[Mne_analysis] how to extract compute_energy_freq_bands features per channel

Ben Ighoyota Ajenaghughrure ighoyota at tlu.ee
Wed Feb 27 13:18:04 EST 2019
Search archives:

        External Email - Use Caution        

Hello All,

I am having a problem extracting "compute_energy_freq_bands" features from
myEEG data.

When i use the python mne function "compute_energy_freq_bands"  , the
resulting feature extracted per channel is more than expected,  for example
if i want to extract the energy frequency band for 4.5 to7hz, having
recorded with 8channel electrode, i get for each channel, say  CZ as
channel 1 in my eeg data, will become
ch1_energy_freq_band0
ch1_energy_freq_band1
ch1_energy_freq_band2
ch1_energy_freq_band3
ch1_energy_freq_band4
ch1_energy_freq_band5
This is the same set I get for all other channels. I do not need all these,
i only need
Ch1_energy_freq_band,
CH2_energy_freq_band.

I have gone through the python mne website and try to understand the
parameters, but I still have a problem, is a there a way to get around this
problem? especially restricting the feature outcome to a single channel and
not splitting them into several bands per channel?

Here is my example code.
selected_funcs1 = {'pow_freq_bands'}
X_new1 = extract_features(data, raw.info['sfreq'],
selected_funcs=selected_funcs1, return_as_df=True)


A. Ighoyota ben
Junior Researcher HCI (PhD in-view)
Tallinn University, Estonia
School of digital Technologies.
mobile:+372582 <+372%205832%206393>78794
skype: ighoyota-ben

<https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail&utm_term=icon>
Virus-free.
www.avast.com
<https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail&utm_term=link>
<#DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mail.nmr.mgh.harvard.edu/pipermail/mne_analysis/attachments/20190227/4d6451b0/attachment.html 


More information about the Mne_analysis mailing list