Scenario recognition for temporal reasoning in medical domains.

The recognition of high level clinical scenes is fundamental in patient monitoring. In this paper, we propose a technique for recognizing a session, i.e. the clinical process evolution, by comparison against a predetermined set of scenarios, i.e. the possible behaviors for this process. We use temporal constraint networks to represent both scenario and session. Specific operations on networks are then applied to perform the recognition task. An index of temporal proximity is introduced to quantify the degree of matching between two temporal networks in order to select the best scenario fitting a session. We explore the application of our technique, implemented in the Déjà Vu system, to the recognition of typical medical scenarios with both precise and imprecise temporal information.

An approach by graphs for the recognition of temporal scenarios.

This paper presents an approach by graphs for the recognition of temporal scenarios, that represent models of the dynamical behavior of a system. The aim of the presented work is to analyze the relative situation of a scenario and an effective behavior of the system, called a session. Different symbolic levels of recognition are proposed to qualify this status. All these levels, as well as most of the properties, are formulated in terms of graphs of temporal constraints. Different contexts are analyzed, where the session is either statically built, when considered as a history, or dynamically built, when information is treated in an incremental manner or on-line. In a second phase, each status is refined using a numeric estimation of the proximity between a scenario and a session. This estimation is performed by calculating an overlapping index or a temporal difference index between the volumes of the domains corresponding to the temporal graphs of the scenario and the session.