[R] create mean ksvm model

[Luigi Marongiu]

Hello,
I am using the ksvm function from the library kernlab to generate an
SVM classification. I am running the model with k-mean
cross-validation, thus obtaining different accuracy.
Is it possible to merge the different models obtained with the
separate data set to generate a kind of median model, one that
accounts for all the datasets used for the training?
Thank you