A modular and flexible system for activity recognition and smart home control based on nonobtrusive sensors

Abstract

This work describes a modular open source AAL framework for event recognition and smart home control. Various integrated tools simplify the configuration task, the personalization as well as the learning of activity models by a novel approach. Flexibility, standard compliant interfaces as well as the ability to transfer the system into new environments with little efforts have a strong focus. The paper describes the system architecture and the algorithms used.