Institutes outside Greece
A smart well-being monitoring system for ambient assisted living of older adults
Abstract
dc:descriptionCyber-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- Υποστηριζόμενη Διαβίωση σε Έξυπνο Περιβάλλον
- Αναγνώριση δραστηριότητας ανθρώπου
- Ανίχνευση Παραγόντων Κινδύνου Αυτοκτονίας
- Κυβερνο-φυσικά συστήματα
- Cyber-physical system
- Ambient assisted living
- Human activity recognition
- Suicide Risk Factors Detection
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Φυσικές Επιστήμες
- Τεχνητή νοημοσύνη
- Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ
- Επιστήμες Μηχανικού και Τεχνολογία
- Αυτοματισμοί και Συστήματα ελέγχου
- Computer and Information Sciences
- Natural Sciences
- Artificial Intelligence
- Electrical Engineering, Electronic Engineering, Information Engineering
- Engineering and Technology
- Automation and control systems
Rights
- Language dc:language
- eng
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/62718