AVEID: Automatic video system for measuring engagement in dementia

Viral Parekh; Pin Sym Foong; Shendong Zhao; Ramanathan Subramanian

doi:10.1145/3172944.3173010

AVEID: Automatic video system for measuring engagement in dementia

Viral Parekh, Pin Sym Foong, Shendong Zhao, Ramanathan Subramanian

Research output: Contribution to conference (non-published works) › Paper › peer-review

15 Citations (Scopus)

Abstract

Engagement in dementia is typically measured using behavior observational scales (BOS) that are tedious and involve intensive manual labor to annotate, and are therefore not easily scalable. We propose AVEID, a low cost and easy-to-use video-based engagement measurement tool to determine the engagement level of a person with dementia (PwD) during digital interaction. We show that the objective behavioral measures computed via AVEID correlate well with subjective expert impressions for the popular MPES and OME BOS, confirming its viability and effectiveness. Moreover, AVEID measures can be obtained for a variety of engagement designs, thereby facilitating large-scale studies with PwD populations.

Original language	English
Pages	409-413
Number of pages	5
DOIs	https://doi.org/10.1145/3172944.3173010
Publication status	Published - 5 Mar 2018
Externally published	Yes
Event	23rd ACM International Conference on Intelligent User Interfaces, IUI 2018 - Tokyo, Japan Duration: 7 Mar 2018 → 11 Mar 2018

Conference

Conference	23rd ACM International Conference on Intelligent User Interfaces, IUI 2018
Country/Territory	Japan
City	Tokyo
Period	7/03/18 → 11/03/18

Access to Document

10.1145/3172944.3173010

Cite this

@conference{a46c55bd5c294b66850b3d30800ba39d,

title = "AVEID: Automatic video system for measuring engagement in dementia",

abstract = "Engagement in dementia is typically measured using behavior observational scales (BOS) that are tedious and involve intensive manual labor to annotate, and are therefore not easily scalable. We propose AVEID, a low cost and easy-to-use video-based engagement measurement tool to determine the engagement level of a person with dementia (PwD) during digital interaction. We show that the objective behavioral measures computed via AVEID correlate well with subjective expert impressions for the popular MPES and OME BOS, confirming its viability and effectiveness. Moreover, AVEID measures can be obtained for a variety of engagement designs, thereby facilitating large-scale studies with PwD populations.",

keywords = "Dementia, Engagement, Video-based analytics",

author = "Viral Parekh and Foong, {Pin Sym} and Shendong Zhao and Ramanathan Subramanian",

note = "Publisher Copyright: {\textcopyright} 2018 Copyright held by the owner/author(s). Publication rights licensed to ACM. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.; 23rd ACM International Conference on Intelligent User Interfaces, IUI 2018 ; Conference date: 07-03-2018 Through 11-03-2018",

year = "2018",

month = mar,

day = "5",

doi = "10.1145/3172944.3173010",

language = "English",

pages = "409--413",

}

TY - CONF

T1 - AVEID

T2 - 23rd ACM International Conference on Intelligent User Interfaces, IUI 2018

AU - Parekh, Viral

AU - Foong, Pin Sym

AU - Zhao, Shendong

AU - Subramanian, Ramanathan

PY - 2018/3/5

Y1 - 2018/3/5

N2 - Engagement in dementia is typically measured using behavior observational scales (BOS) that are tedious and involve intensive manual labor to annotate, and are therefore not easily scalable. We propose AVEID, a low cost and easy-to-use video-based engagement measurement tool to determine the engagement level of a person with dementia (PwD) during digital interaction. We show that the objective behavioral measures computed via AVEID correlate well with subjective expert impressions for the popular MPES and OME BOS, confirming its viability and effectiveness. Moreover, AVEID measures can be obtained for a variety of engagement designs, thereby facilitating large-scale studies with PwD populations.

AB - Engagement in dementia is typically measured using behavior observational scales (BOS) that are tedious and involve intensive manual labor to annotate, and are therefore not easily scalable. We propose AVEID, a low cost and easy-to-use video-based engagement measurement tool to determine the engagement level of a person with dementia (PwD) during digital interaction. We show that the objective behavioral measures computed via AVEID correlate well with subjective expert impressions for the popular MPES and OME BOS, confirming its viability and effectiveness. Moreover, AVEID measures can be obtained for a variety of engagement designs, thereby facilitating large-scale studies with PwD populations.

KW - Dementia

KW - Engagement

KW - Video-based analytics

UR - http://www.scopus.com/inward/record.url?scp=85045452178&partnerID=8YFLogxK

UR - https://dl.acm.org/doi/proceedings/10.1145/3172944

U2 - 10.1145/3172944.3173010

DO - 10.1145/3172944.3173010

M3 - Paper

AN - SCOPUS:85045452178

SP - 409

EP - 413

Y2 - 7 March 2018 through 11 March 2018

ER -

AVEID: Automatic video system for measuring engagement in dementia

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this