[Eeglablist] BCILAB

Daniel Roberts drobertc at gmu.edu
Wed Jul 1 15:02:16 PDT 2015


When datasets are merged in EEGLAB, a "boundary" marker is added, and any
numeric values in the EEG.event.type field are converted to strings (as
EEGLAB tries to keep all event field labels of the same type, and
"boundary" is a string). It sounds like maybe you're specifying numeric
types in the training step when you should be specifying their string


On Wed, Jul 1, 2015 at 4:01 PM, Mock, Jeffrey R <jmock at tulane.edu> wrote:

>  I can not get the training step of BCIlab to work on a "merged" dataset
> from EEGLAB. Is this a known bug? Is there a fix?
>  Thanks,
>  Jeff
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20150701/6e0f2151/attachment.html>

More information about the eeglablist mailing list