I have EEG Data which I extracted a few features from like energy, entropy and PSD using the wavelet approach. I need to classify the resulted matrix with GMM (Gaussian Mixture Model) which have 3 categories, cat1, cat 2 and cat3. Let me know about some software which have a GMM GUI facility. Currently I'm using MATLAB with the following commands for GMM.
mix1 = gmminit(mix1, data(label==1, :),
options(1) = 1; % Print error values
options(5) = 1; % Prevent collapse of variances
options(14) = 1000; % Number of iterations
mix1 = gmmem(mix1, data(label==1, :),
Generate Test data
test = wstest8(:,1:8);
test_label = wstest8(:,9);
test_probs = [gmmprob (mix1, test) gmmprob(mix2, test)
gmmprob(mix3, test)];%
target = [ test_label==1 test_label==2 test_label==3]; %No.
of outputs
fh1 = conffig (test_probs, target);
I did some work with GMM on my EEG data out of curiosity to simulate the study in 'Decoding stimulus-related information from single-trial EEG responses based on voltage topographies'! I used this code in the attachments, It is a very well explained demo that preforms GMM with Expectation Maximization. I developed my code for my application on this code, I hope it will be helpful to you to!
Hi
If you want to have an idea of what could be done with more complex GMM-based tookit, look at what was done in speaker recognition.
We are providing a complete C++ toolkit see alize.univ-avignon.fr
- Badges
- Science topic
- Similar topics
- Engineering
- Electrical Engineering
- Signal Processing