PROJECT TITLE :

Activity Discovery and Detection of Behavioral Deviations of an Inhabitant From Binary Sensors

ABSTRACT:

The aim of this paper is to improve the autonomy of medically monitored patients in a good home instrumented solely with binary sensors; overwatching the disease evolution, which will be characterized by behavior changes, is helped by detecting the activities the inhabitant performs. 2 contributions are presented. On one hand, using sequence mining ways within the flow of sensor events, the foremost frequent patterns mirroring activities of the inhabitant are discovered; these activities are then modeled by an extended finite automaton, that can then be used for activity recognition and generate activity events. On the other hand, given the set of activities that may be recognized, another automaton is built to model necessities from the medical staff supervising the inhabitant; it accepts activity events, and residuals are outlined to detect any behavior deviation. The whole method is applied to the dataset of Domus, an instrumented smart home.