Imperial College London

Dr Peter Hellyer

Faculty of MedicineDepartment of Brain Sciences

Honorary Lecturer
 
 
 
//

Contact

 

+44 (0)20 7594 9568peter.hellyer

 
 
//

Location

 

4.35Royal School of MinesSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Monti:2017:10.3389/fncom.2017.00014,
author = {Monti, RP and Lorenz, R and Hellyer, P and Anagnostopoulos, C and Leech, R and Montana, G},
doi = {10.3389/fncom.2017.00014},
journal = {Frontiers in Computational Neuroscience},
title = {Decoding time-varying functional connectivity networks via linear graph embedding methods},
url = {http://dx.doi.org/10.3389/fncom.2017.00014},
volume = {11},
year = {2017}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - An exciting avenue of neuroscientific research involves quantifying the time-varying prop-erties of functional connectivity networks. As a result, many methods have been proposed toestimate the dynamic properties of such networks. However, one of the challenges associatedwith such methods involves the interpretation and visualization of high-dimensional, dynamicnetworks. In this work, we employ graph embedding algorithms to provide low-dimensionalvector representations of networks, thus facilitating traditional objectives such as visualization,interpretation and classification. We focus on linear graph embedding methods based on prin-cipal component analysis and regularized linear discriminant analysis. The proposed graphembedding methods are validated through a series of simulations and applied to fMRI datafrom the Human Connectome Project.
AU - Monti,RP
AU - Lorenz,R
AU - Hellyer,P
AU - Anagnostopoulos,C
AU - Leech,R
AU - Montana,G
DO - 10.3389/fncom.2017.00014
PY - 2017///
SN - 1662-5188
TI - Decoding time-varying functional connectivity networks via linear graph embedding methods
T2 - Frontiers in Computational Neuroscience
UR - http://dx.doi.org/10.3389/fncom.2017.00014
UR - http://hdl.handle.net/10044/1/45086
VL - 11
ER -