Evaluation of ADL detection in the EMERGE project

This paper presents the results of the empirical evaluation for detecting Activities of Daily Living (ADL) in the research project EMERGE. EMERGE uses ADLs as a basic layer for determining the functional health status of a person and thereupon preventing emergencies with long-term behavior monitoring and behavior deviation assessment. Several formal experiments in a near-real-life laboratory setting were performed to evaluate the accuracy of recognizing ADLs with totally ambient and unobtrusive sensors. Results show that it is possible to detect ADLs with respect to potentially arising emergency situations with an accuracy of 92% on average. Hence, we conclude that it is possible to support elderly people in staying longer in their homes by autonomously detecting potentially arising emergencies on the basis of ADL monitoring and behavior deviation assessment without body mounted or obtrusive sensors such as accelerometers or cameras.