TY - GEN
T1 - Identifying the Most Appropriate Classifier for Underpinning Assistive Technology Adoption for People with Dementia: An Integration of Fuzzy AHP and VIKOR Methods
AU - Ortiz-Barrios, Miguel
AU - Nugent, CD
AU - Garcia-Constantino, Matias
AU - Jimenez-Delgado, Genett
N1 - Funding Information:
Acknowledgments. This research has received funding under the REMIND project Marie Sklodowska-Curie EU Framework for Research and Innovation Horizon 2020, under Grant Agreement No. 734355. The authors also acknowledge the contribution of Giselle Paola Polifroni Avendaño who fully supported this investigation.
Publisher Copyright:
© Springer Nature Switzerland AG 2020.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/7/10
Y1 - 2020/7/10
N2 - Recently, the number of People with Dementia (PwD) has been rising exponentially across the world. The main symptoms that PwD experience include impairments of reasoning, memory, and thought. Owing to the burden faced by this chronic condition, Assistive Technology-based solutions (ATS) have been prescribed as a form of treatment. Nevertheless, it is widely acknowledged that low adoption rates of ATS have hampered their benefits within a health and social care context. It is then necessary to effectively discriminate between adopters and non-adopters of such solutions to avoid cost implications, improve the life quality of adopters, and find intervention alternatives for non-adopters. Several classifiers have been proposed as advancement towards the personalisation of self-management interventions for dementia in a scalable way. As multiple algorithms have been developed, an important step in technology adoption is to select the most appropriate classification alternative based on different criteria. This paper presents the integration of Fuzzy AHP (FAHP) and VIKOR to address this challenge. First, FAHP was used to calculate the criteria and sub-criteria weights under uncertainty and then VIKOR was implemented to rank the classifiers. A case study considering a mobile-based self-management and reminding solution for PwD is described to validate the proposed approach. The results revealed that Easiness of interpretation (GW = 0.192) and Handling of missing data (GW = 0.145) were the two most important criteria. Furthermore, SVM (Qj = 1.0) and AB (Qj = 0.891) were concluded to be the most suitable classifiers for supporting ATS adoption in PwD.
AB - Recently, the number of People with Dementia (PwD) has been rising exponentially across the world. The main symptoms that PwD experience include impairments of reasoning, memory, and thought. Owing to the burden faced by this chronic condition, Assistive Technology-based solutions (ATS) have been prescribed as a form of treatment. Nevertheless, it is widely acknowledged that low adoption rates of ATS have hampered their benefits within a health and social care context. It is then necessary to effectively discriminate between adopters and non-adopters of such solutions to avoid cost implications, improve the life quality of adopters, and find intervention alternatives for non-adopters. Several classifiers have been proposed as advancement towards the personalisation of self-management interventions for dementia in a scalable way. As multiple algorithms have been developed, an important step in technology adoption is to select the most appropriate classification alternative based on different criteria. This paper presents the integration of Fuzzy AHP (FAHP) and VIKOR to address this challenge. First, FAHP was used to calculate the criteria and sub-criteria weights under uncertainty and then VIKOR was implemented to rank the classifiers. A case study considering a mobile-based self-management and reminding solution for PwD is described to validate the proposed approach. The results revealed that Easiness of interpretation (GW = 0.192) and Handling of missing data (GW = 0.145) were the two most important criteria. Furthermore, SVM (Qj = 1.0) and AB (Qj = 0.891) were concluded to be the most suitable classifiers for supporting ATS adoption in PwD.
KW - Technology Adoption
KW - Dementia
KW - Fuzzy Analytic Hierarchy Process (FAHP)
KW - VIKOR
KW - Healthcare
UR - http://www.scopus.com/inward/record.url?scp=85088746972&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-49907-5_29
DO - 10.1007/978-3-030-49907-5_29
M3 - Conference contribution
SN - 978-3-030-49906-8
VL - 12199
T3 - Lecture Notes in Computer Science book series (LNCS, volume 12199)
SP - 406
EP - 419
BT - HCII 2020: Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management. Human Communication, Organization and Work
T2 - 22nd International Conference on Human-Computer Interaction,HCII 2020
Y2 - 19 July 2020 through 24 July 2020
ER -