Back to search

Institutes outside Greece

A smart well-being monitoring system for ambient assisted living of older adults

Abstract

dc:description

Cyber-physical systems (CPSs) are trying to connect a physical environment with a virtual one bringing a new era in healthcare. The research project aims to link a Cyber-physical network to eGRiST Decision Support System (DSS) in an automated way using the most e!cient techniques as well as ambient sensors provided by RedGear company. This dissertation presents our current accomplishments in designing a CPS on early detection of suicide risk factors for ambient assisted living and extracare monitoring. The contributions to science are threefold: The selection, evaluation and design of an innovative system for activity recognition in Ambient Assisted Living while proposing an innovative rule-based system called ”ActiRule”; the demonstration of a two-fold decision-making model for suicide risk factor detection, and the design of a suicide triage tool. The results highlight that Gaussian Hidden Markov Model is the bestperforming behavioural monitoring technique (F1-score=0.86), while the design of a two-layer system for scoring and interpreting an older adult’s behavioural change is promising. The overall performance of Multivariate Gaussian Mixture Model used for personalized decision-making, improves as we move from abrupt behavioural changes (F1-score=0.81) to gradual ones (F1-score=0.91). Also, the outcomes show that the development of a triage tool that includes the most informative questions to predict suicide is encouraging. For evaluation purposes, Orange4Home dataset is used for activity monitoring, a synthesized dataset based on the Aruba dataset for suicidal risk factor desicion making, and an older adult’s dataset for Triage Tool optimization. This study provides the foundation for scaling up and continuing this line of research, which investigates how decision support systems such as eGRiST, combined with ambient sensing technologies, can help clinicians rapidly assess mental health risk, understand its underlying causes, identify ways to reduce risk, and determine e”ective interventions.

Degree

thesis:*
Grantor dc:publisher
Institutes outside Greece
Year dc:date
2025

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Stefani, Anna
  • Στεφανή, Άννα

Subjects

dc:subject × 20

Rights

Language dc:language
eng

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/62718

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Stefani, Anna; Στεφανή, Άννα. A smart well-being monitoring system for ambient assisted living of older adults. Institutes outside Greece, 2025. http://hdl.handle.net/10442/hedi/62718