Italiano (Italian) English (Inglese)
venerdì, 15 dicembre 2017

Pubblicazioni

Indietro
Dettagli Pubblicazione
Autori:Daniele Codetta Raiteri
Luigi Portinale
Area Scientifica:Artificial Intelligence
Uncertain Reasoning
Probabilistic Graphical Models
Formal Models
Titolo:Generalizing Continuous Time Bayesian Networks with Immediate Nodes
Apparso su:Proceedings of the Workshop on Graph Structures for Knowledge Representation and Reasoning
Pagine:12-17
Anno:2009
Tipo Pubblicazione:Paper on Proceedings International Conference
URL:http://www.lirmm.fr/%7E...oru/GKR/GKR-proceedings.pdf
Sommario: An extension to Continuous Time Bayesian Networks (CTBN) called Generalized CTBN (GCTBN) is presented; the formalism allows one to model, in addition to continuous time delayed variables (with exponentially distributed transition rates), also non delayed or “immediate” variables, which act as standard chance nodes in a Bayesian Network. The usefulness of this kind of model is discussed through an example concerning the reliability of a simple component-based system. A semantic model of GCTBNs, based on the formalism of Generalized Stochastic Petri Nets (GSPN) is outlined, whose purpose is twofold: to provide a wellde ned semantics for GCTBNs in terms of the underlying stochastic process, and to provide an actual mean to perform inference (both prediction and smoothing) on GCTBNs. The example case study is then used, in order to highlight the exploitation of GSPN analysis for posterior probability computation on the GCTBN model.