Advanced search
1 file | 1.35 MB Add to list

Assessing the added value of context during stress detection from wearable data

Author
Organization
Project
Abstract
Background Insomnia, eating disorders, heart problems and even strokes are just some of the illnesses that reveal the negative impact of stress overload on health and well-being. Early detection of stress is therefore of utmost importance. Whereas the gold-standard for detecting stress is by means of questionnaires, more recent work uses wearable sensors to find continuous and qualitative physical markers of stress. As some physiological stress responses, e.g. increased heart rate or sweating and chills, might also occur when doing sports, a more profound approach is needed for stress detection than purely considering physiological data. Methods In this paper, we analyse the added value of context information during stress detection from wearable data. We do so by comparing the performance of models trained purely on physiological data and models trained on physiological and context data. We consider the user's activity and hours of sleep as context information, where we compare the influence of user-given context versus machine learning derived context. Results Context-aware models reach higher accuracy and lower standard deviations in comparison to the baseline (physiological) models. We also observe higher accuracy and improved weighted F1 score when incorporating machine learning predicted, instead of user-given, activities as context information. Conclusions In this paper we show that considering context information when performing stress detection from wearables leads to better performance. We also show that it is possible to move away from human labeling and rely only on the wearables for both physiology and context.
Keywords
HUMAN ACTIVITY RECOGNITION, WRIST, IDENTIFICATION, TOOL, Context-aware, Machine learning, Wearable health, Stress

Downloads

  • 8185.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 1.35 MB

Citation

Please use this url to cite or link to this publication:

MLA
Stojchevska, Marija, et al. “Assessing the Added Value of Context during Stress Detection from Wearable Data.” BMC MEDICAL INFORMATICS AND DECISION MAKING, vol. 22, no. 1, 2022, doi:10.1186/s12911-022-02010-5.
APA
Stojchevska, M., Steenwinckel, B., Van Der Donckt, J., De Brouwer, M., Goris, A., De Turck, F., … Ongenae, F. (2022). Assessing the added value of context during stress detection from wearable data. BMC MEDICAL INFORMATICS AND DECISION MAKING, 22(1). https://doi.org/10.1186/s12911-022-02010-5
Chicago author-date
Stojchevska, Marija, Bram Steenwinckel, Jonas Van Der Donckt, Mathias De Brouwer, Annelies Goris, Filip De Turck, Sofie Van Hoecke, and Femke Ongenae. 2022. “Assessing the Added Value of Context during Stress Detection from Wearable Data.” BMC MEDICAL INFORMATICS AND DECISION MAKING 22 (1). https://doi.org/10.1186/s12911-022-02010-5.
Chicago author-date (all authors)
Stojchevska, Marija, Bram Steenwinckel, Jonas Van Der Donckt, Mathias De Brouwer, Annelies Goris, Filip De Turck, Sofie Van Hoecke, and Femke Ongenae. 2022. “Assessing the Added Value of Context during Stress Detection from Wearable Data.” BMC MEDICAL INFORMATICS AND DECISION MAKING 22 (1). doi:10.1186/s12911-022-02010-5.
Vancouver
1.
Stojchevska M, Steenwinckel B, Van Der Donckt J, De Brouwer M, Goris A, De Turck F, et al. Assessing the added value of context during stress detection from wearable data. BMC MEDICAL INFORMATICS AND DECISION MAKING. 2022;22(1).
IEEE
[1]
M. Stojchevska et al., “Assessing the added value of context during stress detection from wearable data,” BMC MEDICAL INFORMATICS AND DECISION MAKING, vol. 22, no. 1, 2022.
@article{8771015,
  abstract     = {{Background Insomnia, eating disorders, heart problems and even strokes are just some of the illnesses that reveal the negative impact of stress overload on health and well-being. Early detection of stress is therefore of utmost importance. Whereas the gold-standard for detecting stress is by means of questionnaires, more recent work uses wearable sensors to find continuous and qualitative physical markers of stress. As some physiological stress responses, e.g. increased heart rate or sweating and chills, might also occur when doing sports, a more profound approach is needed for stress detection than purely considering physiological data. Methods In this paper, we analyse the added value of context information during stress detection from wearable data. We do so by comparing the performance of models trained purely on physiological data and models trained on physiological and context data. We consider the user's activity and hours of sleep as context information, where we compare the influence of user-given context versus machine learning derived context. Results Context-aware models reach higher accuracy and lower standard deviations in comparison to the baseline (physiological) models. We also observe higher accuracy and improved weighted F1 score when incorporating machine learning predicted, instead of user-given, activities as context information. Conclusions In this paper we show that considering context information when performing stress detection from wearables leads to better performance. We also show that it is possible to move away from human labeling and rely only on the wearables for both physiology and context.}},
  articleno    = {{268}},
  author       = {{Stojchevska, Marija and Steenwinckel, Bram and Van Der Donckt, Jonas and De Brouwer, Mathias and Goris, Annelies and De Turck, Filip and Van Hoecke, Sofie and Ongenae, Femke}},
  issn         = {{1472-6947}},
  journal      = {{BMC MEDICAL INFORMATICS AND DECISION MAKING}},
  keywords     = {{HUMAN ACTIVITY RECOGNITION,WRIST,IDENTIFICATION,TOOL,Context-aware,Machine learning,Wearable health,Stress}},
  language     = {{eng}},
  number       = {{1}},
  pages        = {{13}},
  title        = {{Assessing the added value of context during stress detection from wearable data}},
  url          = {{http://doi.org/10.1186/s12911-022-02010-5}},
  volume       = {{22}},
  year         = {{2022}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: