Removal of subject-dependent and activity-dependent variation in physiological measures of stress

F. Alamudun, J. Choi, R. Gutierrez-Osuna, H. Khan, Beena Ahmed

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

The ability to monitor stress levels in daily life can provide valuable information to patients and their caretakers, help identify potential stressors, determine appropriate interventions, and monitor their effectiveness. Wearable sensor technology makes it now possible to measure non-invasively a number of physiological correlates of stress, from skin conductance to heart rate variability. These measures, however, show large individual differences and are also correlated with the physical activity of the subject. In this paper, we propose two multivariate signal processing techniques to reduce the effect of both forms of interference. The first method is an unsupervised technique that removes any systematic variation that is orthogonal to the dependent variable, in this case physiological stress. In contrast, the second method is a supervised technique that first projects the data into a subspace that emphasizes these systematic variations, and then removes them from the data. The two methods were validated on an experimental dataset containing physiological recordings from multiple subjects performing physical and/or mental activities. When compared to z-score normalization, the standard method for removing individual differences, our methods can reduce stress prediction errors by as much as 50%.

Original languageEnglish
Title of host publication2012 6th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, PervasiveHealth 2012
Pages115-122
Number of pages8
DOIs
Publication statusPublished - 2012
Event2012 6th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, PervasiveHealth 2012 - San Diego, CA, United States
Duration: 21 May 201224 May 2012

Other

Other2012 6th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, PervasiveHealth 2012
CountryUnited States
CitySan Diego, CA
Period21/5/1224/5/12

Fingerprint

Individuality
Physiological Stress
Aptitude
Heart Rate
Exercise
Technology
Skin
Datasets

Keywords

  • Electrodermal activity
  • Heart rate variability
  • Individual differences
  • Mental stress
  • Noise cancellation
  • Wearable sensors

ASJC Scopus subject areas

  • Health Informatics
  • Health Information Management

Cite this

Alamudun, F., Choi, J., Gutierrez-Osuna, R., Khan, H., & Ahmed, B. (2012). Removal of subject-dependent and activity-dependent variation in physiological measures of stress. In 2012 6th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, PervasiveHealth 2012 (pp. 115-122) https://doi.org/10.4108/icst.pervasivehealth.2012.248722

Removal of subject-dependent and activity-dependent variation in physiological measures of stress. / Alamudun, F.; Choi, J.; Gutierrez-Osuna, R.; Khan, H.; Ahmed, Beena.

2012 6th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, PervasiveHealth 2012. 2012. p. 115-122.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Alamudun, F, Choi, J, Gutierrez-Osuna, R, Khan, H & Ahmed, B 2012, Removal of subject-dependent and activity-dependent variation in physiological measures of stress. in 2012 6th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, PervasiveHealth 2012. pp. 115-122, 2012 6th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, PervasiveHealth 2012, San Diego, CA, United States, 21/5/12. https://doi.org/10.4108/icst.pervasivehealth.2012.248722
Alamudun F, Choi J, Gutierrez-Osuna R, Khan H, Ahmed B. Removal of subject-dependent and activity-dependent variation in physiological measures of stress. In 2012 6th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, PervasiveHealth 2012. 2012. p. 115-122 https://doi.org/10.4108/icst.pervasivehealth.2012.248722
Alamudun, F. ; Choi, J. ; Gutierrez-Osuna, R. ; Khan, H. ; Ahmed, Beena. / Removal of subject-dependent and activity-dependent variation in physiological measures of stress. 2012 6th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, PervasiveHealth 2012. 2012. pp. 115-122
@inproceedings{19d71d4ba75d4386aa3e730d918dddcd,
title = "Removal of subject-dependent and activity-dependent variation in physiological measures of stress",
abstract = "The ability to monitor stress levels in daily life can provide valuable information to patients and their caretakers, help identify potential stressors, determine appropriate interventions, and monitor their effectiveness. Wearable sensor technology makes it now possible to measure non-invasively a number of physiological correlates of stress, from skin conductance to heart rate variability. These measures, however, show large individual differences and are also correlated with the physical activity of the subject. In this paper, we propose two multivariate signal processing techniques to reduce the effect of both forms of interference. The first method is an unsupervised technique that removes any systematic variation that is orthogonal to the dependent variable, in this case physiological stress. In contrast, the second method is a supervised technique that first projects the data into a subspace that emphasizes these systematic variations, and then removes them from the data. The two methods were validated on an experimental dataset containing physiological recordings from multiple subjects performing physical and/or mental activities. When compared to z-score normalization, the standard method for removing individual differences, our methods can reduce stress prediction errors by as much as 50{\%}.",
keywords = "Electrodermal activity, Heart rate variability, Individual differences, Mental stress, Noise cancellation, Wearable sensors",
author = "F. Alamudun and J. Choi and R. Gutierrez-Osuna and H. Khan and Beena Ahmed",
year = "2012",
doi = "10.4108/icst.pervasivehealth.2012.248722",
language = "English",
isbn = "9781936968435",
pages = "115--122",
booktitle = "2012 6th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, PervasiveHealth 2012",

}

TY - GEN

T1 - Removal of subject-dependent and activity-dependent variation in physiological measures of stress

AU - Alamudun, F.

AU - Choi, J.

AU - Gutierrez-Osuna, R.

AU - Khan, H.

AU - Ahmed, Beena

PY - 2012

Y1 - 2012

N2 - The ability to monitor stress levels in daily life can provide valuable information to patients and their caretakers, help identify potential stressors, determine appropriate interventions, and monitor their effectiveness. Wearable sensor technology makes it now possible to measure non-invasively a number of physiological correlates of stress, from skin conductance to heart rate variability. These measures, however, show large individual differences and are also correlated with the physical activity of the subject. In this paper, we propose two multivariate signal processing techniques to reduce the effect of both forms of interference. The first method is an unsupervised technique that removes any systematic variation that is orthogonal to the dependent variable, in this case physiological stress. In contrast, the second method is a supervised technique that first projects the data into a subspace that emphasizes these systematic variations, and then removes them from the data. The two methods were validated on an experimental dataset containing physiological recordings from multiple subjects performing physical and/or mental activities. When compared to z-score normalization, the standard method for removing individual differences, our methods can reduce stress prediction errors by as much as 50%.

AB - The ability to monitor stress levels in daily life can provide valuable information to patients and their caretakers, help identify potential stressors, determine appropriate interventions, and monitor their effectiveness. Wearable sensor technology makes it now possible to measure non-invasively a number of physiological correlates of stress, from skin conductance to heart rate variability. These measures, however, show large individual differences and are also correlated with the physical activity of the subject. In this paper, we propose two multivariate signal processing techniques to reduce the effect of both forms of interference. The first method is an unsupervised technique that removes any systematic variation that is orthogonal to the dependent variable, in this case physiological stress. In contrast, the second method is a supervised technique that first projects the data into a subspace that emphasizes these systematic variations, and then removes them from the data. The two methods were validated on an experimental dataset containing physiological recordings from multiple subjects performing physical and/or mental activities. When compared to z-score normalization, the standard method for removing individual differences, our methods can reduce stress prediction errors by as much as 50%.

KW - Electrodermal activity

KW - Heart rate variability

KW - Individual differences

KW - Mental stress

KW - Noise cancellation

KW - Wearable sensors

UR - http://www.scopus.com/inward/record.url?scp=84864986600&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864986600&partnerID=8YFLogxK

U2 - 10.4108/icst.pervasivehealth.2012.248722

DO - 10.4108/icst.pervasivehealth.2012.248722

M3 - Conference contribution

AN - SCOPUS:84864986600

SN - 9781936968435

SP - 115

EP - 122

BT - 2012 6th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, PervasiveHealth 2012

ER -