[Mne_analysis] EEG clasifier question regarding label selection
VENKATA PHANIKRISHNA B
b.phanikrishna at gmail.com
Thu Feb 21 02:21:04 EST 2019
External Email - Use Caution
Hi Ighoyota ben
Providing a class label for Machine learning is fully depends on you. For
binary classification generally, labels are 0 and 1.
For your task, classification of low-risk and high-risk class labels
assignment based on your work (what you want to predict). For example, if
your work is finding high-risk EEG, then the high-risk class is a positive
class. Assing '1' for the class label for high-risk related features.
Low-risk (take as 0)
high-risk (take as 1)
for more clarification about positive class and negative class
On Wed, Feb 20, 2019 at 9:32 PM Ben Ighoyota Ajenaghughrure <ighoyota at tlu.ee>
> External Email - Use Caution
> Hello All,
> I am new to machine learning and python mne, but my interest is situated
> around developing Supervised learning model using EEG data.
> I have a question about the aspect of choosing a label.
> Do i have to choose one feature as my label
> Do i have to enter manually digital representation for my labels?
> For example
> I have collected EEG data during two condition experiment (decision making
> under low risk and decision making under high-risk condition)
> My labels here are high and low risk
> How do I represent this during my model development
> Also, can someone point me to how to some feature selection examples,
> having done the feature extraction?
> looking forward to your reply
> 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.
> Mne_analysis mailing list
> Mne_analysis at nmr.mgh.harvard.edu
*VENKATA PHANIKRISHNA B*
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Mne_analysis