Demo abstract: Alzimio: A mobile app with geofencing, activity-recognition and safety features for dementia patients

Dementia, Autism, and Alzheimer's disorders affect millions of people worldwide. Suffering from forgetfulness, affected patients tend to wander off and potentially get into dangerous situations. This work develops the Alzimio mobile app, to provide safety functions to these patients; including safe-zone geofencing, activity-based alarms, take-me-home, navigate to nearest friend, and check-on-me. Six main design goals guided the design of Alzimio, including periodic safety checks, refined user control, flexibility and efficiency of alarms, and optimized operation, among others. Providing reliable continuous sensing and operation without drastically affecting battery lifetime provided a challenge. Such challenge is not unique to Alzimio, but is general to most IoT healthcare devices. Novel activity-recognition and geofencing algorithms are designed and optimized to meet the goals and overcome the challenge. The app was evaluated using extensive scenarios of usage for several months. Alzimio is able to achieve over 95% accuracy in less than 30 sec in most scenarios. The optimal threshold was found to be 65, to achieve best accuracy and delay. The phone was able to last throughout the day in our tests, which is very promising.