A0927
Title: Conditional von Mises Bayesian networks
Authors: Anna Gottard - University of Firenze (Italy)
Agnese Panzera - Università degli Studi di Firenze (Italy) [presenting]
Abstract: Directed acyclic graphical models, commonly known as Bayesian networks, use directed acyclic graphs to represent conditional independence among random variables. A new class of Bayesian networks is proposed for circular random variables, based on the von Mises distribution. The approach is illustrated by applying these models to study the conditional independencies in sequences of angles describing protein structures.
