Online Program Home
My Program

Abstract Details

Activity Number: 253 - Contributed Poster Presentations: Section on Statistical Computing
Type: Contributed
Date/Time: Monday, July 30, 2018 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistical Computing
Abstract #328448
Title: Sequential Modeling of Spatial Temporal Image Data
Author(s): Shufei Ge* and Shijia Wang and Liangliang Wang and Farouk Nathoo
Companies: Simon Fraser University and Simon Fraser University and Simon Fraser University and University of Victoria
Keywords: online clustering; Sequential Monte Carlo; Markov chain Monte Carlo

In this paper, we propose an sequential clustering method for the stream type of image data based on mixtures of spatial spline regressions. MCMC algorithm is derived to make inference for the parameters in our proposed model. However, MCMC has to be rerun when new data arrive. To tackle this issue, we propose an online SMC algorithm to deal with stream type image data. The data augmentation and mixture proposal improve the efficiency of the proposed algorithm. Our method is demonstrated by both simulations and an application to brain image data.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program