Decoding time-varying functional connectivity networks via linear graph embedding methods

Ricardo P. Monti; Romy Lorenz; Peter Hellyer; Robert Leech; Christoforos Anagnostopoulos; Giovanni Montana

doi:10.3389/fncom.2017.00014

Decoding time-varying functional connectivity networks via linear graph embedding methods

Ricardo P. Monti^*, Romy Lorenz, Peter Hellyer, Robert Leech, Christoforos Anagnostopoulos, Giovanni Montana

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

Abstract

An exciting avenue of neuroscientific research involves quantifying the time-varying properties of functional connectivity networks. As a result, many methods have been proposed to estimate the dynamic properties of such networks. However, one of the challenges associated with such methods involves the interpretation and visualization of high-dimensional, dynamic networks. In this work, we employ graph embedding algorithms to provide low-dimensional vector representations of networks, thus facilitating traditional objectives such as visualization, interpretation and classification. We focus on linear graph embedding methods based on principal component analysis and regularized linear discriminant analysis. The proposed graph embedding methods are validated through a series of simulations and applied to fMRI data from the Human Connectome Project.

Original language	English
Article number	14
Journal	Frontiers in Computational Neuroscience
Volume	11
DOIs	https://doi.org/10.3389/fncom.2017.00014
Publication status	Published - 20 Mar 2017

Keywords

Brain decoding
Dynamic networks
Functional connectivity
Graph embedding
Visualization

Access to Document

10.3389/fncom.2017.00014

Cite this

@article{760b8cd12b8547a48333c7277bdea4fc,

title = "Decoding time-varying functional connectivity networks via linear graph embedding methods",

abstract = "An exciting avenue of neuroscientific research involves quantifying the time-varying properties of functional connectivity networks. As a result, many methods have been proposed to estimate the dynamic properties of such networks. However, one of the challenges associated with such methods involves the interpretation and visualization of high-dimensional, dynamic networks. In this work, we employ graph embedding algorithms to provide low-dimensional vector representations of networks, thus facilitating traditional objectives such as visualization, interpretation and classification. We focus on linear graph embedding methods based on principal component analysis and regularized linear discriminant analysis. The proposed graph embedding methods are validated through a series of simulations and applied to fMRI data from the Human Connectome Project.",

keywords = "Brain decoding, Dynamic networks, Functional connectivity, Graph embedding, Visualization",

author = "Monti, {Ricardo P.} and Romy Lorenz and Peter Hellyer and Robert Leech and Christoforos Anagnostopoulos and Giovanni Montana",

year = "2017",

month = mar,

day = "20",

doi = "10.3389/fncom.2017.00014",

language = "English",

volume = "11",

journal = "Frontiers in Computational Neuroscience",

issn = "1662-5188",

publisher = "Frontiers Media S.A.",

}

TY - JOUR

T1 - Decoding time-varying functional connectivity networks via linear graph embedding methods

AU - Monti, Ricardo P.

AU - Lorenz, Romy

AU - Hellyer, Peter

AU - Leech, Robert

AU - Anagnostopoulos, Christoforos

AU - Montana, Giovanni

PY - 2017/3/20

Y1 - 2017/3/20

N2 - An exciting avenue of neuroscientific research involves quantifying the time-varying properties of functional connectivity networks. As a result, many methods have been proposed to estimate the dynamic properties of such networks. However, one of the challenges associated with such methods involves the interpretation and visualization of high-dimensional, dynamic networks. In this work, we employ graph embedding algorithms to provide low-dimensional vector representations of networks, thus facilitating traditional objectives such as visualization, interpretation and classification. We focus on linear graph embedding methods based on principal component analysis and regularized linear discriminant analysis. The proposed graph embedding methods are validated through a series of simulations and applied to fMRI data from the Human Connectome Project.

AB - An exciting avenue of neuroscientific research involves quantifying the time-varying properties of functional connectivity networks. As a result, many methods have been proposed to estimate the dynamic properties of such networks. However, one of the challenges associated with such methods involves the interpretation and visualization of high-dimensional, dynamic networks. In this work, we employ graph embedding algorithms to provide low-dimensional vector representations of networks, thus facilitating traditional objectives such as visualization, interpretation and classification. We focus on linear graph embedding methods based on principal component analysis and regularized linear discriminant analysis. The proposed graph embedding methods are validated through a series of simulations and applied to fMRI data from the Human Connectome Project.

KW - Brain decoding

KW - Dynamic networks

KW - Functional connectivity

KW - Graph embedding

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=85018332466&partnerID=8YFLogxK

U2 - 10.3389/fncom.2017.00014

DO - 10.3389/fncom.2017.00014

M3 - Article

AN - SCOPUS:85018332466

SN - 1662-5188

VL - 11

JO - Frontiers in Computational Neuroscience

JF - Frontiers in Computational Neuroscience

M1 - 14

ER -

Decoding time-varying functional connectivity networks via linear graph embedding methods

Abstract

Keywords

Access to Document

Other files and links

Cite this