Personalization of convolutional neural networks within the stress detection task using heart rate variability data

Stress detection is an active area of research with important implications for personal, occupational, and social health. Most modern approaches use features computed from multiple sensor modalities, i.e., grouping different types of data from multiple sources for processing. These include electroca...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Nauchno-tekhnicheskiĭ vestnik informat͡s︡ionnykh tekhnologiĭ, mekhaniki i optiki Ročník 23; číslo 6; s. 1178 - 1186
Hlavní autori: Dobrokhvalov, M.O., Filatov, A.Yu
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: ITMO University 01.12.2024
Predmet:
ISSN:2226-1494, 2500-0373
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Stress detection is an active area of research with important implications for personal, occupational, and social health. Most modern approaches use features computed from multiple sensor modalities, i.e., grouping different types of data from multiple sources for processing. These include electrocardiogram, electrodermal activity, electromyogram, skin temperature, respiration, accelerometer data, etc. Also, traditional machine learning algorithms (decision tree, discriminant analysis, support vector machine, etc.) or fully-connected neural networks are mostly used. Using these methods requires large amounts of data. Researchers are considering different approaches to personalization or generalization of models relative to subjects, namely subject-independent and subject-dependent (initially personal or adapted) models. The aim of the presented work is to develop a method for detecting stress based on heart rate variability data, taking into account the process of personalization of neural networks. The use of a convolutional neural network is proposed. The dependence of accuracy on the length of the input signal is studied. The dependence of accuracy on the data dimensionality reduction layer (one-dimensional convolutional layer, maximizing and averaging pooling) used in the network is also considered. The importance of personalizing models is demonstrated to significantly increase the accuracy of models of specific subjects. It is shown that the proposed method, based on 60 intervals between heartbeats, makes it possible to binary determine whether a person is under stress. Personalization allowed increasing the accuracy from 91.8 % to 98.9 ± 2.6 %. The F1-score value increased from 0.907 to 0.983 ± 0.038. The proposed personalized networks can be used in systems for monitoring the functional state of a person. They can also be used as part of a system that grants or restricts access to private resources based on whether a person is currently at rest.
AbstractList Stress detection is an active area of research with important implications for personal, occupational, and social health. Most modern approaches use features computed from multiple sensor modalities, i.e., grouping different types of data from multiple sources for processing. These include electrocardiogram, electrodermal activity, electromyogram, skin temperature, respiration, accelerometer data, etc. Also, traditional machine learning algorithms (decision tree, discriminant analysis, support vector machine, etc.) or fully-connected neural networks are mostly used. Using these methods requires large amounts of data. Researchers are considering different approaches to personalization or generalization of models relative to subjects, namely subject-independent and subject-dependent (initially personal or adapted) models. The aim of the presented work is to develop a method for detecting stress based on heart rate variability data, taking into account the process of personalization of neural networks. The use of a convolutional neural network is proposed. The dependence of accuracy on the length of the input signal is studied. The dependence of accuracy on the data dimensionality reduction layer (one-dimensional convolutional layer, maximizing and averaging pooling) used in the network is also considered. The importance of personalizing models is demonstrated to significantly increase the accuracy of models of specific subjects. It is shown that the proposed method, based on 60 intervals between heartbeats, makes it possible to binary determine whether a person is under stress. Personalization allowed increasing the accuracy from 91.8 % to 98.9 ± 2.6 %. The F1-score value increased from 0.907 to 0.983 ± 0.038. The proposed personalized networks can be used in systems for monitoring the functional state of a person. They can also be used as part of a system that grants or restricts access to private resources based on whether a person is currently at rest.
Author Dobrokhvalov, M.O.
Filatov, A.Yu
Author_xml – sequence: 1
  givenname: M.O.
  orcidid: 0000-0002-0571-5836
  surname: Dobrokhvalov
  fullname: Dobrokhvalov, M.O.
– sequence: 2
  givenname: A.Yu
  orcidid: 0000-0003-4298-8523
  surname: Filatov
  fullname: Filatov, A.Yu
BookMark eNo9UdtKBDEMLaLgqvsPffJttJeZXl4EWbwsCPqgzyUz0-52HafSdlf06-2sFwhJTkgOSc4JOhzDaBE6p-SCykaJS8aYqGit64oRxqtiBVKpilPiAM1YQ0hFuOSHJf_rPUbzlDaEECqLY2yG0pONKYww-C_IPow4ONyFcReG7QRhwKPdxn3IHyG-Jvzh89qPOK8tTjnalHBvs-32wxnSK94mP67w2kLMOEK2eAfRQ-sHnz9xDxnO0JGDIdn5bzxFL7c3z4v76uHxbrm4fqg6VktRtdCrTmvNnXQtkcJazlpNneDUkQJkY7VzEgTVnDtGHJ9uZtYJxmivFD9Fyx_ePsDGvEf_BvHTBPBmXwhxZcqOvhus6TgTTNFaQEfqRvVagaQCWt20dUsaXriufri6GFKK1v3zUWL2ipjpy2b6spkUMcUKLIqYSRH-DYRrgwE
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.17586/2226-1494-2023-23-6-1178-1186
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 Engineering
EISSN 2500-0373
EndPage 1186
ExternalDocumentID oai_doaj_org_article_c32628146ac0458d98a716ab95b4b053
10_17586_2226_1494_2023_23_6_1178_1186
GroupedDBID 642
AAYXX
ADBBV
AFKRA
ALMA_UNASSIGNED_HOLDINGS
BCNDV
BENPR
BPHCQ
BYOGL
CITATION
GROUPED_DOAJ
KQ8
PIMPY
PQQKQ
PROAC
VCL
VIT
ID FETCH-LOGICAL-c2476-bad8c9993f7fb076ee32b91f631f0ee375e9ff7a61933f20f325002ef6221d883
IEDL.DBID DOA
ISSN 2226-1494
IngestDate Mon Nov 03 22:03:38 EST 2025
Sat Nov 29 03:57:45 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 6
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2476-bad8c9993f7fb076ee32b91f631f0ee375e9ff7a61933f20f325002ef6221d883
ORCID 0000-0002-0571-5836
0000-0003-4298-8523
OpenAccessLink https://doaj.org/article/c32628146ac0458d98a716ab95b4b053
PageCount 9
ParticipantIDs doaj_primary_oai_doaj_org_article_c32628146ac0458d98a716ab95b4b053
crossref_primary_10_17586_2226_1494_2023_23_6_1178_1186
PublicationCentury 2000
PublicationDate 2024-12-01
PublicationDateYYYYMMDD 2024-12-01
PublicationDate_xml – month: 12
  year: 2024
  text: 2024-12-01
  day: 01
PublicationDecade 2020
PublicationTitle Nauchno-tekhnicheskiĭ vestnik informat͡s︡ionnykh tekhnologiĭ, mekhaniki i optiki
PublicationYear 2024
Publisher ITMO University
Publisher_xml – name: ITMO University
SSID ssj0001700022
ssib026971427
Score 2.2824783
Snippet Stress detection is an active area of research with important implications for personal, occupational, and social health. Most modern approaches use features...
SourceID doaj
crossref
SourceType Open Website
Index Database
StartPage 1178
SubjectTerms вариабельность сердечного ритма
детектирование стресса
машинное обучение
сверточные нейронные сети
субъекто-зависимые модели
Title Personalization of convolutional neural networks within the stress detection task using heart rate variability data
URI https://doaj.org/article/c32628146ac0458d98a716ab95b4b053
Volume 23
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2500-0373
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001700022
  issn: 2226-1494
  databaseCode: DOA
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07SwQxEA4iIlqITzxfpBC74OZxeZQqitVxhYJdSLKJqHCKdwr-e2c2q2xnIwSWDWQJH0Pmm-zMN4ScGmUFuOGGlchbpmxxzEalWMw6YKOHMFapazZhJhP78OCmg1ZfmBNW5YErcOcJ-IXAe6qQ8J9e62wAih-iG0cVwYLw9G2MGwRTYElCO8NVr2_5XEVi0FthpzngGwzCArVKzvDEAL6sz38nGXYTZzDglWN8xbHIeuCxBsL-nQe62SQbPXWkF3XLW2Qpz7bJ-kBQcIfMpz_culZX0tdCMa-8ty9YjfqV3aPL_p5TvId9mlGggbSWjdA2L7r0LJgM8xeKifGPFPteLyjKStBPiK6ruPcXxfzSXXJ_c313dcv6tgosCWU0i6G1CXihLKbExuicpYiOFy15aeDFjDNe5AYIraQsoikSaFIjctFC8NZauUeWZ6-zvE9odrIprTEZ6-USRHpcF-mCM1HzpHgaEfMDnX-r6hkeow4E3SPoHkH3CLqHoVF63HoEfUQuEenfVaiC3U2AbfjeNvxftnHwHx85JGuwP1VTWI7I8uL9Ix-TlfS5eJq_n3Rm9w24D9SR
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=Personalization+of+convolutional+neural+networks+within+the+stress+detection+task+using+heart+rate+variability+data&rft.jtitle=Nauchno-tekhnicheski%C4%AD+vestnik+informat%CD%A1s%EF%B8%A1ionnykh+tekhnologi%C4%AD%2C+mekhaniki+i+optiki&rft.au=Dobrokhvalov%2C+M.O.&rft.au=Filatov%2C+A.Yu&rft.date=2024-12-01&rft.issn=2226-1494&rft.volume=23&rft.issue=6&rft.spage=1178&rft.epage=1186&rft_id=info:doi/10.17586%2F2226-1494-2023-23-6-1178-1186&rft.externalDBID=n%2Fa&rft.externalDocID=10_17586_2226_1494_2023_23_6_1178_1186
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2226-1494&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2226-1494&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2226-1494&client=summon