A statistical-relational activity recognition framework for ambient assisted living systems

Smart environments with ubiquitous sensing technologies are a promising perspective for reliable and continuous healthcare systems with reduced costs. A primary challenge for such assisted living systems is the automated recognition of everyday activities carried out by humans in their own home. In this work, we investigate the use of Markov Logic Networks as a framework for activity recognition within intelligent home-like environments equipped with pervasive light-weight sensor technologies. In particular, we explore the ability of MLNs to capture temporal relations and background knowledge for improving the recognition performance