Predictive Behavioural Monitoring and Deviation Detection in Activities of Daily Living of Older Adults

Jiawei Zheng; Petros Papapanagiotou

doi:10.5220/0010974500003123

Predictive Behavioural Monitoring and Deviation Detection in Activities of Daily Living of Older Adults

Jiawei Zheng, Petros Papapanagiotou

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

Abstract / Description of output

Predictive behaviour monitoring of Activities of Daily Living (ADLs) can provide unique, personalised insights about an older person’s physical and cognitive health and lead to unique opportunities to support self- management, proactive intervention and promote independent living. In this paper, we analyse ADL data from ambient sensors to model behaviour markers on a daily basis. Using a number of machine learning and statistical methods we model a predicted daily routine for each marker, detect deviations based on a set of relative thresholds and calculate long-term drifts. We further analyse the causal factors of deviations by investigating relationships between different activities. We demonstrate our results using data from a sample of 11 participants from the CASAS dataset. Finally, we develop a dashboard to visualize our computed daily routines and quantified deviations in an attempt to offer useful feedback to the monitored person and their caregivers.

Original language	English
Title of host publication	15th International Joint Conference on Biomedical Engineering Systems and Technologies, Volume 5 - HEALTHINF
Editors	Nathalie Bier, Ana Fred, Hugo Gamboa
Publisher	SCITEPRESS
Pages	899-910
Number of pages	12
Volume	5
ISBN (Electronic)	978-989-758-552-4
DOIs	https://doi.org/10.5220/0010974500003123
Publication status	Published - 24 Feb 2022
Event	15th International Conference on Health Informatics 2022 - Virtual Conference Duration: 9 Feb 2022 → 11 Feb 2022 Conference number: 15 https://healthinf.scitevents.org/?y=2022

Publication series

Name
Volume	5
ISSN (Electronic)	2184-4305

Conference

Conference	15th International Conference on Health Informatics 2022
Abbreviated title	HEALTHINF 2022
Period	9/02/22 → 11/02/22
Internet address	https://healthinf.scitevents.org/?y=2022

Keywords / Materials (for Non-textual outputs)

Activities of Daily Living
Behaviour Monitoring
Deviation Detection
Predictive Modelling
Sensor Data

Access to Document

10.5220/0010974500003123Licence: Creative Commons: Attribution-NonCommercial-NoDerivatives (CC BY-NC-ND)

PredictiveBehavioural_ZHENG_DOA15112021_VOR_CC-BY-NC-NDFinal published version, 675 KBLicence: Creative Commons: Attribution-NonCommercial-NoDerivatives (CC BY-NC-ND)

https://www.scitepress.org/PublicationsDetail.aspx?ID=i19VylVxeoc=&t=1Licence: Creative Commons: Attribution-NonCommercial-NoDerivatives (CC BY-NC-ND)

Cite this

Zheng, J., & Papapanagiotou, P. (2022). Predictive Behavioural Monitoring and Deviation Detection in Activities of Daily Living of Older Adults. In N. Bier, A. Fred, & H. Gamboa (Eds.), 15th International Joint Conference on Biomedical Engineering Systems and Technologies, Volume 5 - HEALTHINF (Vol. 5, pp. 899-910). SCITEPRESS. https://doi.org/10.5220/0010974500003123

@inproceedings{606cae8545314030869685fccf2548ba,

title = "Predictive Behavioural Monitoring and Deviation Detection in Activities of Daily Living of Older Adults",

abstract = "Predictive behaviour monitoring of Activities of Daily Living (ADLs) can provide unique, personalised insights about an older person{\textquoteright}s physical and cognitive health and lead to unique opportunities to support self- management, proactive intervention and promote independent living. In this paper, we analyse ADL data from ambient sensors to model behaviour markers on a daily basis. Using a number of machine learning and statistical methods we model a predicted daily routine for each marker, detect deviations based on a set of relative thresholds and calculate long-term drifts. We further analyse the causal factors of deviations by investigating relationships between different activities. We demonstrate our results using data from a sample of 11 participants from the CASAS dataset. Finally, we develop a dashboard to visualize our computed daily routines and quantified deviations in an attempt to offer useful feedback to the monitored person and their caregivers.",

keywords = "Activities of Daily Living, Behaviour Monitoring, Deviation Detection, Predictive Modelling, Sensor Data",

author = "Jiawei Zheng and Petros Papapanagiotou",

year = "2022",

month = feb,

day = "24",

doi = "10.5220/0010974500003123",

language = "English",

volume = "5",

publisher = "SCITEPRESS",

pages = "899--910",

editor = "Nathalie Bier and Ana Fred and Hugo Gamboa",

booktitle = "15th International Joint Conference on Biomedical Engineering Systems and Technologies, Volume 5 - HEALTHINF",

note = "15th International Conference on Health Informatics 2022, HEALTHINF 2022 ; Conference date: 09-02-2022 Through 11-02-2022",

url = "https://healthinf.scitevents.org/?y=2022",

}

Zheng, J & Papapanagiotou, P 2022, Predictive Behavioural Monitoring and Deviation Detection in Activities of Daily Living of Older Adults. in N Bier, A Fred & H Gamboa (eds), 15th International Joint Conference on Biomedical Engineering Systems and Technologies, Volume 5 - HEALTHINF. vol. 5, SCITEPRESS, pp. 899-910, 15th International Conference on Health Informatics 2022, 9/02/22. https://doi.org/10.5220/0010974500003123

Predictive Behavioural Monitoring and Deviation Detection in Activities of Daily Living of Older Adults. / Zheng, Jiawei; Papapanagiotou, Petros.
15th International Joint Conference on Biomedical Engineering Systems and Technologies, Volume 5 - HEALTHINF. ed. / Nathalie Bier; Ana Fred; Hugo Gamboa. Vol. 5 SCITEPRESS, 2022. p. 899-910.

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

TY - GEN

T1 - Predictive Behavioural Monitoring and Deviation Detection in Activities of Daily Living of Older Adults

AU - Zheng, Jiawei

AU - Papapanagiotou, Petros

N1 - Conference code: 15

PY - 2022/2/24

Y1 - 2022/2/24

N2 - Predictive behaviour monitoring of Activities of Daily Living (ADLs) can provide unique, personalised insights about an older person’s physical and cognitive health and lead to unique opportunities to support self- management, proactive intervention and promote independent living. In this paper, we analyse ADL data from ambient sensors to model behaviour markers on a daily basis. Using a number of machine learning and statistical methods we model a predicted daily routine for each marker, detect deviations based on a set of relative thresholds and calculate long-term drifts. We further analyse the causal factors of deviations by investigating relationships between different activities. We demonstrate our results using data from a sample of 11 participants from the CASAS dataset. Finally, we develop a dashboard to visualize our computed daily routines and quantified deviations in an attempt to offer useful feedback to the monitored person and their caregivers.

AB - Predictive behaviour monitoring of Activities of Daily Living (ADLs) can provide unique, personalised insights about an older person’s physical and cognitive health and lead to unique opportunities to support self- management, proactive intervention and promote independent living. In this paper, we analyse ADL data from ambient sensors to model behaviour markers on a daily basis. Using a number of machine learning and statistical methods we model a predicted daily routine for each marker, detect deviations based on a set of relative thresholds and calculate long-term drifts. We further analyse the causal factors of deviations by investigating relationships between different activities. We demonstrate our results using data from a sample of 11 participants from the CASAS dataset. Finally, we develop a dashboard to visualize our computed daily routines and quantified deviations in an attempt to offer useful feedback to the monitored person and their caregivers.

KW - Activities of Daily Living

KW - Behaviour Monitoring

KW - Deviation Detection

KW - Predictive Modelling

KW - Sensor Data

U2 - 10.5220/0010974500003123

DO - 10.5220/0010974500003123

M3 - Conference contribution

VL - 5

SP - 899

EP - 910

BT - 15th International Joint Conference on Biomedical Engineering Systems and Technologies, Volume 5 - HEALTHINF

A2 - Bier, Nathalie

A2 - Fred, Ana

A2 - Gamboa, Hugo

PB - SCITEPRESS

T2 - 15th International Conference on Health Informatics 2022

Y2 - 9 February 2022 through 11 February 2022

ER -

Predictive Behavioural Monitoring and Deviation Detection in Activities of Daily Living of Older Adults

Abstract / Description of output

Publication series

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this