This report analyzes the use of the modified Cholesky decomposition technique as applied to the feature selection and classification algorithms used in the analysis of remote sensing data (e. g.•as in LARSYS). This technique is approximately 30% faster in classification and a factor of 2- 3 faster in divergence, as compared with LARSYS. Also numerical stability and accuracy are slightly improved. Other methods necessary to deal with numerical stability problems are briefly discussed.

Date of this Version