Detection of prolonged stress in smart office

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

Detection of long-lasting stress in its early stage may allow prevention of irreversible health damages, but most of today’s stress detectors are not sufficiently convenient for long-term use. Some detectors rely on wearable physiological devices, known to have high abandonment rate, whereas other systems collect only behavioural data, but require each user to report occurrences of his/her stress during at least a month because behavioural patterns notably vary between individuals. Therefore, behaviour-based stress detection models should be learned separately for each person, and in existing systems such learning is typically supervised. In contrast, this work proposes a person-specific stress monitoring system, requiring no efforts from end users. This system acquires users’ motion trajectories via in-office depth cameras and employs a novel unsupervised method for analysis of these trajectories, based on discrete Hidden Markov Models. In 10-months-long real life study the proposed system correctly recognised the most stressful working periods of the monitored subjects and pointed out the most stress-prone persons.

Original languageEnglish
Title of host publicationIntelligent Computing
Subtitle of host publicationProceedings of the 2018 Computing Conference
EditorsSupriya Kapoor, Rahul Bhatia, Kohei Arai
PublisherSpringer Verlag
Pages1253-1261
Number of pages9
ISBN (Print)978-303-00117-6-5
DOIs
Publication statusPublished - 2018
MoE publication typeNot Eligible
EventComputing Conference 2018, SAI 2018 - London, United Kingdom
Duration: 10 Jul 201812 Jul 2018

Publication series

NameAdvances in Intelligent Systems and Computing
Volume857
ISSN (Print)2194-5357

Conference

ConferenceComputing Conference 2018, SAI 2018
Abbreviated titleSAI 2018
CountryUnited Kingdom
CityLondon
Period10/07/1812/07/18

Fingerprint

Trajectories
Detectors
Hidden Markov models
Learning systems
Cameras
Health
Monitoring

Keywords

  • Ambient intelligence
  • Hidden Markov Models (HMM)
  • Stress detection
  • Unsupervised learning

Cite this

Vildjiounaite, E., Huotari, V., Kallio, J., Kyllönen, V., Mäkelä, S. M., & Gimel’farb, G. (2018). Detection of prolonged stress in smart office. In S. Kapoor, R. Bhatia, & K. Arai (Eds.), Intelligent Computing: Proceedings of the 2018 Computing Conference (pp. 1253-1261). Springer Verlag. Advances in Intelligent Systems and Computing, Vol.. 857 https://doi.org/10.1007/978-3-030-01177-2_90
Vildjiounaite, Elena ; Huotari, Ville ; Kallio, Johanna ; Kyllönen, Vesa ; Mäkelä, Satu Marja ; Gimel’farb, Georgy. / Detection of prolonged stress in smart office. Intelligent Computing: Proceedings of the 2018 Computing Conference. editor / Supriya Kapoor ; Rahul Bhatia ; Kohei Arai. Springer Verlag, 2018. pp. 1253-1261 (Advances in Intelligent Systems and Computing, Vol. 857).
@inproceedings{c9ad2599cf4e4b31b6635075f8a0d5e6,
title = "Detection of prolonged stress in smart office",
abstract = "Detection of long-lasting stress in its early stage may allow prevention of irreversible health damages, but most of today’s stress detectors are not sufficiently convenient for long-term use. Some detectors rely on wearable physiological devices, known to have high abandonment rate, whereas other systems collect only behavioural data, but require each user to report occurrences of his/her stress during at least a month because behavioural patterns notably vary between individuals. Therefore, behaviour-based stress detection models should be learned separately for each person, and in existing systems such learning is typically supervised. In contrast, this work proposes a person-specific stress monitoring system, requiring no efforts from end users. This system acquires users’ motion trajectories via in-office depth cameras and employs a novel unsupervised method for analysis of these trajectories, based on discrete Hidden Markov Models. In 10-months-long real life study the proposed system correctly recognised the most stressful working periods of the monitored subjects and pointed out the most stress-prone persons.",
keywords = "Ambient intelligence, Hidden Markov Models (HMM), Stress detection, Unsupervised learning",
author = "Elena Vildjiounaite and Ville Huotari and Johanna Kallio and Vesa Kyll{\"o}nen and M{\"a}kel{\"a}, {Satu Marja} and Georgy Gimel’farb",
year = "2018",
doi = "10.1007/978-3-030-01177-2_90",
language = "English",
isbn = "978-303-00117-6-5",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "1253--1261",
editor = "Supriya Kapoor and Rahul Bhatia and Kohei Arai",
booktitle = "Intelligent Computing",
address = "Germany",

}

Vildjiounaite, E, Huotari, V, Kallio, J, Kyllönen, V, Mäkelä, SM & Gimel’farb, G 2018, Detection of prolonged stress in smart office. in S Kapoor, R Bhatia & K Arai (eds), Intelligent Computing: Proceedings of the 2018 Computing Conference. Springer Verlag, Advances in Intelligent Systems and Computing, vol. 857, pp. 1253-1261, Computing Conference 2018, SAI 2018, London, United Kingdom, 10/07/18. https://doi.org/10.1007/978-3-030-01177-2_90

Detection of prolonged stress in smart office. / Vildjiounaite, Elena; Huotari, Ville; Kallio, Johanna; Kyllönen, Vesa; Mäkelä, Satu Marja; Gimel’farb, Georgy.

Intelligent Computing: Proceedings of the 2018 Computing Conference. ed. / Supriya Kapoor; Rahul Bhatia; Kohei Arai. Springer Verlag, 2018. p. 1253-1261 (Advances in Intelligent Systems and Computing, Vol. 857).

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Detection of prolonged stress in smart office

AU - Vildjiounaite, Elena

AU - Huotari, Ville

AU - Kallio, Johanna

AU - Kyllönen, Vesa

AU - Mäkelä, Satu Marja

AU - Gimel’farb, Georgy

PY - 2018

Y1 - 2018

N2 - Detection of long-lasting stress in its early stage may allow prevention of irreversible health damages, but most of today’s stress detectors are not sufficiently convenient for long-term use. Some detectors rely on wearable physiological devices, known to have high abandonment rate, whereas other systems collect only behavioural data, but require each user to report occurrences of his/her stress during at least a month because behavioural patterns notably vary between individuals. Therefore, behaviour-based stress detection models should be learned separately for each person, and in existing systems such learning is typically supervised. In contrast, this work proposes a person-specific stress monitoring system, requiring no efforts from end users. This system acquires users’ motion trajectories via in-office depth cameras and employs a novel unsupervised method for analysis of these trajectories, based on discrete Hidden Markov Models. In 10-months-long real life study the proposed system correctly recognised the most stressful working periods of the monitored subjects and pointed out the most stress-prone persons.

AB - Detection of long-lasting stress in its early stage may allow prevention of irreversible health damages, but most of today’s stress detectors are not sufficiently convenient for long-term use. Some detectors rely on wearable physiological devices, known to have high abandonment rate, whereas other systems collect only behavioural data, but require each user to report occurrences of his/her stress during at least a month because behavioural patterns notably vary between individuals. Therefore, behaviour-based stress detection models should be learned separately for each person, and in existing systems such learning is typically supervised. In contrast, this work proposes a person-specific stress monitoring system, requiring no efforts from end users. This system acquires users’ motion trajectories via in-office depth cameras and employs a novel unsupervised method for analysis of these trajectories, based on discrete Hidden Markov Models. In 10-months-long real life study the proposed system correctly recognised the most stressful working periods of the monitored subjects and pointed out the most stress-prone persons.

KW - Ambient intelligence

KW - Hidden Markov Models (HMM)

KW - Stress detection

KW - Unsupervised learning

UR - http://www.scopus.com/inward/record.url?scp=85057106645&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-01177-2_90

DO - 10.1007/978-3-030-01177-2_90

M3 - Conference article in proceedings

SN - 978-303-00117-6-5

T3 - Advances in Intelligent Systems and Computing

SP - 1253

EP - 1261

BT - Intelligent Computing

A2 - Kapoor, Supriya

A2 - Bhatia, Rahul

A2 - Arai, Kohei

PB - Springer Verlag

ER -

Vildjiounaite E, Huotari V, Kallio J, Kyllönen V, Mäkelä SM, Gimel’farb G. Detection of prolonged stress in smart office. In Kapoor S, Bhatia R, Arai K, editors, Intelligent Computing: Proceedings of the 2018 Computing Conference. Springer Verlag. 2018. p. 1253-1261. (Advances in Intelligent Systems and Computing, Vol. 857). https://doi.org/10.1007/978-3-030-01177-2_90