A keyhole plan recognition model for alzheimer's patients: First results

Abstract

This article addresses the problem of recognizing the behavior of a person suffering from Alzheimer's disease at early-intermediate stages. We present a keyhole plan recognition model, based on lattice theory and action description logic, which transforms the recognition problem into a classification issue. This approach allows us to formalize the plausible incoherent intentions of the patient, resulting from the symptoms of his cognitive impairment, such as disorientation, memory lapse, etc. An implementation of this model was tested in our smart home laboratory, by simulating a set of real case scenarios.