Alzheimer’s Disease (AD) and other forms of dementia constitute a large-scale public health concern with significant number of people with dementia being at risk of wandering and getting lost. These individuals may get hurt, cause distress to families and caregivers, and require costly search parties. Ubiquitous presence of IoT health technologies including health trackers, GPS devices, smartwatches and other wearables open new possibilities for improving safety and care for individuals with AD. In the presented work, we utilize GPS SmartSole by GTX Corp., one of several types of trackers available on the market, to assess feasibility of finding and predicting movement patterns to aid in searching for missing people with AD and to better understand wandering. Spatiotemporal clustering and supervised learning are used to detect and classify patterns of movementt of people with AD. Results indicate overall high average accuracy, but predictibility depends on specific individuals and theri routines.

Learning Objective: After participating in this session, the learner should be better able to:
- Understand importance of IoT and GPS technologies to track people with Alzheimer's Disease
- Undesstand use of GPS trackers to model patterns of movement for people with AD
- Apply spatiotemporal clustering and supervised learning to GPS data


Janusz Wojtusiak (Presenter)
George Mason University

Reyhaneh Mogharabnia, George Mason University
U. Nalla Durai, Department of Veterans Administration
Beverly Middle, George Mason University
Robert Koester, dbs-sar
Catherine Tompkins, George Mason University

Presentation Materials: