skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Discriminant forest classification method and system

Abstract

A hybrid machine learning methodology and system for classification that combines classical random forest (RF) methodology with discriminant analysis (DA) techniques to provide enhanced classification capability. A DA technique which uses feature measurements of an object to predict its class membership, such as linear discriminant analysis (LDA) or Andersen-Bahadur linear discriminant technique (AB), is used to split the data at each node in each of its classification trees to train and grow the trees and the forest. When training is finished, a set of n DA-based decision trees of a discriminant forest is produced for use in predicting the classification of new samples of unknown class.

Inventors:
; ; ; ; ;
Publication Date:
Research Org.:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1080437
Patent Number(s):
8,306,942
Application Number:
12/436,667
Assignee:
Lawrence Livermore National Security, LLC (Livermore, CA)
DOE Contract Number:  
AC52-07NA27344
Resource Type:
Patent
Country of Publication:
United States
Language:
English
Subject:
54 ENVIRONMENTAL SCIENCES

Citation Formats

Chen, Barry Y., Hanley, William G., Lemmond, Tracy D., Hiller, Lawrence J., Knapp, David A., and Mugge, Marshall J. Discriminant forest classification method and system. United States: N. p., 2012. Web.
Chen, Barry Y., Hanley, William G., Lemmond, Tracy D., Hiller, Lawrence J., Knapp, David A., & Mugge, Marshall J. Discriminant forest classification method and system. United States.
Chen, Barry Y., Hanley, William G., Lemmond, Tracy D., Hiller, Lawrence J., Knapp, David A., and Mugge, Marshall J. 2012. "Discriminant forest classification method and system". United States. https://www.osti.gov/servlets/purl/1080437.
@article{osti_1080437,
title = {Discriminant forest classification method and system},
author = {Chen, Barry Y. and Hanley, William G. and Lemmond, Tracy D. and Hiller, Lawrence J. and Knapp, David A. and Mugge, Marshall J.},
abstractNote = {A hybrid machine learning methodology and system for classification that combines classical random forest (RF) methodology with discriminant analysis (DA) techniques to provide enhanced classification capability. A DA technique which uses feature measurements of an object to predict its class membership, such as linear discriminant analysis (LDA) or Andersen-Bahadur linear discriminant technique (AB), is used to split the data at each node in each of its classification trees to train and grow the trees and the forest. When training is finished, a set of n DA-based decision trees of a discriminant forest is produced for use in predicting the classification of new samples of unknown class.},
doi = {},
url = {https://www.osti.gov/biblio/1080437}, journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Nov 06 00:00:00 EST 2012},
month = {Tue Nov 06 00:00:00 EST 2012}
}

Works referenced in this record:

Random decision forests
conference, January 1995


Random Forest:  A Classification and Regression Tool for Compound Classification and QSAR Modeling
journal, November 2003


The use of Multiple Measurements in Taxonomic Problems
journal, September 1936


The random subspace method for constructing decision forests
journal, January 1998


Rotation Forest: A New Classifier Ensemble Method
journal, October 2006


Bagging predictors
journal, August 1996


Random Forests
journal, January 2001


Classification into two Multivariate Normal Distributions with Different Covariance Matrices
journal, June 1962


Decision Forest:  Combining the Predictions of Multiple Independent Decision Tree Models
journal, February 2003