Comparison of machine learning techniques for psychophysiological stress detection

Elena Smets; Pierluigi Casale; Ulf Großekathöfer; Bishal Lamichhane; Walter De Raedt; Katleen Bogaerts; Ilse Van Diest; Chris Van Hoof

doi:10.1007/978-3-319-32270-4_2

Comparison of machine learning techniques for psychophysiological stress detection

Elena Smets, Pierluigi Casale, Ulf Großekathöfer, Bishal Lamichhane, Walter De Raedt, Katleen Bogaerts, Ilse Van Diest, Chris Van Hoof

Houston Methodist

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

63 Scopus citations

Abstract

Previous research has indicated that physiological signals can be used to detect mental stress. There is however no consensus on the optimal algorithm for this detection. The aim of this study is to compare different machine learning techniques for the measurement of stress based on physiological responses in a controlled environment. Electrocardiogram (ECG), galvanic skin response (GSR), temperature and respiration were measured during a laboratory stress test. Six machine learning techniques were investigated using a general and personal approach. The results show that personalized dynamic Bayesian networks and generalized support vector machines render the best average classification results with 84.6% and 82.7% respectively.

Original language	English (US)
Title of host publication	Pervasive Computing Paradigms for Mental Health - 5th International Conference, MindCare 2015, Revised Selected Papers
Editors	Dimitris Giakoumis, Guillaume Lopez, Aleksandar Matic, Silvia Serino, Pietro Cipresso
Publisher	Springer Verlag
Pages	13-22
Number of pages	10
ISBN (Print)	9783319322698
DOIs	https://doi.org/10.1007/978-3-319-32270-4_2
State	Published - 2016
Event	5th International Conference on Pervasive Computing Paradigms for Mental Health, MindCare 2015 - Milan, Italy Duration: Sep 24 2015 → Sep 25 2015

Publication series

Name	Communications in Computer and Information Science
Volume	604
ISSN (Print)	1865-0929

Conference

Conference	5th International Conference on Pervasive Computing Paradigms for Mental Health, MindCare 2015
Country/Territory	Italy
City	Milan
Period	9/24/15 → 9/25/15

Keywords

Machine learning
Physiology
Stress monitoring

ASJC Scopus subject areas

General Computer Science
General Mathematics

Access to Document

10.1007/978-3-319-32270-4_2

Cite this

Smets, E., Casale, P., Großekathöfer, U., Lamichhane, B., De Raedt, W., Bogaerts, K., Van Diest, I., & Van Hoof, C. (2016). Comparison of machine learning techniques for psychophysiological stress detection. In D. Giakoumis, G. Lopez, A. Matic, S. Serino, & P. Cipresso (Eds.), Pervasive Computing Paradigms for Mental Health - 5th International Conference, MindCare 2015, Revised Selected Papers (pp. 13-22). (Communications in Computer and Information Science; Vol. 604). Springer Verlag. https://doi.org/10.1007/978-3-319-32270-4_2

Comparison of machine learning techniques for psychophysiological stress detection. / Smets, Elena; Casale, Pierluigi; Großekathöfer, Ulf et al.
Pervasive Computing Paradigms for Mental Health - 5th International Conference, MindCare 2015, Revised Selected Papers. ed. / Dimitris Giakoumis; Guillaume Lopez; Aleksandar Matic; Silvia Serino; Pietro Cipresso. Springer Verlag, 2016. p. 13-22 (Communications in Computer and Information Science; Vol. 604).

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

Smets, E, Casale, P, Großekathöfer, U, Lamichhane, B, De Raedt, W, Bogaerts, K, Van Diest, I & Van Hoof, C 2016, Comparison of machine learning techniques for psychophysiological stress detection. in D Giakoumis, G Lopez, A Matic, S Serino & P Cipresso (eds), Pervasive Computing Paradigms for Mental Health - 5th International Conference, MindCare 2015, Revised Selected Papers. Communications in Computer and Information Science, vol. 604, Springer Verlag, pp. 13-22, 5th International Conference on Pervasive Computing Paradigms for Mental Health, MindCare 2015, Milan, Italy, 9/24/15. https://doi.org/10.1007/978-3-319-32270-4_2

Smets E, Casale P, Großekathöfer U, Lamichhane B, De Raedt W, Bogaerts K et al. Comparison of machine learning techniques for psychophysiological stress detection. In Giakoumis D, Lopez G, Matic A, Serino S, Cipresso P, editors, Pervasive Computing Paradigms for Mental Health - 5th International Conference, MindCare 2015, Revised Selected Papers. Springer Verlag. 2016. p. 13-22. (Communications in Computer and Information Science). doi: 10.1007/978-3-319-32270-4_2

Smets, Elena ; Casale, Pierluigi ; Großekathöfer, Ulf et al. / Comparison of machine learning techniques for psychophysiological stress detection. Pervasive Computing Paradigms for Mental Health - 5th International Conference, MindCare 2015, Revised Selected Papers. editor / Dimitris Giakoumis ; Guillaume Lopez ; Aleksandar Matic ; Silvia Serino ; Pietro Cipresso. Springer Verlag, 2016. pp. 13-22 (Communications in Computer and Information Science).

@inproceedings{01348981ce4644df938a8a6c1c240fee,

title = "Comparison of machine learning techniques for psychophysiological stress detection",

abstract = "Previous research has indicated that physiological signals can be used to detect mental stress. There is however no consensus on the optimal algorithm for this detection. The aim of this study is to compare different machine learning techniques for the measurement of stress based on physiological responses in a controlled environment. Electrocardiogram (ECG), galvanic skin response (GSR), temperature and respiration were measured during a laboratory stress test. Six machine learning techniques were investigated using a general and personal approach. The results show that personalized dynamic Bayesian networks and generalized support vector machines render the best average classification results with 84.6\% and 82.7\% respectively.",

keywords = "Machine learning, Physiology, Stress monitoring",

author = "Elena Smets and Pierluigi Casale and Ulf Gro{\ss}ekath{\"o}fer and Bishal Lamichhane and \{De Raedt\}, Walter and Katleen Bogaerts and \{Van Diest\}, Ilse and \{Van Hoof\}, Chris",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2016.; 5th International Conference on Pervasive Computing Paradigms for Mental Health, MindCare 2015 ; Conference date: 24-09-2015 Through 25-09-2015",

year = "2016",

doi = "10.1007/978-3-319-32270-4\_2",

language = "English (US)",

isbn = "9783319322698",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "13--22",

editor = "Dimitris Giakoumis and Guillaume Lopez and Aleksandar Matic and Silvia Serino and Pietro Cipresso",

booktitle = "Pervasive Computing Paradigms for Mental Health - 5th International Conference, MindCare 2015, Revised Selected Papers",

address = "Germany",

}

TY - GEN

T1 - Comparison of machine learning techniques for psychophysiological stress detection

AU - Smets, Elena

AU - Casale, Pierluigi

AU - Großekathöfer, Ulf

AU - Lamichhane, Bishal

AU - De Raedt, Walter

AU - Bogaerts, Katleen

AU - Van Diest, Ilse

AU - Van Hoof, Chris

N1 - Publisher Copyright: © Springer International Publishing Switzerland 2016.

PY - 2016

Y1 - 2016

N2 - Previous research has indicated that physiological signals can be used to detect mental stress. There is however no consensus on the optimal algorithm for this detection. The aim of this study is to compare different machine learning techniques for the measurement of stress based on physiological responses in a controlled environment. Electrocardiogram (ECG), galvanic skin response (GSR), temperature and respiration were measured during a laboratory stress test. Six machine learning techniques were investigated using a general and personal approach. The results show that personalized dynamic Bayesian networks and generalized support vector machines render the best average classification results with 84.6% and 82.7% respectively.

AB - Previous research has indicated that physiological signals can be used to detect mental stress. There is however no consensus on the optimal algorithm for this detection. The aim of this study is to compare different machine learning techniques for the measurement of stress based on physiological responses in a controlled environment. Electrocardiogram (ECG), galvanic skin response (GSR), temperature and respiration were measured during a laboratory stress test. Six machine learning techniques were investigated using a general and personal approach. The results show that personalized dynamic Bayesian networks and generalized support vector machines render the best average classification results with 84.6% and 82.7% respectively.

KW - Machine learning

KW - Physiology

KW - Stress monitoring

UR - https://www.scopus.com/pages/publications/84964059130

UR - https://www.scopus.com/inward/citedby.url?scp=84964059130&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-32270-4_2

DO - 10.1007/978-3-319-32270-4_2

M3 - Conference contribution

AN - SCOPUS:84964059130

SN - 9783319322698

T3 - Communications in Computer and Information Science

SP - 13

EP - 22

BT - Pervasive Computing Paradigms for Mental Health - 5th International Conference, MindCare 2015, Revised Selected Papers

A2 - Giakoumis, Dimitris

A2 - Lopez, Guillaume

A2 - Matic, Aleksandar

A2 - Serino, Silvia

A2 - Cipresso, Pietro

PB - Springer Verlag

T2 - 5th International Conference on Pervasive Computing Paradigms for Mental Health, MindCare 2015

Y2 - 24 September 2015 through 25 September 2015

ER -

Comparison of machine learning techniques for psychophysiological stress detection

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this