Print  Close

Bayesian temporal biclustering with applications to multi-subject neuroscience studies

Abstract Number:

3548 

Submission Type:

Contributed Abstract 

Contributed Abstract Type:

Paper 

Participants:

Federica Zoe Ricci (1), Jaylen Lee (2), Michele Guindani (3), Marina Vannucci (4), Megan A.K Peters (2), Sana Hussain (5), Erik Sudderth (6)

Institutions:

(1) University of California Irvine, N/A, (2) University of California, Irvine, N/A, (3) University of California-Los Angeles, N/A, (4) Rice University, N/A, (5) University of California, Riverside, N/A, (6) University of California, Berkeley, N/A

Co-Author(s):

Jaylen Lee  
University of California, Irvine
Michele Guindani  
University of California-Los Angeles
Marina Vannucci  
Rice University
Megan A.K Peters  
University of California, Irvine
Sana Hussain  
University of California, Riverside
Erik Sudderth  
University of California, Berkeley

First Author:

Federica Zoe Ricci  
University of California Irvine

Presenting Author:

Jaylen Lee  
University of California, Irvine

Abstract Text:

We consider the problem of analyzing multivariate time series collected on multiple subjects, with the goal of identifying groups of subjects exhibiting similar trends in their recorded measurements over time as well as time-varying groups of associated measurements. We propose a Bayesian model for temporal bi-clustering featuring nested partitions, where a time-invariant partition of subjects induces a time-varying partition of measurements. Our approach allows for data-driven determination of the number of subject and measurement clusters as well as estimation of the number and location of changepoints in measurement partitions. To efficiently perform model fitting and posterior estimation with Markov Chain Monte Carlo, we derive a blocked update of measurements' cluster-assignment sequences.
We illustrate the performance of our model in two applications to functional magnetic resonance imaging data and to an electroencephalogram (EEG) dataset. The results indicate that the proposed model can combine information from potentially many subjects to discover a set of interpretable, dynamic patterns.

Keywords:

Bayesian|Time Series|Neuroimaging|Clustering| |

Sponsors:

Section on Statistics in Imaging

Tracks:

Brain Imaging

Can this be considered for alternate subtype?

No

Are you interested in volunteering to serve as a session chair?

No

I have read and understand that JSM participants must abide by the Participant Guidelines.

Yes

I understand that JSM participants must register and pay the appropriate registration fee by June 1, 2024. The registration fee is non-refundable.

I understand