Bayesian principal curve clustering by species-sampling mixture models Clustering mediante modelli mistura a campionamento di specie di curve principali bayesiane

Raffaele Argiento, Alessandra Guglielmi

Risultato della ricerca: Contributo in libroContributo a convegno

Abstract

Abstract In this work we are interested in clustering data whose support is “curved”. For this purpose, we will follow a Bayesian nonparametric approach by considering a species sampling mixture model. Our first goal is to define a general/flexible class of distributions, such that they can model data from clusters with non standard shape. To this end, we extend the definition of principal curve given in [8] (Tibshirani 1992) into a Bayesian framework. We propose a new hierarchical model, where the data in each cluster are parametrically distributed around the Bayesian principal curve, and the prior cluster assignment is given on the latent variables at the second level of hierarchy according to a species sampling model. As an application we will consider the detection of seismic faults using data coming from Italian earthquake catalogues.
Lingua originaleEnglish
Titolo della pubblicazione ospiteProceedings of 47th SIS Scientific Meeting of the Italian Statistica Society
Pagine1-6
Numero di pagine6
Stato di pubblicazionePubblicato - 2014
Evento47th SIS Scientific Meeting of the Italian Statistica Society - Cagliari
Durata: 11 giu 201413 giu 2014

Convegno

Convegno47th SIS Scientific Meeting of the Italian Statistica Society
CittàCagliari
Periodo11/6/1413/6/14

Keywords

  • Cluster Analysis, Mixture Models, Principal Curve, Specie Sampling Models

Fingerprint Entra nei temi di ricerca di 'Bayesian principal curve clustering by species-sampling mixture models Clustering mediante modelli mistura a campionamento di specie di curve principali bayesiane'. Insieme formano una fingerprint unica.

Cita questo