This work deals with the classification problem in the case that groups are known and both labeled and unlabeled data are available. The classification rule is derived using Gaussian mixtures, with covariance matrices fixed according to a multiple testing procedure, which allows to choose among four alternatives: het- eroscedasticity, homometroscedasticity, homotroposcedasticity, and homoscedastic- ity. The mixture models are then fitted using all available data (labeled and unla- beled) and adopting the EM and the CEM algorithms. Applications on real data are provided in order to show the classification performance of the proposed procedure

Bagnato, L., Greselin, F. (2011). Model-based clustering and classification via patterned covariance analysis. In P. Cerchiello, C. Tarantola (a cura di), CLADAG 2011, Book of Abstracts. Pavia University Press.

Model-based clustering and classification via patterned covariance analysis

Greselin, F
2011

Abstract

This work deals with the classification problem in the case that groups are known and both labeled and unlabeled data are available. The classification rule is derived using Gaussian mixtures, with covariance matrices fixed according to a multiple testing procedure, which allows to choose among four alternatives: het- eroscedasticity, homometroscedasticity, homotroposcedasticity, and homoscedastic- ity. The mixture models are then fitted using all available data (labeled and unla- beled) and adopting the EM and the CEM algorithms. Applications on real data are provided in order to show the classification performance of the proposed procedure
Capitolo o saggio
Model-basedclustering; Classification; Patterned covariance analysis; Multiple testing procedure
English
CLADAG 2011, Book of Abstracts
Cerchiello, P; Tarantola, C
2011
978-88-96764-22-0
Pavia University Press
Bagnato, L., Greselin, F. (2011). Model-based clustering and classification via patterned covariance analysis. In P. Cerchiello, C. Tarantola (a cura di), CLADAG 2011, Book of Abstracts. Pavia University Press.
open
File in questo prodotto:
File Dimensione Formato  
BG Cladag 2011 Model-Based Clustering and Classification via Patterned Covariance Analysis.pdf

accesso aperto

Dimensione 1.3 MB
Formato Adobe PDF
1.3 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/47448
Citazioni
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
Social impact