R help - Dec 2007 - How to choose the best Kernel in SVM classification

Hi all,

I'm working with some data with 54 variables, 44 of them are binary, and
I'm using SVM in package e1071 to carry out general classification but I
don't know how to choose the best kernel for my data. I would be very
grateful if someone could help me on this task.

Best regards,

Pedro Marques