Technology-supported Aging in Place

Abstract

Aging in place is a priority for many older adults, but challenges such as reduced mobility, cognitive decline, and increased risk of injury can compromise their independence and well-being. Early detection of changes in health and behavior is critical to preventing emergencies, yet current monitoring methods often raise privacy concerns or are too intrusive. This research is part of a bigger project to identify activities of daily living and track those changes over time. This study explores a non-invasive approach to monitor activities of daily living (ADLs) using relative signal strength indicator (RSSI) data from an Apple AirTag worn on the wrist, tracked through strategically placed smartphones within the home. The system estimates the location of the wearer and infers patterns of movement to approximate ADLs. By establishing a behavioral baseline, deviations may indicate emerging health concerns. Preliminary results show that room-level positioning using RSSI data can effectively identify key daily routines such as sleep, kitchen use, and bathroom visits. This foundational work sets the stage for training AI models to detect significant deviations that could trigger healthcare provider alerts. Future work will focus on improving localization accuracy, expanding the dataset, and integrating machine learning models to support timely interventions in care for older adults.