Sensor based micro context for mild dementia assistance

Abstract

Due to decline in their cognitive function, elderly people with mild dementia living alone at home are at risk of making errors in their activities of daily living (ADLs). In order to help such people, most activity recognition systems for assistive living in smart homes attempt to classify activities from coarse grained context such as location or time of day. Location by itself however, does not provide adequate context information for the recognition of ADLs and instrumental ADLs. It does not help to know that a person is in the kitchen if we are interested in knowing whether or not he has taken his meal (ADL) or prepared it (iADL). Additional information about the activity is needed. In this paper micro-context is introduced as a key aspect both for activity recognition as well as for prompted correction. Initial results from our laboratory experiments are presented herein, and it is shown that micro-context is useful for both activity recognition and prompted error correction.