[Eeglablist] Extracting features from bigdata

Md. Abdul Awal awalece04 at yahoo.com
Mon Oct 19 01:42:41 PDT 2015

Thanks for your useful suggestions. I went through the TAPEEG and it is also useful. However, this software doesn't extract much features. 
I need to extract different features from these neonatal EEG to correlate with underdevelopmental outcome.Do respected EEGLABListers know any software or related materials for extracting different features to predict outcome. 

Thanks in advance. 
 with regards, 
 ------------------------ Md. Abdul Awal 
The University of Queensland, Australia
      From: Tarik S Bel-Bahar <tarikbelbahar at gmail.com>
 To: Md. Abdul Awal <awalece04 at yahoo.com> 
Cc: "eeglablist at sccn.ucsd.edu" <eeglablist at sccn.ucsd.edu> 
 Sent: Monday, October 19, 2015 1:07 PM
 Subject: Re: [Eeglablist] Extracting features from bigdata
Hello Abdul.If your computer is strong and fast enough it should be able to load each single file at least. Try loaing your data in matlab, eeglab, or the software with which the EEG was recorded, if you have not yet.
I've seen eeglab work fine with 8+ hour files. I don't see any reason why other major EEG programs out there (for pay and public) could not handle 12 hours of data. Many are built to work with sleep data that is often that long. 
You can also cut down the 12 hours into several 3 hour chunks, or something like that.You may also downsample in terms of how many samples you have per second (say from 1000 to 250), and in terms of number of total channels per file.
See TAPEEG, a recent automatic EEG processing toolbox, it may be of help to you for automatic cleaning and metrics.

On Fri, Oct 16, 2015 at 4:42 AM, Md. Abdul Awal <awalece04 at yahoo.com> wrote:

Dear EEGLABlisters
I have  EEG recordings from 67 subjects. Duration of each recording is at least 12hrs. I have the outcome of the subjects. 

I want to extract different signal features e.g. alpha band power, symmetry etc and correlate  them with outcome. 
Can anybody help me how i can handle such a bigdata and what will be possible approach?
Looking forward to hearing from you. 
 with regards, ------------------------ 
Md. Abdul Awal The University of Queensland, Australia
Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
To unsubscribe, send an empty email to eeglablist-unsubscribe at sccn.ucsd.edu
For digest mode, send an email with the subject "set digest mime" to eeglablist-request at sccn.ucsd.edu

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20151019/5f7446e6/attachment.html>

More information about the eeglablist mailing list