AIoT for aging in place: from theory to practice

The rapidly aging global population necessitates solutions to support the growing preference among seniors to age in place. This thesis presents a novel integration of the Person-Environment (P-E) Fit theory with Artificial Intelligence of Things (AIoT) to guide aging in place (AIP) system design, f...

Full description

Saved in:
Bibliographic Details
Main Author: Zhang, Huiguo
Other Authors: Vun Chan Hua, Nicholas
Format: Thesis-Doctor of Philosophy
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/175547
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:The rapidly aging global population necessitates solutions to support the growing preference among seniors to age in place. This thesis presents a novel integration of the Person-Environment (P-E) Fit theory with Artificial Intelligence of Things (AIoT) to guide aging in place (AIP) system design, focusing on personalized, privacy-preserving solutions that allow elderly individuals to live independently while ensuring their safety and well-being. Based on the foundation of the P-E Fit theory, we introduce a comprehensive P-E for AIP model (PE4AIP) that assesses elderly well-being through three primary dimensions: person characteristics, environment characteristics, and person-environment interactions. The model identifies key P-E fit indicators, such as motion, lifestyle regularity, social interactions, and environmental comfort, which are essential for quantifying the `fit' between seniors and their environments. To operationalize this model, a PE4AIP-enabled AIP design architecture was developed, guiding the creation of AIP systems with a emphasis on privacy and personalization. Notably, the developed architecture incorporates innovative technologies for real-time monitoring and data processing, including a non-intrusive fall detection system using ambient sensors and edge computing, and a unique notification system using 3D animation to communicate the status of the elderly to caregivers without compromising privacy. Empirical studies and experiments validate the effectiveness of the proposed model and the architecture. A implementation of the Smart Aging in Place System (SAIPS) demonstrated the practicality and acceptance of the system among elderly participants and their caregivers. The results highlight the system’s accuracy in predicting well-being, its unobtrusiveness, and the overall positive reception of the technology. This research advances gerontechnology by offering a theoretically grounded and empirically validated framework that enhances the independence and quality of life for the elderly. The breadth and depth of our work stand as a meaningful contribution to the development of intelligent, practical, and effective aging-in-place solutions, with wide-reaching implications for the continually evolving field of assistive technology for older adults.