Sensor data fusion for activity monitoring in the PERSONA ambient assisted living project

User activity monitoring is a major problem in Ambient Assisted Living, since it requires to infer new knowledge from collected and fused sensor data while dealing with highly dynamic environments, where devices continu- ously change their availability and (or) physical location. In the context of the European project PERSONA, we have developed an activity monitoring sub- system characterized by high modularity, little invasiveness of the environment and good responsiveness. In this paper we rst illustrate the functional archi- tecture of the proposed solution from a general point of view, discussing the motivations of the design. Then we describe in details the software components - Sensor Abstraction and Integration Layer, Human Posture Classi cation, Ac- tivity Monitor - and the resulting activity monitoring application, presenting also a performance evaluation.