EM experiment: red class, full covariances

Number of Gaussians, assumes full covariance matrices

Choose number of Gaussians in mixture model

k = 5 ;

Assumes full covariance matrices

initFull = EMInitializationFull[data1, k] ;

Compute EM algorithm

RowBox[{Timing, [, RowBox[{RowBox[{em,  , =,  , RowBox[{EM, [, RowBox[{data1, ,, initFull, ,, 0.001}], ]}]}], ;}], ]}]

RowBox[{{, RowBox[{RowBox[{0.3,  , Second}], ,, Null}], }}]

Visualization

Initial model

AnnularAllPlot[c1, rr1, rr2, em//First] ;

[Graphics:../HTMLFiles/index_26.gif]

Final model

AnnularAllPlot[c1, rr1, rr2, em//Last] ;

[Graphics:../HTMLFiles/index_28.gif]

Save solution

full1 = em // Last ;

Classification

Classification parameters

model = full1 ; thresholdList = Table[i/5, {i, 1, 15}] // N ;

Generate classification data for increasing thresholds (1/5 to 3)

OneClassClassify1[model, #] & /@ thresholdList ;

[Graphics:../HTMLFiles/index_32.gif]

[Graphics:../HTMLFiles/index_33.gif]

[Graphics:../HTMLFiles/index_34.gif]

[Graphics:../HTMLFiles/index_35.gif]

[Graphics:../HTMLFiles/index_36.gif]

[Graphics:../HTMLFiles/index_37.gif]

[Graphics:../HTMLFiles/index_38.gif]

[Graphics:../HTMLFiles/index_39.gif]

[Graphics:../HTMLFiles/index_40.gif]

[Graphics:../HTMLFiles/index_41.gif]

[Graphics:../HTMLFiles/index_42.gif]

[Graphics:../HTMLFiles/index_43.gif]

[Graphics:../HTMLFiles/index_44.gif]

[Graphics:../HTMLFiles/index_45.gif]

[Graphics:../HTMLFiles/index_46.gif]


Created by Mathematica  (October 9, 2003)