Cluster Analysis of Curved-Shaped Data with Species-Sampling Mixture Models

Raffaele Argiento, Andrea Cremaschi, Alessandra Guglielmi

Risultato della ricerca: Contributo in libroContributo a convegno

Abstract

A BSTRACT. We are interested in clustering data whose support is “curved”. Recently we have ad- dressed this problem, introducing a model which combines two ingredients: species sampling mixtures of parametric densities on one hand, and a deterministic clustering procedure (DBSCAN) on the other. In short, under this model two observations share the same cluster if the distance between the densities corresponding to their latent parameters is smaller than a threshold. However, in this case, the prior cluster assignment is based on the geometry of the space of kernel densities rather than a direct random partition prior elicitation. Following the latter alternative, a new hierarchical model for clustering is proposed here, where the data in each cluster are parametrically distributed around a curve (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. These two mixture models are compared here with respect to cluster estimates obtained for a simulated bivariate dataset from two clusters, one being banana-shaped.
Lingua originaleEnglish
Titolo della pubblicazione ospiteProceedings of SCo2013 - Complex Data Modeling and Computationally Intensive Statistical Methods for Estimation and Prediction
Pagine1-6
Numero di pagine6
Stato di pubblicazionePubblicato - 2013
EventoSCo2013 - Complex Data Modeling and Computationally Intensive Statistical Methods for Estimation and Prediction. - M
Durata: 9 set 201311 set 2013

Convegno

ConvegnoSCo2013 - Complex Data Modeling and Computationally Intensive Statistical Methods for Estimation and Prediction.
CittàM
Periodo9/9/1311/9/13

Keywords

  • clustering, species-sampling mixture, principal curves

Fingerprint Entra nei temi di ricerca di 'Cluster Analysis of Curved-Shaped Data with Species-Sampling Mixture Models'. Insieme formano una fingerprint unica.

Cita questo