Towards stress detection in real-life scenarios using wearable sensors: Normalization factor to reduce variability in stress physiology

Bishal Lamichhane; Ulf Großekathöfer; Giuseppina Schiavone; Pierluigi Casale

doi:10.1007/978-3-319-49655-9_34

Towards stress detection in real-life scenarios using wearable sensors: Normalization factor to reduce variability in stress physiology

Bishal Lamichhane, Ulf Großekathöfer, Giuseppina Schiavone, Pierluigi Casale

Houston Methodist

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

16 Scopus citations

Abstract

Wearable physiological sensors offer possibilities for the development of continuous stress detection models. Such models need to address the inter-individual and intra-individual differences in stress physiology. In this paper we propose and evaluate a normalization factor, StressResponse Factor (SRF), to address such differences. SRF is computed using physiological features and the corresponding stress level at a reference point. The proposed normalization factor is evaluated in a dataset obtained from a free-living study with 10 participants, where each participant was monitored for 5 days during their working hours using different physiological sensors. We obtain an average reduction of mean squared error by up to 32% in models with SRF compared to the models without SRF.

Original language	English (US)
Title of host publication	eHealth 360° - International Summit on eHealth, Revised Selected Papers
Editors	Laszlo Bokor, Frank Hopfgartner, Kostas Giokas
Publisher	Springer Verlag
Pages	259-270
Number of pages	12
ISBN (Print)	9783319496542
DOIs	https://doi.org/10.1007/978-3-319-49655-9_34
State	Published - 2017
Event	International Summit on eHealth 360°, 2016 - Budapest, Hungary Duration: Jun 14 2016 → Jun 16 2016

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume	181 LNICST
ISSN (Print)	1867-8211

Conference

Conference	International Summit on eHealth 360°, 2016
Country/Territory	Hungary
City	Budapest
Period	6/14/16 → 6/16/16

Keywords

Machine learning
Physiology normalization
Stress detection
Wearable sensors

ASJC Scopus subject areas

Computer Networks and Communications

Access to Document

10.1007/978-3-319-49655-9_34

Cite this

Lamichhane, B., Großekathöfer, U., Schiavone, G., & Casale, P. (2017). Towards stress detection in real-life scenarios using wearable sensors: Normalization factor to reduce variability in stress physiology. In L. Bokor, F. Hopfgartner, & K. Giokas (Eds.), eHealth 360° - International Summit on eHealth, Revised Selected Papers (pp. 259-270). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 181 LNICST). Springer Verlag. https://doi.org/10.1007/978-3-319-49655-9_34

Towards stress detection in real-life scenarios using wearable sensors: Normalization factor to reduce variability in stress physiology. / Lamichhane, Bishal; Großekathöfer, Ulf; Schiavone, Giuseppina et al.
eHealth 360° - International Summit on eHealth, Revised Selected Papers. ed. / Laszlo Bokor; Frank Hopfgartner; Kostas Giokas. Springer Verlag, 2017. p. 259-270 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 181 LNICST).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lamichhane, B, Großekathöfer, U, Schiavone, G & Casale, P 2017, Towards stress detection in real-life scenarios using wearable sensors: Normalization factor to reduce variability in stress physiology. in L Bokor, F Hopfgartner & K Giokas (eds), eHealth 360° - International Summit on eHealth, Revised Selected Papers. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, vol. 181 LNICST, Springer Verlag, pp. 259-270, International Summit on eHealth 360°, 2016, Budapest, Hungary, 6/14/16. https://doi.org/10.1007/978-3-319-49655-9_34

Lamichhane B, Großekathöfer U, Schiavone G, Casale P. Towards stress detection in real-life scenarios using wearable sensors: Normalization factor to reduce variability in stress physiology. In Bokor L, Hopfgartner F, Giokas K, editors, eHealth 360° - International Summit on eHealth, Revised Selected Papers. Springer Verlag. 2017. p. 259-270. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST). doi: 10.1007/978-3-319-49655-9_34

Lamichhane, Bishal ; Großekathöfer, Ulf ; Schiavone, Giuseppina et al. / Towards stress detection in real-life scenarios using wearable sensors : Normalization factor to reduce variability in stress physiology. eHealth 360° - International Summit on eHealth, Revised Selected Papers. editor / Laszlo Bokor ; Frank Hopfgartner ; Kostas Giokas. Springer Verlag, 2017. pp. 259-270 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST).

@inproceedings{f37b05ed557b4feca895d6d94a3ae64d,

title = "Towards stress detection in real-life scenarios using wearable sensors: Normalization factor to reduce variability in stress physiology",

abstract = "Wearable physiological sensors offer possibilities for the development of continuous stress detection models. Such models need to address the inter-individual and intra-individual differences in stress physiology. In this paper we propose and evaluate a normalization factor, StressResponse Factor (SRF), to address such differences. SRF is computed using physiological features and the corresponding stress level at a reference point. The proposed normalization factor is evaluated in a dataset obtained from a free-living study with 10 participants, where each participant was monitored for 5 days during their working hours using different physiological sensors. We obtain an average reduction of mean squared error by up to 32\% in models with SRF compared to the models without SRF.",

keywords = "Machine learning, Physiology normalization, Stress detection, Wearable sensors",

author = "Bishal Lamichhane and Ulf Gro{\ss}ekath{\"o}fer and Giuseppina Schiavone and Pierluigi Casale",

note = "Publisher Copyright: {\textcopyright} ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2017.; International Summit on eHealth 360°, 2016 ; Conference date: 14-06-2016 Through 16-06-2016",

year = "2017",

doi = "10.1007/978-3-319-49655-9\_34",

language = "English (US)",

isbn = "9783319496542",

series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST",

publisher = "Springer Verlag",

pages = "259--270",

editor = "Laszlo Bokor and Frank Hopfgartner and Kostas Giokas",

booktitle = "eHealth 360° - International Summit on eHealth, Revised Selected Papers",

address = "Germany",

}

TY - GEN

T1 - Towards stress detection in real-life scenarios using wearable sensors

T2 - International Summit on eHealth 360°, 2016

AU - Lamichhane, Bishal

AU - Großekathöfer, Ulf

AU - Schiavone, Giuseppina

AU - Casale, Pierluigi

N1 - Publisher Copyright: © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2017.

PY - 2017

Y1 - 2017

N2 - Wearable physiological sensors offer possibilities for the development of continuous stress detection models. Such models need to address the inter-individual and intra-individual differences in stress physiology. In this paper we propose and evaluate a normalization factor, StressResponse Factor (SRF), to address such differences. SRF is computed using physiological features and the corresponding stress level at a reference point. The proposed normalization factor is evaluated in a dataset obtained from a free-living study with 10 participants, where each participant was monitored for 5 days during their working hours using different physiological sensors. We obtain an average reduction of mean squared error by up to 32% in models with SRF compared to the models without SRF.

AB - Wearable physiological sensors offer possibilities for the development of continuous stress detection models. Such models need to address the inter-individual and intra-individual differences in stress physiology. In this paper we propose and evaluate a normalization factor, StressResponse Factor (SRF), to address such differences. SRF is computed using physiological features and the corresponding stress level at a reference point. The proposed normalization factor is evaluated in a dataset obtained from a free-living study with 10 participants, where each participant was monitored for 5 days during their working hours using different physiological sensors. We obtain an average reduction of mean squared error by up to 32% in models with SRF compared to the models without SRF.

KW - Machine learning

KW - Physiology normalization

KW - Stress detection

KW - Wearable sensors

UR - https://www.scopus.com/pages/publications/85009443027

UR - https://www.scopus.com/inward/citedby.url?scp=85009443027&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-49655-9_34

DO - 10.1007/978-3-319-49655-9_34

M3 - Conference contribution

AN - SCOPUS:85009443027

SN - 9783319496542

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

SP - 259

EP - 270

BT - eHealth 360° - International Summit on eHealth, Revised Selected Papers

A2 - Bokor, Laszlo

A2 - Hopfgartner, Frank

A2 - Giokas, Kostas

PB - Springer Verlag

Y2 - 14 June 2016 through 16 June 2016

ER -

Towards stress detection in real-life scenarios using wearable sensors: Normalization factor to reduce variability in stress physiology

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this