Automated Discovery of Human Activities inside Pervasive Living Spaces

The recognition and detection of human activities constitutes a very important step towards the fulfilment of the notion of pervasive environments. By detecting patterns on those behaviours, an environment can adapt and respond to the inhabitants´ needs, thus improving the quality of life. This paper presents a framework in which those ideas can be applied and tested. It includes a system using a temporal neural-network driven embedded agent working with online, real-time data from a network of unobtrusive low-level sensors situated in either a simulated environment or a fully fitted real environment such as a whole flat