Online Program Home
My Program

Abstract Details

Activity Number: 465 - SPEED: Statistical Computing: Methods, Implementation, and Application, Part 1
Type: Contributed
Date/Time: Wednesday, July 31, 2019 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistical Computing
Abstract #307197
Title: Tensor Variate Models Applied to Sensor Data
Author(s): Peter Tait* and Paul D McNicholas
Companies: McMaster University and McMaster University
Keywords: child health; physical activity; accelerometers; tensors
Abstract:

Motivated by our work in pediatric research, a tensor variate model is proposed to cluster tensor variate data. The model builds on the Tucker tensor decomposition and which allows the parameters to be easily interpretable. The model parameters are estimated using an EM algorithm. Our model is implemented in Julia, a dynamic and high performance numerical computing language. The tensor variate data is generated from accelerometers worn by a cohort of school aged children.


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

Back to the full JSM 2019 program