[Eeglablist] Human Identification & biometric authentication system using EEG

[Makoto Miyakoshi]

Dear Mahmudul,

Very interesting project! I have never thought of it.
Generally speaking, use of ICA should increase signal to noise ratio
because it unmixes the scalp recorded signals into source signals. I'm not
sure either time-domain analysis or frequency-domain analysis is more
useful for this purpose, but ICA is surely helpful for both cases.

Maybe BCI people have much more ideas and suggestions.

Makoto

On Thu, Feb 11, 2016 at 1:36 PM, Mahmudul Hasan mubin <
mubin.eee.kuet at gmail.com> wrote:

> Dear all,
>
> I am doing my research in "Development of an EEG based biometric
> authentication & security system". This is my undergraduate thesis topic.
> Please can anyone tell me is it possible to identify an individual
> correctly from a group of people correctly? I heve studied a lot of
> research papers about this & they said thay got almost 100% accuracy.
> Someone are using time-frequency based feature extraction algorithm i.e.
> WPD(Wavelet Packet Decomposition). I am novice in EEGlab but learning
> everyday from this amazing tool. I just only learnt Time domain feature
> extraction i.e. mean, median, variance etc. How EEGlab can be helpful in
> this regard? Can anyone please suggest me which method will be best for
> human identification using EEG? Which feature is not varied of an
> individual at different trials?
>
> With thanks,
> Md. Mahmudul Hasan
> Final  year undergraduate student
> Department of Electrical & Electronic Engineering (EEE)
> Khulna University of Engineering & Technology (KUET), Bangladesh.
>
> _______________________________________________
> 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
>



-- 
Makoto Miyakoshi
Swartz Center for Computational Neuroscience
Institute for Neural Computation, University of California San Diego
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20160322/2ded3aed/attachment.html>