Design of a Home Sensing System for Monitoring Agitation in People with Dementia with Real-World Deployment Considerations
Dugan, Joshua, Computer Engineering - School of Engineering and Applied Science, University of Virginia
Lach, John, Department of Electrical and Computer Engineering, University of Virginia
Alzheimer’s disease affects a large number of elderly people throughout the world. Caring for a person with Alzheimer’s dementia who lives at home rather than in a nursing facility can be extremely taxing on the family of the person with dementia (PWD). Caregivers report high levels of stress and depression, and that episodes of agitation are the most difficult part of caring for a PWD. An inability to adequately deal with agitation is the most important reason caregivers cite for moving the PWD to a nursing facility. The Behavioral and Environmental Sensing and Intervention (BESI) project aims to increase the caregivers’ self-perceived ability to deal with agitation by predicting agitation events and providing the caregivers with real-time notifications and targeted interventions. Agitation is predicted based on the environmental conditions around the PWD measured continuously using a sensor system deployed in the home. Physical agitation and the behaviors that lead up agitation events are measured using a wearable inertial sensor on the PWD. The inertial and environmental data will be fed into a model personalized to each PWD that predicts agitation and suggests targeted interventions to the caregivers.
This thesis presents the design of a sensor system for use in the BESI project that measures the environmental conditions in a house occupied by a caregiver and a PWD and detects agitation using a wearable accelerometer on the PWD. The system continuously collects sensor data from multiple rooms, and aggregates it in a central location for analysis. Designing home monitoring systems like this one, presents a number of significant engineering challenges that need to be addressed to collect, transmit, and synchronize data from many disparate sensing modalities. These challenges along with considerations for in-home deployment, such as system reliability, monitoring, repair, and appearance are discussed. The sensor system has been deployed in the homes’ of two caregiver-PWD dyads with each deployment lasting seven days, and the results from these deployments are presented in terms of the amount of data collected from the environmental and body-worn sensors.
MS (Master of Science)
Home Sensing, Body-Sensor Networks, Dementia Agitation
English
2016/07/29