The 'svmtrain' function returns a model which can be used for future
prediction.  It is a structure and is organized as [Parameters, nr_class,
totalSV, rho, Label, ProbA, ProbB, nSV, sv_coef, SVs]:

-Parameters: parameters
        -nr_class: number of classes; = 2 for regression/one-class svm
        -totalSV: total #SV
        -rho: -b of the decision function(s) wx+b
        -Label: label of each class; empty for regression/one-class SVM
        -ProbA: pairwise probability information; empty if -b 0 or in one-class SVM
        -ProbB: pairwise probability information; empty if -b 0 or in one-class SVM
        -nSV: number of SVs for each class; empty for regression/one-class SVM
        -sv_coef: coefficients for SVs in decision functions
        -SVs: support vectors