Longitudinal estimation of stress-related states through bio-sensor data

PurposeThe authors aim to develop a conceptual framework for longitudinal estimation of stress-related states in the wild (IW), based on the machine learning (ML) algorithms that use physiological and non-physiological bio-sensor data.Design/methodology/approachThe authors propose a conceptual frame...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied computing & informatics Jg. 21; H. 3-4; S. 186 - 197
1. Verfasser: Mozgovoy, Vadym
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Emerald Publishing 29.10.2025
Schlagworte:
ISSN:2634-1964, 2210-8327
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract PurposeThe authors aim to develop a conceptual framework for longitudinal estimation of stress-related states in the wild (IW), based on the machine learning (ML) algorithms that use physiological and non-physiological bio-sensor data.Design/methodology/approachThe authors propose a conceptual framework for longitudinal estimation of stress-related states consisting of four blocks: (1) identification; (2) validation; (3) measurement and (4) visualization. The authors implement each step of the proposed conceptual framework, using the example of Gaussian mixture model (GMM) and K-means algorithm. These ML algorithms are trained on the data of 18 workers from the public administration sector who wore biometric devices for about two months.FindingsThe authors confirm the convergent validity of a proposed conceptual framework IW. Empirical data analysis suggests that two-cluster models achieve five-fold cross-validation accuracy exceeding 70% in identifying stress. Coefficient of accuracy decreases for three-cluster models achieving around 45%. The authors conclude that identification models may serve to derive longitudinal stress-related measures.Research limitations/implicationsProposed conceptual framework may guide researchers in creating validated stress-related indicators. At the same time, physiological sensing of stress through identification models is limited because of subject-specific reactions to stressors.Practical implicationsLongitudinal indicators on stress allow estimation of long-term impact coming from external environment on stress-related states. Such stress-related indicators can become an integral part of mobile/web/computer applications supporting stress management programs.Social implicationsTimely identification of excessive stress may improve individual well-being and prevent development stress-related diseases.Originality/valueThe study develops a novel conceptual framework for longitudinal estimation of stress-related states using physiological and non-physiological bio-sensor data, given that scientific knowledge on validated longitudinal indicators of stress is in emergent state.
AbstractList PurposeThe authors aim to develop a conceptual framework for longitudinal estimation of stress-related states in the wild (IW), based on the machine learning (ML) algorithms that use physiological and non-physiological bio-sensor data.Design/methodology/approachThe authors propose a conceptual framework for longitudinal estimation of stress-related states consisting of four blocks: (1) identification; (2) validation; (3) measurement and (4) visualization. The authors implement each step of the proposed conceptual framework, using the example of Gaussian mixture model (GMM) and K-means algorithm. These ML algorithms are trained on the data of 18 workers from the public administration sector who wore biometric devices for about two months.FindingsThe authors confirm the convergent validity of a proposed conceptual framework IW. Empirical data analysis suggests that two-cluster models achieve five-fold cross-validation accuracy exceeding 70% in identifying stress. Coefficient of accuracy decreases for three-cluster models achieving around 45%. The authors conclude that identification models may serve to derive longitudinal stress-related measures.Research limitations/implicationsProposed conceptual framework may guide researchers in creating validated stress-related indicators. At the same time, physiological sensing of stress through identification models is limited because of subject-specific reactions to stressors.Practical implicationsLongitudinal indicators on stress allow estimation of long-term impact coming from external environment on stress-related states. Such stress-related indicators can become an integral part of mobile/web/computer applications supporting stress management programs.Social implicationsTimely identification of excessive stress may improve individual well-being and prevent development stress-related diseases.Originality/valueThe study develops a novel conceptual framework for longitudinal estimation of stress-related states using physiological and non-physiological bio-sensor data, given that scientific knowledge on validated longitudinal indicators of stress is in emergent state.
Author Mozgovoy, Vadym
Author_xml – sequence: 1
  givenname: Vadym
  orcidid: 0000-0001-5322-3740
  surname: Mozgovoy
  fullname: Mozgovoy, Vadym
BookMark eNo9kE1LAzEQhoMoWGvvHvcPRCeZ7GZzLEVtoeBFzyGbj3ZL3UiSHvz3plY8vTMvzMPw3JHrKU6ekAcGj4xB_7RcbSgg5cAZBZBwRWacM6A9cnld5w4FZaoTt2SR8wEAmMSecZyR9TZOu7Gc3DiZY-NzGT9NGePUxNDkknzONPmjKd7VtUZuyj7F027fDGOk2U85psaZYu7JTTDH7Bd_OScfL8_vqzXdvr1uVssttQiiULSqw4630kkzQCuhU6HlIJSwwfcclWNqGFCBa6XwYQhM1Yo5tJ1v6wnOyebCddEc9Feq_6ZvHc2of4uYdtqkMtqj14Ni3AIqZZ0U0vIeBycDWAOiF1y2lQUXlk0x5-TDP4-BPovVVawG1Gex-iwWfwAUB2xt
Cites_doi 10.1111/j.2044-8295.1991.tb02391.x
10.1016/j.bspc.2019.101736
10.1109/TITS.2020.2980555
10.1108/JMP-03-2013-0085
10.1109/ACCESS.2020.2975351
10.1016/j.autcon.2021.103560
10.1016/j.jbi.2019.103139
10.1016/j.physbeh.2021.113365
10.1109/JBHI.2015.2446195
10.1080/0144929X.2019.1673820
10.1016/j.eswa.2021.114693
10.1007/s12668-013-0089-2
10.1016/j.avb.2021.101587
10.3390/s19081849
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.1108/ACI-03-2021-0070
DatabaseName CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2210-8327
EndPage 197
ExternalDocumentID oai_doaj_org_article_b912c0399cd747c283bd7f0ca0484275
10_1108_ACI_03_2021_0070
GroupedDBID 0R~
4.4
457
5VS
AAEDT
AAIKJ
AALRI
AAYXX
ABGJK
ABMAC
ACGFS
ADBBV
ADEZE
AEXQZ
AFFHD
AFKRA
AGHFR
AKRWK
ALMA_UNASSIGNED_HOLDINGS
BCNDV
BENPR
CCPQU
CITATION
EBS
FDB
GEI
GROUPED_DOAJ
H13
IXB
KQ8
M~E
O-L
O9-
OK1
PHGZM
PHGZT
PIMPY
SES
SSZ
XDTOA
XH2
ID FETCH-LOGICAL-c304t-3c9636257d7ab057069f520494cfe8239d19bb390d574efbf199d11d3c6e57ab3
IEDL.DBID DOA
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001603452200014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2634-1964
IngestDate Mon Nov 03 22:04:14 EST 2025
Wed Oct 29 21:07:12 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3-4
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c304t-3c9636257d7ab057069f520494cfe8239d19bb390d574efbf199d11d3c6e57ab3
ORCID 0000-0001-5322-3740
OpenAccessLink https://doaj.org/article/b912c0399cd747c283bd7f0ca0484275
PageCount 12
ParticipantIDs doaj_primary_oai_doaj_org_article_b912c0399cd747c283bd7f0ca0484275
crossref_primary_10_1108_ACI_03_2021_0070
PublicationCentury 2000
PublicationDate 2025-10-29
PublicationDateYYYYMMDD 2025-10-29
PublicationDate_xml – month: 10
  year: 2025
  text: 2025-10-29
  day: 29
PublicationDecade 2020
PublicationTitle Applied computing & informatics
PublicationYear 2025
Publisher Emerald Publishing
Publisher_xml – name: Emerald Publishing
References Mou (2025102804365310800_ref017) 2021; 173
Feng (2025102804365310800_ref003) 2021; 40
Zubair (2025102804365310800_ref013) 2020; 57
Finke (2025102804365310800_ref018) 2021; 233
de Santos Sierra (2025102804365310800_ref028) 2010
Zhai (2025102804365310800_ref027) 2005
Jin (2025102804365310800_ref010) 2021
Can (2025102804365310800_ref016) 2020; 8
de Santos (2025102804365310800_ref025) 2011
Wang (2025102804365310800_ref015) 2020; 22
Schmidt (2025102804365310800_ref024) 2018
Corbett (2025102804365310800_ref020) 2015; 30
Mozgovoy (2025102804365310800_ref023) 2019
Bonaccorso (2025102804365310800_ref009) 2018
Angus (2025102804365310800_ref026) 2005
Vadym (2025102804365310800_ref005) 2020
Stepanovic (2025102804365310800_ref004) 2019
Bishop (2025102804365310800_ref007) 2006
Chae (2025102804365310800_ref019) 2021; 124
Can (2025102804365310800_ref001) 2019
Li (2025102804365310800_ref011) 2020; 20
Greco (2025102804365310800_ref012) 2021
Garcia-Ceja (2025102804365310800_ref029) 2015; 20
Muaremi (2025102804365310800_ref006) 2013; 3
Han (2025102804365310800_ref008) 2011
Can (2025102804365310800_ref014) 2019; 19
Kalas (2025102804365310800_ref002) 2016
Hardy (2025102804365310800_ref021)
Hardy (2025102804365310800_ref022) 1991; 82
References_xml – start-page: 37
  year: 2019
  ident: 2025102804365310800_ref023
  article-title: Stress pattern recognition through wearable biosensors in the workplace: experimental longitudinal study on the role of motion intensity
– volume: 82
  start-page: 163
  issue: 2
  year: 1991
  ident: 2025102804365310800_ref022
  article-title: A catastrophe model of anxiety and performance
  publication-title: Br J Psychol
  doi: 10.1111/j.2044-8295.1991.tb02391.x
– volume-title: Data mining: concepts and techniques
  year: 2011
  ident: 2025102804365310800_ref008
– start-page: 400
  year: 2018
  ident: 2025102804365310800_ref024
  article-title: Introducing wesad, a multimodal dataset for wearable stress and affect detection
– volume: 57
  year: 2020
  ident: 2025102804365310800_ref013
  article-title: Multilevel mental stress detection using ultra-short pulse rate variability series
  publication-title: Biomed Signal Process Control
  doi: 10.1016/j.bspc.2019.101736
– volume: 22
  start-page: 3303
  issue: 6
  year: 2020
  ident: 2025102804365310800_ref015
  article-title: An ensemble classification model with unsupervised representation learning for driving stress recognition using physiological signals
  publication-title: IEEE Trans Intell Transportation Syst.
  doi: 10.1109/TITS.2020.2980555
– volume: 30
  start-page: 741
  issue: 6
  year: 2015
  ident: 2025102804365310800_ref020
  article-title: From law to folklore: work stress and the Yerkes-Dodson Law
  publication-title: J Managerial Psychol
  doi: 10.1108/JMP-03-2013-0085
– start-page: 23
  year: 2020
  ident: 2025102804365310800_ref005
  article-title: Exploration of scenario-based simulations for stress benchmarking in Swiss public service
– volume: 8
  start-page: 38146
  year: 2020
  ident: 2025102804365310800_ref016
  article-title: Personal stress-level clustering and decision-level smoothing to enhance the performance of ambulatory stress detection with smartwatches
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.2975351
– volume: 124
  year: 2021
  ident: 2025102804365310800_ref019
  article-title: Relationship between rework of engineering drawing tasks and stress level measured from physiological signals
  publication-title: Autom ConStruct
  doi: 10.1016/j.autcon.2021.103560
– year: 2019
  ident: 2025102804365310800_ref001
  article-title: Stress detection in daily life scenarios using smart phones and wearable sensors: a survey
  publication-title: J Biomed Inform
  doi: 10.1016/j.jbi.2019.103139
– volume-title: Machine Learning Algorithms: popular algorithms for data science and machine learning
  year: 2018
  ident: 2025102804365310800_ref009
– volume: 233
  year: 2021
  ident: 2025102804365310800_ref018
  article-title: Combining mental and physical stress: synergy or interference?
  publication-title: Physiol Behav
  doi: 10.1016/j.physbeh.2021.113365
– year: 2021
  ident: 2025102804365310800_ref012
  article-title: Acute stress state classification based on electrodermal activity modeling
  publication-title: IEEE Transactions on Affective Computing
– start-page: 81
  ident: 2025102804365310800_ref021
  article-title: A catastrophe model of performance in sport
– start-page: 471
  year: 2016
  ident: 2025102804365310800_ref002
  article-title: Stress detection and reduction using EEG signals
– start-page: 94
  year: 2019
  ident: 2025102804365310800_ref004
  article-title: Designing visualizations for Workplace stress management: results of a pilot study at a Swiss municipality
– volume-title: Pattern recognition and machine learning
  year: 2006
  ident: 2025102804365310800_ref007
– start-page: 364
  year: 2010
  ident: 2025102804365310800_ref028
  article-title: Two stress detection schemes based on physiological signals for real-time applications
– volume: 20
  start-page: 1
  issue: 11
  year: 2020
  ident: 2025102804365310800_ref011
  article-title: Stress detection using deep neural networks
  publication-title: BMC Med Inform Decis Making
– volume: 20
  start-page: 1053
  issue: 4
  year: 2015
  ident: 2025102804365310800_ref029
  article-title: Automatic stress detection in working environments from smartphones' accelerometer data: a first step
  publication-title: IEEE J Biomed Health Info
  doi: 10.1109/JBHI.2015.2446195
– volume: 40
  start-page: 116
  issue: 2
  year: 2021
  ident: 2025102804365310800_ref003
  article-title: Leveraging ECG signals and social media for stress detection
  publication-title: Behav Inf Technology
  doi: 10.1080/0144929X.2019.1673820
– volume: 173
  year: 2021
  ident: 2025102804365310800_ref017
  article-title: Driver stress detection via multimodal fusion using attention-based CNN-LSTM
  publication-title: Expert Syst Appl
  doi: 10.1016/j.eswa.2021.114693
– volume: 3
  start-page: 172
  issue: 2
  year: 2013
  ident: 2025102804365310800_ref006
  article-title: Towards measuring stress with smartphones and wearable devices during workday and sleep
  publication-title: BioNanoScience
  doi: 10.1007/s12668-013-0089-2
– start-page: 415
  volume-title: SoutheastCon
  year: 2005
  ident: 2025102804365310800_ref027
  article-title: Realization of stress detection using psychophysiological signals for improvement of human-computer interactions
– year: 2021
  ident: 2025102804365310800_ref010
  article-title: IoT based psychological and physical stress evaluation in sportsmen using heart rate variability
  publication-title: Aggress Violent Behav
  doi: 10.1016/j.avb.2021.101587
– volume: 19
  start-page: 1849
  issue: 8
  year: 2019
  ident: 2025102804365310800_ref014
  article-title: Continuous stress detection using wearable sensors in real life: algorithmic programming contest case study
  publication-title: Sensors
  doi: 10.3390/s19081849
– volume-title: Recent application in biometrics: InTech
  year: 2011
  ident: 2025102804365310800_ref025
– start-page: 218
  year: 2005
  ident: 2025102804365310800_ref026
  article-title: Front-end analog pre-processing for real-time psychophysiological stress measurements
SSID ssj0001738123
Score 2.327711
Snippet PurposeThe authors aim to develop a conceptual framework for longitudinal estimation of stress-related states in the wild (IW), based on the machine learning...
SourceID doaj
crossref
SourceType Open Website
Index Database
StartPage 186
SubjectTerms Bio-sensor
Conceptual framework
Longitudinal measure
Stress identification
Validation
Well-being
Title Longitudinal estimation of stress-related states through bio-sensor data
URI https://doaj.org/article/b912c0399cd747c283bd7f0ca0484275
Volume 21
WOSCitedRecordID wos001603452200014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2210-8327
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001738123
  issn: 2634-1964
  databaseCode: DOA
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2210-8327
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001738123
  issn: 2634-1964
  databaseCode: M~E
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2210-8327
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001738123
  issn: 2634-1964
  databaseCode: BENPR
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2210-8327
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001738123
  issn: 2634-1964
  databaseCode: PIMPY
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07a8MwEBYldOjSd2n6QkOXDiKyJFvWmIaEFNLQoYVswnpBlrjkNfa39yQ7JZ26dDFG2MbcSfru7LvvQ-jR5LAFZrkjMIENEZWQxCg4Y9wCoBWO-ZDY9SdyOi1nM_W2J_UVa8IaeuDGcD2jMmYpwKh1EPlaQEPjZKC2gqknmEzspVSqvWQqfV2RgERJ240VXJDIOrX7R0nLXn_wEsuIWCxPiHw3vzBpj7o_YczoFB23wSHuNy91hg784hyd7IQXcLsOL9B4UkeZoY2LklY48mQ0DYi4Drhp_iCpR8U7nBqGVriV48FmXpMVZK71Esfa0Ev0MRq-D8aklUQgllOxJtzCgoGURTpZGQi1aKFCziLHiw2-ZFy5TBnDFXW5FD6YkCkYyhy3hc_hFn6FOot64a8RVjILwfoqM6UQzPCqpMb4nHrYAQJEFV30tDOK_myYL3TKGGipwYCach0NqKMBu-g5Wu3nushZnQbAk7r1pP7Lkzf_8ZBbdMSiQi-gC1N3qLNebvw9OrTb9Xy1fEiTBI6vX8Nv96m-TQ
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Longitudinal+estimation+of+stress-related+states+through+bio-sensor+data&rft.jtitle=Applied+computing+%26+informatics&rft.au=Mozgovoy%2C+Vadym&rft.date=2025-10-29&rft.issn=2634-1964&rft.eissn=2210-8327&rft.volume=21&rft.issue=3-4&rft.spage=186&rft.epage=197&rft_id=info:doi/10.1108%2FACI-03-2021-0070&rft.externalDBID=n%2Fa&rft.externalDocID=10_1108_ACI_03_2021_0070
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2634-1964&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2634-1964&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2634-1964&client=summon