A joint project of the Graduate School, Peabody College, and the Jean & Alexander Heard Library

Title page for ETD etd-07222016-224434

Type of Document Master's Thesis
Author VanHouten, Jacob Paul
Author's Email Address jacob.p.vanhouten@vanderbilt.edu
URN etd-07222016-224434
Title A Modified Random Forest Kernel for Highly Nonstationary Gaussian Process Regression with Application to Clinical Data
Degree Master of Science
Department Biostatistics
Advisory Committee
Advisor Name Title
Christopher J. Fonnesbeck Committee Chair
Thomas A. Lasko Committee Member
  • statistics
  • machine learning
  • data mining
  • longitudinal data
Date of Defense 2016-04-01
Availability unrestricted
Nonstationary Gaussian process regression can be used to transform irregularly episodic and noisy measurements into continuous probability densities to make them more compatible with standard machine learning algorithms. However, current inference algorithms are time-consuming or have difficulty with the highly bursty, extremely nonstationary data that are common in the medical domain. One efficient and flexible solution uses a partition kernel based on random forests, but its current embodiment produces undesirable pathologies rooted in the piecewise-constant nature of its inferred posteriors. I present a modified random forest kernel that adds a new sources of randomness to the trees, which overcomes existing pathologies and produces good results for highly bursty, extremely nonstationary clinical laboratory measurements.
  Filename       Size       Approximate Download Time (Hours:Minutes:Seconds) 
 28.8 Modem   56K Modem   ISDN (64 Kb)   ISDN (128 Kb)   Higher-speed Access 
  VanHouten_Thesis.pdf 943.55 Kb 00:04:22 00:02:14 00:01:57 00:00:58 00:00:05

Browse All Available ETDs by ( Author | Department )

If you have more questions or technical problems, please Contact LITS.