Hyperspectral parameter estimation of elliptically contoured t mixture models using expectation-maximisation

2005 ◽  
Vol 26 (22) ◽  
pp. 5071-5097 ◽  
Author(s):  
M. D. Farrell ◽  
R. M. Mersereau
2011 ◽  
Vol 23 (6) ◽  
pp. 1605-1622 ◽  
Author(s):  
Lingyan Ruan ◽  
Ming Yuan ◽  
Hui Zou

Finite gaussian mixture models are widely used in statistics thanks to their great flexibility. However, parameter estimation for gaussian mixture models with high dimensionality can be challenging because of the large number of parameters that need to be estimated. In this letter, we propose a penalized likelihood estimator to address this difficulty. The [Formula: see text]-type penalty we impose on the inverse covariance matrices encourages sparsity on its entries and therefore helps to reduce the effective dimensionality of the problem. We show that the proposed estimate can be efficiently computed using an expectation-maximization algorithm. To illustrate the practical merits of the proposed method, we consider its applications in model-based clustering and mixture discriminant analysis. Numerical experiments with both simulated and real data show that the new method is a valuable tool for high-dimensional data analysis.


2014 ◽  
Vol 10 (10) ◽  
pp. 2124-2134 ◽  
Author(s):  
G. F. Araújo ◽  
H. T. Macedo ◽  
M. T. Chella ◽  
C. A.E. Montesco ◽  
M. V.O. Medeiros

Sign in / Sign up

Export Citation Format

Share Document