A regularization approach for identifying cumulative lagged effects in smart health applications

Karthik Srinivasan, Faiz Currim, Sudha Ram, Casey Lindberg, Esther Sternberg, Perry Skeath, Bijan Najafi, Javad Razjouyan, Hyo Ki Lee, Matthias R. Mehl, Davida Herzl, Reuben Herzl, Melissa Lunden, Nicole Goebel, Scott Andrews, Brian Gilligan, Judith Heerwagen, Kevin Kampschroer, Kelli Canada

Research output: ResearchConference contribution

Abstract

Recent development1 of wearable sensor technologies have made it possible to capture concurrent data streams for ambient environment and instantaneous physiological stress response at a fine granularity. Characterizing the delay in physiological stress response time to each environment stimulus is as important as capturing the magnitude of the effect. In this paper, we discuss and evaluate a new regularization-based statistical method to determine the ideal lagged effect of five environmental factors - carbon dioxide, temperature, relative humidity, atmospheric pressure and noise levels on instantaneous stress response. Using this method, we infer that the first four environment variables have a cumulative lagged effect, of approximately 60 minutes, on stress response whereas noise level has an instantaneous effect on stress response. The proposed transformations to inputs result in models with better fit and predictive performance. This study not only informs the field of environment-wellbeing research about the cumulative lagged effects of the specified environmental factors, but also proposes a new method for determining optimal feature transformation in similar smart health studies.

LanguageEnglish (US)
Title of host publicationDH 2017 - Proceedings of the 2017 International Conference on Digital Health
PublisherAssociation for Computing Machinery
Pages99-103
Number of pages5
VolumePart F128634
ISBN (Electronic)9781450352499
DOIs
StatePublished - Jul 2 2017
Event7th International Conference on Digital Health, DH 2017 - London, United Kingdom
Duration: Jul 2 2017Jul 5 2017

Other

Other7th International Conference on Digital Health, DH 2017
CountryUnited Kingdom
CityLondon
Period7/2/177/5/17

Fingerprint

Atmospheric pressure
Atmospheric humidity
Statistical methods
Carbon dioxide
Health
Temperature
Wearable sensors

Keywords

  • Cumulative lag
  • Environment-wellbeing studies
  • Heart rate variability
  • Indoor environment quality
  • Smart health

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Srinivasan, K., Currim, F., Ram, S., Lindberg, C., Sternberg, E., Skeath, P., ... Canada, K. (2017). A regularization approach for identifying cumulative lagged effects in smart health applications. In DH 2017 - Proceedings of the 2017 International Conference on Digital Health (Vol. Part F128634, pp. 99-103). Association for Computing Machinery. DOI: 10.1145/3079452.3079503

A regularization approach for identifying cumulative lagged effects in smart health applications. / Srinivasan, Karthik; Currim, Faiz; Ram, Sudha; Lindberg, Casey; Sternberg, Esther; Skeath, Perry; Najafi, Bijan; Razjouyan, Javad; Lee, Hyo Ki; Mehl, Matthias R.; Herzl, Davida; Herzl, Reuben; Lunden, Melissa; Goebel, Nicole; Andrews, Scott; Gilligan, Brian; Heerwagen, Judith; Kampschroer, Kevin; Canada, Kelli.

DH 2017 - Proceedings of the 2017 International Conference on Digital Health. Vol. Part F128634 Association for Computing Machinery, 2017. p. 99-103.

Research output: ResearchConference contribution

Srinivasan, K, Currim, F, Ram, S, Lindberg, C, Sternberg, E, Skeath, P, Najafi, B, Razjouyan, J, Lee, HK, Mehl, MR, Herzl, D, Herzl, R, Lunden, M, Goebel, N, Andrews, S, Gilligan, B, Heerwagen, J, Kampschroer, K & Canada, K 2017, A regularization approach for identifying cumulative lagged effects in smart health applications. in DH 2017 - Proceedings of the 2017 International Conference on Digital Health. vol. Part F128634, Association for Computing Machinery, pp. 99-103, 7th International Conference on Digital Health, DH 2017, London, United Kingdom, 7/2/17. DOI: 10.1145/3079452.3079503
Srinivasan K, Currim F, Ram S, Lindberg C, Sternberg E, Skeath P et al. A regularization approach for identifying cumulative lagged effects in smart health applications. In DH 2017 - Proceedings of the 2017 International Conference on Digital Health. Vol. Part F128634. Association for Computing Machinery. 2017. p. 99-103. Available from, DOI: 10.1145/3079452.3079503
Srinivasan, Karthik ; Currim, Faiz ; Ram, Sudha ; Lindberg, Casey ; Sternberg, Esther ; Skeath, Perry ; Najafi, Bijan ; Razjouyan, Javad ; Lee, Hyo Ki ; Mehl, Matthias R. ; Herzl, Davida ; Herzl, Reuben ; Lunden, Melissa ; Goebel, Nicole ; Andrews, Scott ; Gilligan, Brian ; Heerwagen, Judith ; Kampschroer, Kevin ; Canada, Kelli. / A regularization approach for identifying cumulative lagged effects in smart health applications. DH 2017 - Proceedings of the 2017 International Conference on Digital Health. Vol. Part F128634 Association for Computing Machinery, 2017. pp. 99-103
@inbook{dfaa1463ebf544f09b3eaa4422e4b146,
title = "A regularization approach for identifying cumulative lagged effects in smart health applications",
abstract = "Recent development1 of wearable sensor technologies have made it possible to capture concurrent data streams for ambient environment and instantaneous physiological stress response at a fine granularity. Characterizing the delay in physiological stress response time to each environment stimulus is as important as capturing the magnitude of the effect. In this paper, we discuss and evaluate a new regularization-based statistical method to determine the ideal lagged effect of five environmental factors - carbon dioxide, temperature, relative humidity, atmospheric pressure and noise levels on instantaneous stress response. Using this method, we infer that the first four environment variables have a cumulative lagged effect, of approximately 60 minutes, on stress response whereas noise level has an instantaneous effect on stress response. The proposed transformations to inputs result in models with better fit and predictive performance. This study not only informs the field of environment-wellbeing research about the cumulative lagged effects of the specified environmental factors, but also proposes a new method for determining optimal feature transformation in similar smart health studies.",
keywords = "Cumulative lag, Environment-wellbeing studies, Heart rate variability, Indoor environment quality, Smart health",
author = "Karthik Srinivasan and Faiz Currim and Sudha Ram and Casey Lindberg and Esther Sternberg and Perry Skeath and Bijan Najafi and Javad Razjouyan and Lee, {Hyo Ki} and Mehl, {Matthias R.} and Davida Herzl and Reuben Herzl and Melissa Lunden and Nicole Goebel and Scott Andrews and Brian Gilligan and Judith Heerwagen and Kevin Kampschroer and Kelli Canada",
year = "2017",
month = "7",
doi = "10.1145/3079452.3079503",
volume = "Part F128634",
pages = "99--103",
booktitle = "DH 2017 - Proceedings of the 2017 International Conference on Digital Health",
publisher = "Association for Computing Machinery",

}

TY - CHAP

T1 - A regularization approach for identifying cumulative lagged effects in smart health applications

AU - Srinivasan,Karthik

AU - Currim,Faiz

AU - Ram,Sudha

AU - Lindberg,Casey

AU - Sternberg,Esther

AU - Skeath,Perry

AU - Najafi,Bijan

AU - Razjouyan,Javad

AU - Lee,Hyo Ki

AU - Mehl,Matthias R.

AU - Herzl,Davida

AU - Herzl,Reuben

AU - Lunden,Melissa

AU - Goebel,Nicole

AU - Andrews,Scott

AU - Gilligan,Brian

AU - Heerwagen,Judith

AU - Kampschroer,Kevin

AU - Canada,Kelli

PY - 2017/7/2

Y1 - 2017/7/2

N2 - Recent development1 of wearable sensor technologies have made it possible to capture concurrent data streams for ambient environment and instantaneous physiological stress response at a fine granularity. Characterizing the delay in physiological stress response time to each environment stimulus is as important as capturing the magnitude of the effect. In this paper, we discuss and evaluate a new regularization-based statistical method to determine the ideal lagged effect of five environmental factors - carbon dioxide, temperature, relative humidity, atmospheric pressure and noise levels on instantaneous stress response. Using this method, we infer that the first four environment variables have a cumulative lagged effect, of approximately 60 minutes, on stress response whereas noise level has an instantaneous effect on stress response. The proposed transformations to inputs result in models with better fit and predictive performance. This study not only informs the field of environment-wellbeing research about the cumulative lagged effects of the specified environmental factors, but also proposes a new method for determining optimal feature transformation in similar smart health studies.

AB - Recent development1 of wearable sensor technologies have made it possible to capture concurrent data streams for ambient environment and instantaneous physiological stress response at a fine granularity. Characterizing the delay in physiological stress response time to each environment stimulus is as important as capturing the magnitude of the effect. In this paper, we discuss and evaluate a new regularization-based statistical method to determine the ideal lagged effect of five environmental factors - carbon dioxide, temperature, relative humidity, atmospheric pressure and noise levels on instantaneous stress response. Using this method, we infer that the first four environment variables have a cumulative lagged effect, of approximately 60 minutes, on stress response whereas noise level has an instantaneous effect on stress response. The proposed transformations to inputs result in models with better fit and predictive performance. This study not only informs the field of environment-wellbeing research about the cumulative lagged effects of the specified environmental factors, but also proposes a new method for determining optimal feature transformation in similar smart health studies.

KW - Cumulative lag

KW - Environment-wellbeing studies

KW - Heart rate variability

KW - Indoor environment quality

KW - Smart health

UR - http://www.scopus.com/inward/record.url?scp=85025475310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85025475310&partnerID=8YFLogxK

U2 - 10.1145/3079452.3079503

DO - 10.1145/3079452.3079503

M3 - Conference contribution

VL - Part F128634

SP - 99

EP - 103

BT - DH 2017 - Proceedings of the 2017 International Conference on Digital Health

PB - Association for Computing Machinery

ER -