DocumentCode :
2172112
Title :
Identifying modular relations in complex brain networks
Author :
Andersen, Kasper Winther ; Mørup, Morten ; Siebner, Hartwig ; Madsen, Kristoffer H. ; Hansen, Lars Kai
Author_Institution :
DTU Inf., Tech. Univ. of Denmark, Lyngby, Denmark
fYear :
2012
fDate :
23-26 Sept. 2012
Firstpage :
1
Lastpage :
6
Abstract :
We evaluate the infinite relational model (IRM) against two simpler alternative nonparametric Bayesian models for identifying structures in multi subject brain networks. The models are evaluated for their ability to predict new data and infer reproducible structures. Prediction and reproducibility are measured within the data driven NPAIRS split-half framework. Using synthetic data drawn from each of the generative models we show that the IRM model outperforms the two competing models when data contain relational structure. For data drawn from the other two simpler models the IRM does not overfit and obtains comparable reproducibility and predictability. For resting state functional magnetic resonance imaging data from 30 healthy controls the IRM model is also superior to the two simpler alternatives, suggesting that brain networks indeed exhibit universal complex relational structure in the population.
Keywords :
Bayes methods; brain; magnetic resonance imaging; medical image processing; neural nets; neurophysiology; IRM model; alternative nonparametric Bayesian models; complex brain networks; complex relational structure; data driven NPAIRS split-half framework; infinite relational model; modular relations identification; multi subject brain networks; reproducible structures; state functional magnetic resonance imaging data; synthetic data; Bayesian methods; Brain modeling; Communities; Data models; Mathematical model; Predictive models; Sociology; Complex Networks; Infinite Relational Model; fMRI;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning for Signal Processing (MLSP), 2012 IEEE International Workshop on
Conference_Location :
Santander
ISSN :
1551-2541
Print_ISBN :
978-1-4673-1024-6
Electronic_ISBN :
1551-2541
Type :
conf
DOI :
10.1109/MLSP.2012.6349739
Filename :
6349739
Link To Document :
بازگشت