Empirical Thresholding on Spatio-Temporal Autoencoders Trained on Surveillance Videos in a Dementia Care Unit

Agitation is a key behavioural and psychological symptom exhibited by people with dementia. These behaviours can put the patient with dementia and others' health and safety at risk. Surveillance cameras installed in long-term care facilities provide an opportunity to monitor patients continuous...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2023 20th Conference on Robots and Vision (CRV) s. 265 - 272
Hlavní autori: Khan, Shehroz S., Mishra, Pratik K., Ye, Bing, Newman, Kristine, Iaboni, Andrea, Mihailidis, Alex
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.06.2023
Predmet:
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Agitation is a key behavioural and psychological symptom exhibited by people with dementia. These behaviours can put the patient with dementia and others' health and safety at risk. Surveillance cameras installed in long-term care facilities provide an opportunity to monitor patients continuously and flag behaviours of risks, including agitation. However, agitation behaviours occur rarely and diversely, leading to very small training data. Therefore, an anomaly detection approach is more suitable for this problem. In this paper, we train three baseline spatio-temporal convolutional autoencoders (on raw video, skeletons and segmentation mask) on 21 hours of normal activities and tested it on 9 hours of labelled normal and agitation data collected from a real patient in a dementia unit. The deployment of anomaly detection-based classifiers is challenging in real-world due to the absence of a validation set to obtain an operating threshold to regulate true positive and false positive rates. We present a new approach to create a proxy validation set for unseen agitation events utilizing the outliers within normal activities, and trained two separate autoencoders on normal and outliers activities. Then, we present 11 empirical thresholding approaches (existing, adapted and new) using either only normal training data or the proxy validation set. Our results showed consistently across raw video, skeletons and segmentation masks input that incorporating a proxy validation set improved performance both in terms of geometric means and Matthew's correlation coefficient. This paper highlights the real-world deployment challenges and assessment of the limit of true positives or false positives that can be acceptable in a clinical care environment.
AbstractList Agitation is a key behavioural and psychological symptom exhibited by people with dementia. These behaviours can put the patient with dementia and others' health and safety at risk. Surveillance cameras installed in long-term care facilities provide an opportunity to monitor patients continuously and flag behaviours of risks, including agitation. However, agitation behaviours occur rarely and diversely, leading to very small training data. Therefore, an anomaly detection approach is more suitable for this problem. In this paper, we train three baseline spatio-temporal convolutional autoencoders (on raw video, skeletons and segmentation mask) on 21 hours of normal activities and tested it on 9 hours of labelled normal and agitation data collected from a real patient in a dementia unit. The deployment of anomaly detection-based classifiers is challenging in real-world due to the absence of a validation set to obtain an operating threshold to regulate true positive and false positive rates. We present a new approach to create a proxy validation set for unseen agitation events utilizing the outliers within normal activities, and trained two separate autoencoders on normal and outliers activities. Then, we present 11 empirical thresholding approaches (existing, adapted and new) using either only normal training data or the proxy validation set. Our results showed consistently across raw video, skeletons and segmentation masks input that incorporating a proxy validation set improved performance both in terms of geometric means and Matthew's correlation coefficient. This paper highlights the real-world deployment challenges and assessment of the limit of true positives or false positives that can be acceptable in a clinical care environment.
Author Khan, Shehroz S.
Iaboni, Andrea
Mishra, Pratik K.
Ye, Bing
Newman, Kristine
Mihailidis, Alex
Author_xml – sequence: 1
  givenname: Shehroz S.
  surname: Khan
  fullname: Khan, Shehroz S.
  email: shehroz.khan@uhn.ca
  organization: KITE University Health Network,Canada
– sequence: 2
  givenname: Pratik K.
  surname: Mishra
  fullname: Mishra, Pratik K.
  email: pratik.mishra@mail.utoronto.ca
  organization: KITE University Health Network,Canada
– sequence: 3
  givenname: Bing
  surname: Ye
  fullname: Ye, Bing
  email: bing.ye@utoronto.ca
  organization: KITE University Health Network,Canada
– sequence: 4
  givenname: Kristine
  surname: Newman
  fullname: Newman, Kristine
  email: kristine.newman@torontomu.ca
  organization: Daphne Cockwell School of Nursing, Toronto Metropolitan University,Canada
– sequence: 5
  givenname: Andrea
  surname: Iaboni
  fullname: Iaboni, Andrea
  email: andrea.iaboni@uhn.ca
  organization: KITE University Health Network,Canada
– sequence: 6
  givenname: Alex
  surname: Mihailidis
  fullname: Mihailidis, Alex
  email: alex.mihailidis@utoronto.ca
  organization: KITE University Health Network,Canada
BookMark eNotj81Kw0AURkfQhdY-gS7mBRLvzE2azLLE-gMFQdNuyyRzYy8kM2GSCr69RV19i3M48N2ISx88CXGnIFUKzEP1vl8BlDrVoDEFgExdiKUpTIk5YKbQ4LUYNsPIkVvby_oYaTqG3rH_lMHLj9HOHJKahjHEM1-f5kC-DY7iJOto2ZP79U7xi7jvrW9J7tlRmCR7aeUjDeRntrKykeTO83wrrjrbT7T834XYPW3q6iXZvj2_VuttwhqyOcm7Ims6h0ppp1WDuTVostxAA45y6AqHZblyqqGioVy3RKhRU-daXXTgSlyI-78uE9FhjDzY-H1QoPX5POAP1qNXyg
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/CRV60082.2023.00041
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Psychology
EISBN 9798350341393
EndPage 272
ExternalDocumentID 10229830
Genre orig-research
GrantInformation_xml – fundername: Alzheimer's Association
  funderid: 10.13039/501100000143
– fundername: Natural Sciences and Engineering Research Council
  funderid: 10.13039/501100000038
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i204t-5f74bfd3112d21b35a9394590b0de50f7d3886d1be7be52cee3232efdc27f0d83
IEDL.DBID RIE
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001062462800033&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Thu Jan 18 11:14:24 EST 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i204t-5f74bfd3112d21b35a9394590b0de50f7d3886d1be7be52cee3232efdc27f0d83
PageCount 8
ParticipantIDs ieee_primary_10229830
PublicationCentury 2000
PublicationDate 2023-June
PublicationDateYYYYMMDD 2023-06-01
PublicationDate_xml – month: 06
  year: 2023
  text: 2023-June
PublicationDecade 2020
PublicationTitle 2023 20th Conference on Robots and Vision (CRV)
PublicationTitleAbbrev CRV
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.8628173
Snippet Agitation is a key behavioural and psychological symptom exhibited by people with dementia. These behaviours can put the patient with dementia and others'...
SourceID ieee
SourceType Publisher
StartPage 265
SubjectTerms agitation
anomaly detection
autoencoder
Cameras
Correlation coefficient
dementia
Health and safety
Psychology
Skeleton
Surveillance
threshold
Training data
Title Empirical Thresholding on Spatio-Temporal Autoencoders Trained on Surveillance Videos in a Dementia Care Unit
URI https://ieeexplore.ieee.org/document/10229830
WOSCitedRecordID wos001062462800033&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09a8MwEBVt6ZCpXyn9RkNXJbYlWdZY0oROIbRuyBYk6wyGxg6JHei_ryS7KR06dBNCIHQHujvp3nsIPQrOY8UjTqSRnDDKFEkSGZOcsgyEcoQgzItNiOk0WSzkrAOreywMAPjmMxi4of_LN1XWuKeyoatOZEJthX4oRNyCtTomoTCQw9HrPHYhbeAkwT0NZ_hLM8WHjMnJPzc7Rf0f8B2e7cPKGTqA8hz19hfV5wVajVfrwlN74NS6Ytv9IOGqxG--QZqkLeHUB35q6spRVbp2ZZw6OQgwfl2z2YETHHK7zQsD1RYXJVb42T8XFgo7YBJ2GWkfvU_G6eiFdLIJpIgCVhOeC6ZzQ20mZaJQU64klYzLQAcGeJALQ5MkNqEGoYFH9jjUplWQmywSeWASeomOyqqEK4RZYAR3jIBaZUxzrZg2YBM2axdbOUt5jfrOcMt1y4yx_LbZzR_zt6jnfNO2Wt2ho3rTwD06znZ1sd08eH9-AftDo4A
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA4yBT35a-Jvc_CaLW2SpjnK3Jg4x9A6dhtJk0LBtWNrB_73NmmdePDgLYRAyHuQ917yvu8D4J4zFkjmMyS0YIgSKlEYigAlhMaGS0sIQp3YBB-Pw9lMTBqwusPCGGNc85np2KH7y9d5XNqnsq6tTkRIqgp9l1Hq4xqu1XAJeVh0e6_TwAa1jhUFd0Sc3i_VFBc0Bof_3O4ItH_gd3CyDSzHYMdkJ-Bge1V9noJFf7FMHbkHjCpnrJs_JJhn8M21SKOoppz6gA9lkVuyStuwDCMrCGG0W1euNsZKDtndpqk2-RqmGZTw0T0YphJaaBK0OWkbvA_6UW-IGuEElPqYFoglnKpEkyqX0r6nCJOCCMoEVlgbhhOuSRgG2lOGK8P86jikSqxMomOfJ1iH5Ay0sjwz5wBSrDmznIBKxlQxJanSpkrZKrtUtbMQF6BtDTdf1twY82-bXf4xfwf2h9HLaD56Gj9fgQPrp7rx6hq0ilVpbsBevCnS9erW-fYLp1Cmxw
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%3Abook&rft.genre=proceeding&rft.title=2023+20th+Conference+on+Robots+and+Vision+%28CRV%29&rft.atitle=Empirical+Thresholding+on+Spatio-Temporal+Autoencoders+Trained+on+Surveillance+Videos+in+a+Dementia+Care+Unit&rft.au=Khan%2C+Shehroz+S.&rft.au=Mishra%2C+Pratik+K.&rft.au=Ye%2C+Bing&rft.au=Newman%2C+Kristine&rft.date=2023-06-01&rft.pub=IEEE&rft.spage=265&rft.epage=272&rft_id=info:doi/10.1109%2FCRV60082.2023.00041&rft.externalDocID=10229830