[Mne_analysis] [MNE_analysis] converting EEGlab ICAed .set file to MNE ICA object

Brunner, Clemens (clemens.brunner@uni-graz.at) clemens.brunner at uni-graz.at
Sun Mar 11 03:44:33 EDT 2018
Search archives:


In principle this should be possible. You can load the .set file with scipy.io.loadmat (because it is a valid .mat file). The important ICA-related parts are stored in EEG.weights and EEG.sphering - these roughly correspond to MNE’s ICA.unmixing_matrix_ and ICA.pca_components_. You could create a new ICA object with ica = mne.preprocessing.ICA() and then set these two fields. However, you might need to set other attributes in order for this to work (https://martinos.org/mne/stable/generated/mne.preprocessing.ICA.html#attributes). Furthermore, EEGLAB and MNE handle these matrices slightly differently in terms of performed transformations. MNE performs a pre-whitening transform (which is usually a scaling to unit variance), and this is not included in the two matrices. I’m currently trying to simplify this process, so if it doesn’t work please feel free to contact me again.


> On Mar 10, 2018, at 21:46, Taehwan Kim <iankim at nyu.edu> wrote:
> Hi,
> I fitted ICA on EEGlab with EEG data, and generated some .set files. I want to try the MNE Python ICA functions, and want to try converting those .set files into MNE Python ICA objects. Is there a way to do that? 
> Thanks in advance!
> Ian
> _______________________________________________
> Mne_analysis mailing list
> Mne_analysis at nmr.mgh.harvard.edu
> https://mail.nmr.mgh.harvard.edu/mailman/listinfo/mne_analysis
> The information in this e-mail is intended only for the person to whom it is
> addressed. If you believe this e-mail was sent to you in error and the e-mail
> contains patient information, please contact the Partners Compliance HelpLine at
> http://www.partners.org/complianceline . If the e-mail was sent to you in error
> but does not contain patient information, please contact the sender and properly
> dispose of the e-mail.

More information about the Mne_analysis mailing list