Skip to main content

New Statistical Transfer Learning Models for Health Care Applications

Abstract Transfer learning is a sub-field of statistical modeling and machine learning. It refers to methods that integrate the knowledge of other domains (called source domains) and the data of the target domain in a mathematically rigorous and intelligent way, to develop a better model for the target domain than a model using the data of the target domain alone. While transfer learning is a promising approach in various application domains, my dissertation research focuses on the particular application in health care, including telemonitoring of Parkinson’s Disease (PD) and radiomics for glioblastoma.

The first topic is a Mixed Effects Transfer Learning (METL) model that can flexibly incorporate mixed effects and a general-form covariance mat... (more)
Created Date 2018
Contributor Yoon, Hyunsoo (Author) / Li, Jing (Advisor) / Wu, Teresa (Committee member) / Yan, Hao (Committee member) / Hu, Leland S. (Committee member) / Arizona State University (Publisher)
Subject Information science / Statistics / Health sciences / Health care / Machine learning / Mixed models / Negative transfer / Telemonitoring / Transfer learning
Type Doctoral Dissertation
Extent 137 pages
Language English
Note Doctoral Dissertation Industrial Engineering 2018
Collaborating Institutions Graduate College / ASU Library
Additional Formats MODS / OAI Dublin Core / RIS

  Full Text
3.5 MB application/pdf
Download Count: 705

Description Dissertation/Thesis