processed, allow the monitoring and development of interventions in various areas of health, including mental disorders. In Clinical Psychology, this type of technology can cooperate to the objective and continuous measurement of stress, as well as to generate feedback when stressful situations occur. This narrative literature review focused on these devices, presenting the main scientific data available, as well as opportunities and difficulties in implementing these devices in stress assessment and health treatments. The reviewed research indicated that it is necessary to develop more robust and theoretically based systems that integrate physiological, subjective and contextual responses to implement this type of wearable in clinical contexts. However, the accuracy already demonstrated by wearable sensors in laboratory situations and some continuous monitoring tests, reinforce that these are tools with great potential for application in clinical psychological practice.

show abstract

“…In the wellness category, the focus is on physical health, with papers on general physical activity [27] Theories used in one paper each Adoption; ANT; D&M success model/Social support theory/Social presence theory; Effectuation; Information processing theory; Protection motivation theory/Task-technology fit; Self-determination theory; Social cognitive theory of self regulation; Systems' thinking; Unified theory of acceptance; Uses and gratifications theory Theories used in two papers each Affordance; Cognitive dissonance; Design Theory, Fogg behavior*; Health belief model** Theories used in three papers each Technology acceptance model Total number of papers that cite specific theories and fitness-oriented activity [28], covering 74% of the 23 papers. Mental wellness is only considered by three papers, two focusing on stress management [29], [30], and one on mood [31]. The remaining papers were categorized as other type of wellness and focused on obesity [32] public health [33] and safe driving [34].…”

Section: Sickness Versus Wellnessmentioning

confidence: 99%

Trends in Patient Generated Data – An Initial Review

Imre¹,

Wass

2019

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

In recent years, patient-centered care has gained significant momentum in healthcare and the patient is more involved as an active participant in data generation. In this state of the art review we identify trends in patient generated data (PGD) and areas in need of further research by reviewing papers published in the health tracks of five high-ranked IS conferences. Our results suggest that research is mostly empirically grounded and primarily focuses on sickness rather than wellness issues. There is an emphasis on chronic diseases and self-management, dealing with user motivation, and a focus mostly on mobile apps. Though technology plays an important part, there is scarce problematization of and theorization on PGD. Further studies are needed that investigate the effects of PGD on patients and healthcare providers, include a wider range of issues and incorporate wearable devices more comprehensively.

show abstract

Mobile Stress Recognition and Relaxation Support with SmartCoping: User-Adaptive Interpretation of Physiological Stress Parameters

Cited by 12 publications

References 45 publications

Real-Time Personalized Physiologically Based Stress Detection for Hazardous Operations

Real-Time Personalized Physiologically Based Stress Detection for Hazardous Operations

Dispositivos Vestíveis para monitoramento psicofisiológico do estresse: uma revisão narrativa

Trends in Patient Generated Data – An Initial Review

Contact Info

Product

Resources

About