[Eeglablist] Queries related to Feature Extraction from EEG data

Laxmi Shaw laxmi.shaw22 at gmail.com
Sat May 17 05:40:41 PDT 2014

Dear EEGLAB List,
I have extracted many features from EEG data. Features like mean, variance,
kurtosis, skewness,
Hjorth parameters etc. I am working on 64 channel data containing 64000
samples each. So per subject I have a 64000*64 data-set to deal with and I
have considered 34 subjects.

After standard pre-processing,I have adopted constant segmentation for each
channel. The segment width is 1 second(256 samples) with 50 percent
overlapping. I have calculated statistical parameters as mentioned above
for these small segments. In this way I have tried to reduce the data
dimensionality to some extent. But I am unable to form a feature vector
that i can input to some standard classifier or clustering tool.

Please help with this problem. Please tell me whether my procedure is fine
or I need to make some amendments. Above all please, help me form a feature
vector that i can input into a classifier.
Hoping for a positive response.

PhD Scholar
IIT Kharagpur,
West Bengal
Ph no-08388837821
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20140517/3896d6fe/attachment.html>

More information about the eeglablist mailing list