[Comp-neuro] New temporal multiple kernel learning method for characterizing relating SC to connectivity dynamics and Brain state switching

Dipanjan dipanjan at cbcs.ac.in
Tue Oct 2 16:55:45 CEST 2018


Dear all,

It is my pleasure to share with you a very recent methods and data 
driven modelling paper from our lab on how Resting State Dynamics Meets 
Anatomical Structure:
Temporal Multiple Kernel Learning (tMKL) Model to explore SC-dFC-FC 
tripartite relationship published in Neuroimage.

https://www.sciencedirect.com/science/article/pii/S1053811918318597?via%3Dihub#sec2

The proposed model uses spectral graph theory techniques to partitions 
aspects of the whole-brain dynamics essentially into two parts: (i) 
characterizing temporal
dynamics through identification of latent transient states, and (ii) 
linking them to the underlying structural geometry. These two aspects 
are captured using a novel blend of unique methods. The proposed 
solution does not make strong assumptions about the underlying data and 
is generally applicable to resting or task data for learning 
subject-specific state transitions and for successfully characterizing 
SC-dFC-FC relationship through a unifying framework.

MATLAB code for the proposed method can be downloaded from:

https://github.com/SriniwasGovindaSurampudi/tMKL

Any comments/questions/suggestions on the method/code are of course welcome.

Regards,

Dipanjan

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.tnb.ua.ac.be/pipermail/comp-neuro/attachments/20181002/4b128985/attachment.html>


More information about the Comp-neuro mailing list