Activity Number:
|
483
- Integration of Diverse Data Sets
|
Type:
|
Invited
|
Date/Time:
|
Wednesday, August 2, 2017 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistical Learning and Data Science
|
Abstract #322307
|
View Presentation
|
Title:
|
Data Integration for Heterogenous Data Sets
|
Author(s):
|
Alfred Hero, III*
|
Companies:
|
University of Michigan
|
Keywords:
|
data science ;
big data ;
diverse data
|
Abstract:
|
Heterogeneous data comes in two forms: sample heterogeneity, which is due to the existence of diverse data types in each sample vector; and population heterogeneity, which is due to non-identical distribution of different sample realizations. This presentation will focus on the problem of sample heterogeneity. We will present a case study and a multimodal factor analysis framework for combining the information from different data types and different scales.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2017 program
|