Uma abordagem de fusão de sinais vitais baseada em redes bayesianas

Abstract

It is proposed in this paper the use of probabilistic nets (with the use of Bayesian network technique) for vital and movement signal fusion. The signals are acquired by a mobile telemonitoring system for patients at home (called RFPAT), developed for automatic identification of urgent situations. The advantages of probabilistic network are shown, as well as the methodology used to perform the sensor signal classification. Finally, the applicability of the system as an important tool to assist elderly patients or patients with cardiac diseases attendance hospitalized at home is demonstrated through experiments. © Springer-Verlag Berlin Heidelberg 2007.