BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Estimating whole brain dynamics using spectral clustering - Yi Yu 
 (University of Cambridge)
DTSTART:20151104T160000Z
DTEND:20151104T170000Z
UID:TALK61850@talks.cam.ac.uk
CONTACT:Adam Kashlak
DESCRIPTION:Spectral clustering is a computationally feasible and model-fr
 ee method widely used in the identification of communities in networks. In
  this work\, we introduce a data-driven method\, namely Network Change Poi
 nts Detection (NCPD)\, which detects change points in the network structur
 e of a multivariate time series\, with each component of the time series r
 epresented by a node in the network. NCPD consists of three parts: spectra
 l clustering allows us to consider high dimensional time series where the 
 dimension of the time series is greater than the number of time points (N 
 > T)\; the principal angles allows for estimation of the change in terms o
 f network/graph structures across time without prior knowledge of the numb
 er or location of the change points\; permutation and bootstrapping method
 s are used to perform inference on the change points. NCPD is applied to v
 arious simulated data sets as well as to a resting state functional Magnet
 ic Resonance Imaging (fMRI) data set. The results illustrate the ability o
 f NCPD to observe how the network structure changes over the time course. 
  The new methodology also allows us to identify common functional states a
 cross subjects.  Finally\, the method promises to offer a deep insight int
 o the large-scale characterisations and dynamics of the brain.
LOCATION:MR14\, Centre for Mathematical Sciences
END:VEVENT
END:VCALENDAR