An event-driven approach to activity recognition in ambient assisted living

One central challenge of Ambient Assisted Living systems is reliable recognition of the assisted person's current behavior, so that adequate assistance services can be offered in a specific situation. In the context of emergency support, such a situation might be an acute emergency situation or a deviation from the usual behavior. To optimize prevention of emergencies, reliable recognition of charac teristic Activities of Daily Living (ADLs) is promising. In this paper, we present our approach to processing information for the detection of ADLs in the EMERGE project. The approach is based on our multi-agent activity recog nition framework EARS with its special definition language EARL. An evaluation with controlled experiments has proven its suitability.