Human Behavior Drift Detection in a Smart Home Environment
Andrea Masciadri, Trofimova Anna A., Matteucci Matteo, Fabio Salice · Studies in health technology and informatics · 2017
The proposed system aims at elderly people independent living by providing an early indicator of habits changes which might be relevant for a diagnosis of diseases. It relies on Hidden Markov Model to describe the behavior observing sensors data, while Likelihood Ratio Test gives the variation within different time periods.