Mild Dementia Care at Home - Integrating Activity Monitoring, User Interface Plasticity and Scenario Verification

We discuss an integrated approach towards building systems for monitoring and assisting people with mild dementia in their homes. Our approach differs from existing approaches in three ways. First we improve context acquisition and understanding with the concept of micro-context that takes us beyond existing notions of location and temporal context; second, we incorporate plasticity concept into the human computer interface, in order to provide a natural interaction way and accommodative interface to the user; third we target robust and reliable systems that are easy to scale and deploy in diverse end-user settings, through the use of formal model building tools to specify and verify systems at key stages from requirements generation all the way to deployment and user statistics gathering. In order to address real-life end user requirements we are working closely with geriatric doctors and their staff, so as to get inputs as to precise challenges in caring for mild dementia patients, and how systems targeted at holistic, personalized assistance and care-giving can be built with a view towards scaled up deployment in diverse settings. The main contribution of this paper is an approach for system building that incorporates activity monitoring, user interface plasticity and scenario verification targeting people with cognitive decline in regards to a Singapore initiative called A-Star Home 2015 Phase II. We expect our work to lead to a methodology for systematic development of monitoring and assistive systems for cognitive interventions for mild dementia patients at home. Although the integrated framework is still not completely realized, the three areas mentioned above have each yielded significant results on their own, and these are mentioned in the paper.