[Mne_analysis] Extracting features from EEG dataset

[manda awad]

        External Email - Use Caution        

Hi everyone,

Thank you for sharing these useful links.
Can you please explain what do attached figures mean?

If I have a feature vector (28793 X 713) extracted by using wavelet packet decomposition(4 decomposition level with window size = 256, window increment = 32) from dataset for one patient (23 channels X921600 samples) recorded for one hour sampled on 256 Hz, how to plot it ?

Do I have to make feature selection after extracting features ?If so what method should I go for?

Also, How to implement Y vector ? (My dataset is for 24 patients, each one has 46 recorded files for one hour (the start time and end time foe seizure is known))

Thank you for giving me your precious time answering my questions.

Kind regards,
Manda

--------------------------------------------
On Wed, 9/19/18, Alexandre Gramfort <alexandre.gramfort at inria.fr> wrote:

 Subject: Re: [Mne_analysis] Extracting features from EEG dataset
 To: "sheraz" <sheraz at nmr.mgh.harvard.edu>, "Discussion and support forum for the users of MNE Software" <mne_analysis at nmr.mgh.harvard.edu>
 Cc: mandaawad at yahoo.com
 Date: Wednesday, September 19, 2018, 12:25 PM
 
 Manda,
 
 you can have a look at:
 
 https://github.com/mne-tools/mne-features
 https://mne-tools.github.io/mne-features/
 
 and the paper for which we
 wrote this package:
 
 https://hal.archives-ouvertes.fr/hal-01724272
 https://sigport.org/documents/ensemble-learning-approach-detect-epileptic-seizures-long-intracranial-eeg-recordings
 
 hope this helps
 Alex
 On Tue, Sep 18, 2018 at
 10:40 PM Sheraz Khan, PhD
 <sheraz at nmr.mgh.harvard.edu>
 wrote:
 >
 > Hi
 Manda,
 >
 > Please look
 at the following examples:
 >
 > https://martinos.org/mne/stable/auto_examples/decoding/plot_decoding_csp_timefreq.html
 >
 > Best
 >
 > Sheraz
 >
 >
 >
 >         External Email - Use Caution
 > >
 > > Hello
 everyone,
 > >
 >
 > I am an Electrical Engineering student in my last year
 and currently
 > > working on my
 graduation project (detection the onset of epileptic
 > > seizures using CHB EEG data set), is
 there any MNE tutorial for extracting
 >
 > feature using wavelet transform?
 >
 >
 > > Any help will be
 appreciated.
 > > Thank you
 > >
 > > Regards,
 > > Manda
 > >
 > >
 _______________________________________________
 > > Mne_analysis mailing list
 > > Mne_analysis at nmr.mgh.harvard.edu
 > > https://mail.nmr.mgh.harvard.edu/mailman/listinfo/mne_analysis
 > >
 > >
 > >
 >
 >
 >
 -------------------------
 > Sheraz Khan,
 M.Eng, Ph.D.
 > Instructor in Radiology
 >
 > Athinoula A. Martinos
 Center for Biomedical Imaging
 >
 Massachusetts General Hospital
 > Harvard
 Medical School
 >
 >
 McGovern Institute for Brain Research
 >
 Massachusetts Institute of Technology
 >
 > Tel:   +1
 617-643-5634
 > Fax:   +1 617-948-5966
 > Email: sheraz at nmr.mgh.harvard.edu
 >        sheraz at mit.edu
 > Web:   http://sheraz.mit.edu
 >
 _______________________________________________
 > 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.
 >
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Figure_1.jpeg
Type: image/jpeg
Size: 45956 bytes
Desc: not available
Url : http://mail.nmr.mgh.harvard.edu/pipermail/mne_analysis/attachments/20181019/b83f85ee/attachment-0002.jpeg 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Figure_2.jpeg
Type: image/jpeg
Size: 47771 bytes
Desc: not available
Url : http://mail.nmr.mgh.harvard.edu/pipermail/mne_analysis/attachments/20181019/b83f85ee/attachment-0003.jpeg