Back to Search Start Over

Monotone Constrained EM Algorithms for Multinormal Mixture Models.

Authors :
Bock, H. -H.
Gaul, W.
Vichi, M.
Arabie, Ph.
Baier, D.
Critchley, F.
Decker, R.
Diday, E.
Greenacre, M.
Lauro, C.
Meulman, J.
Monari, P.
Nishisato, S.
Ohsumi, N.
Opitz, O.
Ritter, G.
Schader, M.
Weihs, C.
Zani, Sergio
Cerioli, Andrea
Source :
Data Analysis, Classification & the Forward Search; 2006, p111-118, 8p
Publication Year :
2006

Abstract

We investigate the spectral decomposition of the covariance matrices of a multivariate normal mixture distribution in order to construct constrained EM algorithms which guarantee the monotonicity property. Furthermore we propose different set of constraints which can be simply implemented. These procedures have been tested on the ground of many numerical experiments. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISBNs :
9783540359777
Database :
Supplemental Index
Journal :
Data Analysis, Classification & the Forward Search
Publication Type :
Book
Accession number :
33101345
Full Text :
https://doi.org/10.1007/3-540-35978-8_13