Abstract. With the ever-growing prevalence of dementia, nursing costs are increasing, while the ability to live independently vanishes. Dem@Home is an ambient assisted living framework to support independent living while receiving intelligent clinical care. Dem@Home integrates a variety of ambient and wearable sensors together with sophisticated, interdisciplinary methods of image and semantic analysis. Semantic Web technologies, such as OWL 2, are extensively employed to represent sensor observations and application domain specifics as well as to implement hybrid activity recognition and problem detection. Complete with tailored user interfaces, clinicians are provided with accurate monitoring of multiple life aspects, such as physical activity, sleep, complex daily tasks and clinical problems, leading to adaptive non-pharmaceutical interventions. The method has been already validated for both recognition performance and improvement on a clinical level, in four home pilots.