In turco: Bu bildiride, seyrek olaylar?n (rare events) sezimi problemi icin parc¸ac?k s¨uzgec¸lerine dayanan bir y¨ontem onermekteyiz.C¸al?s¸mam?zda seyrek olaylar, arkaplan is¸aretine bindirilmis¸ bir ¨ozba?glan?ml? s¨urec¸ (AR) olarak modellenmis¸lerdir. O¨zbag?lan?ml? su¨recin etkinles¸tirme ve etkinsizles¸tirme zamanlar? bilinmemektedir. Bindirilmis¸ seyrek olay?n gerc¸ek zamanda sezim problemi durum uzay? boyutunu genis¸leterek c¸ ¨oz¨ulm¨us¸t¨ur. Ek durum parametresi etkinsizles¸tirme durumunda s?f?r olan AR-is¸aretini temsil etmektedir. Say?sal deneyler yaklas¸?m?m?z?n bas¸ar?m?n? g¨ostermektedir.
In this paper1, we consider the detection of rare events by applying particle filtering. We model the rare event as an AR signal superposed on a background signal. The activation and deactivation times of the AR-signal are unknown. We solve the online detection problem of this superpositional rare event by extending the state space dimension by one. The additional parameter of the state represents the AR-signal, which is zero when deactivated. Numerical experiments demonstrate the effectiveness of our approach.
Ardısık Monte Carlo Yontemiyle Bindirilmis Olay Sezimi = Superimposed Event Detection by Sequential Monte Carlo Methods
Kuruoglu E E;
2007
Abstract
In this paper1, we consider the detection of rare events by applying particle filtering. We model the rare event as an AR signal superposed on a background signal. The activation and deactivation times of the AR-signal are unknown. We solve the online detection problem of this superpositional rare event by extending the state space dimension by one. The additional parameter of the state represents the AR-signal, which is zero when deactivated. Numerical experiments demonstrate the effectiveness of our approach.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
