Skip to Main Content
The paper describes a year-long experiment dedicated to the development, deployment and evaluation of a system for coarse assessment of the state of dementia patients in a real world nursing home. The system is based on the analysis of users' motion patterns between broadly defined, semantically meaningful areas of the living space. On a data set recorded from six inhabitants in different stages of dementia during a year (a total of about 900 individual daily traces organized in groups of 14 days) a recognition accuracy of 92% is demonstrated for a two state problem (positive, negative)with 3 subjects having perfect (100%) recognition. For the 3 state problem (positive, normal, negative) we get 80% with one case of perfect recognition. We present an elaborate evaluation of the methods' performance and describe relevant practical issues involved in the design and deployment in the nursing home.