Research Article

Gaussian Mixture Models Based on Principal Components and Applications

Table 7

Forensic glass fragments data: parameter estimates and BIC of the bivariate GMM (second technique) by taking cluster means as initial values of model means, and the initial values for 1.49372 and −0.51297 for PC1, while those for PC2 were −0.58542 and 0.20104.

ValuesModel parameters
First componentSecond component

Parameter estimation0.242931.58683−0.630171.977513.974910.75707−0.509190.202220.375190.20682
Log-likelihood = −531.5947, BIC = 1111.483
Number of iterations: 7