question about classification between events and normalization

✉️ Mailing List Archive (read-only)
1

External Email - Use Caution

Hi all,
I'm new to MNE Python. I have experience in Tensorflow but for Images
Classification using cnn models.
I have EEG data from Brainvision (.vhdr extension). (31 channels,
sampling rate 500 Hz, High pass filtered at 0.5 Hz). For every trial I
have an EEG dataset, and I have many trials. Each trial is about 2 - 3
seconds and consists of different 5 events. The time period is
different between trials and different between events.

My goal is to make a multi-classifier to distinguish between Events by
using the data from many trials. I looked in the internet but it's
still unclear for me. I have qeustions:
Is there a function that can take the .vhdr files, convert them to
numpy arrays.
Is there a function that can take the files with events, and possibly
cut them into segments and normalize them?
Which classifier would you recommend?

Many thanks in advance for your kind help

2

External Email - Use Caution

I have EEG data from Brainvision (.vhdr extension).

[snip]

Is there a function that can take the .vhdr files, convert them to
numpy arrays.

yes:
# convert brainvision .eeg file to mne.Raw format

3

External Email - Use Caution

Which classifier would you recommend?

You can start with a simple linear classifier such as the logistic

regression:
https://martinos.org/mne/dev/auto_tutorials/plot_sensors_decoding.html#decoding-over-time

JR

Many thanks in advance for your kind help

_______________________________________________
Mne_analysis mailing list
Mne_analysis at nmr.mgh.harvard.edu
Mne_analysis Info Page

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mail.nmr.mgh.harvard.edu/pipermail/mne_analysis/attachments/20181205/3cf4feb7/attachment.html