Probabilistic Analysis of Abnormal Behaviour Detection in Activities of Daily Living

Matias Garcia-Constantino, Alexandros Konios, Idongesit Ekerete, Stavros Christopoulos, Colin Shewell, Chris Nugent, Gareth Morrison

Research output: Chapter in Book/Report/Conference proceedingConference proceeding

9 Downloads (Pure)

Abstract

This paper presents a probabilistic approach for the identification of abnormal behaviour in Activities of Daily Living(ADLs) from sensor data collected from 30 participants. The ADLs considered are: (i) preparing and drinking tea, and (ii)preparing and drinking coffee. Abnormal behaviour identified in the context of these activities can be an indicator of a progressive health problem or the occurrence of a hazardous incident. The approach presented considers the temporal aspect of the sequences of actions that are part of each ADL and that vary between participants. The average and standard deviation for the duration of each action were calculated to define an average time and a range in which a behaviour could be considered as normal for each stage and activity. The Cumulative Distribution Function (CDF) was used to obtain the probabilities of abnormal behaviours related to the early and late completion of activities and stages within an activity. The data analysis shows that CDF can provide accurate and reliable results regarding the presence of abnormal behaviour in stages and activities that last over a minute. Finally, this approach could be used to train machine learning algorithms for the abnormal behaviour detection.
Original languageEnglish
Title of host publicationProceedings of IEEE International Conference on Pervasive Computing and Communications 2019
PublisherIEEE
Pages(In-Press)
Volume(In-Press)
Publication statusAccepted/In press - Jan 2019
EventIEEE International Conference on Pervasive Computing and Communications - Kyoto, Japan
Duration: 11 Mar 201915 Mar 2019
http://www.percom.org/home

Conference

ConferenceIEEE International Conference on Pervasive Computing and Communications
Abbreviated titlePerCom 2019
CountryJapan
CityKyoto
Period11/03/1915/03/19
Internet address

Fingerprint

Distribution functions
Coffee
Medical problems
Learning algorithms
Learning systems
Sensors
Tea

Cite this

Garcia-Constantino, M., Konios, A., Ekerete, I., Christopoulos, S., Shewell, C., Nugent, C., & Morrison, G. (Accepted/In press). Probabilistic Analysis of Abnormal Behaviour Detection in Activities of Daily Living. In Proceedings of IEEE International Conference on Pervasive Computing and Communications 2019 (Vol. (In-Press), pp. (In-Press)). IEEE.

Probabilistic Analysis of Abnormal Behaviour Detection in Activities of Daily Living. / Garcia-Constantino, Matias; Konios, Alexandros; Ekerete, Idongesit; Christopoulos, Stavros; Shewell, Colin; Nugent, Chris; Morrison, Gareth.

Proceedings of IEEE International Conference on Pervasive Computing and Communications 2019. Vol. (In-Press) IEEE, 2019. p. (In-Press).

Research output: Chapter in Book/Report/Conference proceedingConference proceeding

Garcia-Constantino, M, Konios, A, Ekerete, I, Christopoulos, S, Shewell, C, Nugent, C & Morrison, G 2019, Probabilistic Analysis of Abnormal Behaviour Detection in Activities of Daily Living. in Proceedings of IEEE International Conference on Pervasive Computing and Communications 2019. vol. (In-Press), IEEE, pp. (In-Press), IEEE International Conference on Pervasive Computing and Communications, Kyoto, Japan, 11/03/19.
Garcia-Constantino M, Konios A, Ekerete I, Christopoulos S, Shewell C, Nugent C et al. Probabilistic Analysis of Abnormal Behaviour Detection in Activities of Daily Living. In Proceedings of IEEE International Conference on Pervasive Computing and Communications 2019. Vol. (In-Press). IEEE. 2019. p. (In-Press)
Garcia-Constantino, Matias ; Konios, Alexandros ; Ekerete, Idongesit ; Christopoulos, Stavros ; Shewell, Colin ; Nugent, Chris ; Morrison, Gareth. / Probabilistic Analysis of Abnormal Behaviour Detection in Activities of Daily Living. Proceedings of IEEE International Conference on Pervasive Computing and Communications 2019. Vol. (In-Press) IEEE, 2019. pp. (In-Press)
@inproceedings{9879aaaadd744a70b491ff85507f7a4c,
title = "Probabilistic Analysis of Abnormal Behaviour Detection in Activities of Daily Living",
abstract = "This paper presents a probabilistic approach for the identification of abnormal behaviour in Activities of Daily Living(ADLs) from sensor data collected from 30 participants. The ADLs considered are: (i) preparing and drinking tea, and (ii)preparing and drinking coffee. Abnormal behaviour identified in the context of these activities can be an indicator of a progressive health problem or the occurrence of a hazardous incident. The approach presented considers the temporal aspect of the sequences of actions that are part of each ADL and that vary between participants. The average and standard deviation for the duration of each action were calculated to define an average time and a range in which a behaviour could be considered as normal for each stage and activity. The Cumulative Distribution Function (CDF) was used to obtain the probabilities of abnormal behaviours related to the early and late completion of activities and stages within an activity. The data analysis shows that CDF can provide accurate and reliable results regarding the presence of abnormal behaviour in stages and activities that last over a minute. Finally, this approach could be used to train machine learning algorithms for the abnormal behaviour detection.",
author = "Matias Garcia-Constantino and Alexandros Konios and Idongesit Ekerete and Stavros Christopoulos and Colin Shewell and Chris Nugent and Gareth Morrison",
year = "2019",
month = "1",
language = "English",
volume = "(In-Press)",
pages = "(In--Press)",
booktitle = "Proceedings of IEEE International Conference on Pervasive Computing and Communications 2019",
publisher = "IEEE",

}

TY - GEN

T1 - Probabilistic Analysis of Abnormal Behaviour Detection in Activities of Daily Living

AU - Garcia-Constantino, Matias

AU - Konios, Alexandros

AU - Ekerete, Idongesit

AU - Christopoulos, Stavros

AU - Shewell, Colin

AU - Nugent, Chris

AU - Morrison, Gareth

PY - 2019/1

Y1 - 2019/1

N2 - This paper presents a probabilistic approach for the identification of abnormal behaviour in Activities of Daily Living(ADLs) from sensor data collected from 30 participants. The ADLs considered are: (i) preparing and drinking tea, and (ii)preparing and drinking coffee. Abnormal behaviour identified in the context of these activities can be an indicator of a progressive health problem or the occurrence of a hazardous incident. The approach presented considers the temporal aspect of the sequences of actions that are part of each ADL and that vary between participants. The average and standard deviation for the duration of each action were calculated to define an average time and a range in which a behaviour could be considered as normal for each stage and activity. The Cumulative Distribution Function (CDF) was used to obtain the probabilities of abnormal behaviours related to the early and late completion of activities and stages within an activity. The data analysis shows that CDF can provide accurate and reliable results regarding the presence of abnormal behaviour in stages and activities that last over a minute. Finally, this approach could be used to train machine learning algorithms for the abnormal behaviour detection.

AB - This paper presents a probabilistic approach for the identification of abnormal behaviour in Activities of Daily Living(ADLs) from sensor data collected from 30 participants. The ADLs considered are: (i) preparing and drinking tea, and (ii)preparing and drinking coffee. Abnormal behaviour identified in the context of these activities can be an indicator of a progressive health problem or the occurrence of a hazardous incident. The approach presented considers the temporal aspect of the sequences of actions that are part of each ADL and that vary between participants. The average and standard deviation for the duration of each action were calculated to define an average time and a range in which a behaviour could be considered as normal for each stage and activity. The Cumulative Distribution Function (CDF) was used to obtain the probabilities of abnormal behaviours related to the early and late completion of activities and stages within an activity. The data analysis shows that CDF can provide accurate and reliable results regarding the presence of abnormal behaviour in stages and activities that last over a minute. Finally, this approach could be used to train machine learning algorithms for the abnormal behaviour detection.

M3 - Conference proceeding

VL - (In-Press)

SP - (In-Press)

BT - Proceedings of IEEE International Conference on Pervasive Computing and Communications 2019

PB - IEEE

ER -