[Eeglablist] value of PCA pre-processing before running ICA on EEG data?
Anish Patel
apatel2009 at meds.uwo.ca
Wed Jul 26 16:25:02 PDT 2006
Dear EEGLab/ICA experts,
I am currently working with 128-channel EEG data (sampling rate of 500 Hz
and epoch length of 10 seconds) with the intention of running ICA on it to
try and elucidate the original sources.
After low-pass filtering the raw data at 70 Hz, I started playing around
with PCA as a pre-processing technique to try and reduce the dimensionality
of the data (since I don't think I have enough data points - 500 * 10 =
5000 - to accurately extract 128 independent components) before running ICA.
A few things I was wondering about:
[1] How do I know how many dimensions to reduce the data to? So far, I have
been choosing to keep just enough principal components such that ~ 99% of
the variance is retained (but I only picked that value arbitrarily), which
usually halves the dimension of the data.
[2] Once I reduce the dimensionality of the data with PCA to 'p'
uncorrelated components, how many independent components 'c' do I choose to
extract? Should c=p?
[3] Is there any difference between: [a] running ICA and extracting (say) 60
components from the original raw data, and [b] first running PCA to reduce
the raw data to the largest 60 principal components, and then running ICA
and extracting 60 independent components from the pre-processed data? If
there is a difference, which is the more appropriate method?
If anyone can offer any insight into these questions, it would be greatly
appreciated. So far, I have just been picking arbitrary values for 'c' and
'p' (ie. trial and error) and hoping for things to work out. I am really
stumped about question [3] though... I don't know which method is better, or
even if it makes a difference which I choose.
Thanks in advance for any assistance!
- Anish
More information about the eeglablist
mailing list