Dear Varina,
in order create your own training dataset you have to run
fix -t <training-output-basename> -l <mel1.ica> <mel2.ica>
where the first input is your output basename (e.g. Training instead of Training.RData),
the -l option (not -1) is optional but is used to run the leave-one-out test (to test the classification accuracy of your training dataset and to choose the best threshold), and finally you list all your .ica directories.
so the command would be:
fix -t Training -l subject1.ica subject2.ica …
you should get the following outputs:
Training.RData - the actual training dataset
Training - a folder with a copy of the labels and the features of the subjects used to build the training dataset
Traning_LOO - a folder containing the intermediate files for the leave-one-out test (if you used the -l option)
Traning_LOO_results - a file with the results of the leave-one-out test (if you used the -l option)
Hope that helps
Best,
Ludovica
--
Dr Ludovica Griffanti, PhD
Analysis Postdoctoral Research Assistant
Oxford Centre for Functional MRI of the Brain (FMRIB)
Nuffield Department of Clinical Neurosciences, University of Oxford
John Radcliffe Hospital
Oxford, OX3 9DU, UK
email: [log in to unmask]
|