DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Method of generating features optimal to a dataset and classifier

Abstract

A method of generating features optimal to a particular dataset and classifier is disclosed. A dataset of messages is inputted and a classifier is selected. An algebra of features is encoded. Computable features that are capable of describing the dataset from the algebra of features are selected. Irredundant features that are optimal for the classifier and the dataset are selected.

Inventors:
; ;
Issue Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1329308
Patent Number(s):
9471871
Application Number:
14/186,740
Assignee:
BATTELLE MEMORIAL INSTITUTE (Richland, WA)
Patent Classifications (CPCs):
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
DOE Contract Number:  
AC05-76RL01830
Resource Type:
Patent
Resource Relation:
Patent File Date: 2014 Feb 21
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING

Citation Formats

Bruillard, Paul J., Gosink, Luke J., and Jarman, Kenneth D. Method of generating features optimal to a dataset and classifier. United States: N. p., 2016. Web.
Bruillard, Paul J., Gosink, Luke J., & Jarman, Kenneth D. Method of generating features optimal to a dataset and classifier. United States.
Bruillard, Paul J., Gosink, Luke J., and Jarman, Kenneth D. Tue . "Method of generating features optimal to a dataset and classifier". United States. https://www.osti.gov/servlets/purl/1329308.
@article{osti_1329308,
title = {Method of generating features optimal to a dataset and classifier},
author = {Bruillard, Paul J. and Gosink, Luke J. and Jarman, Kenneth D.},
abstractNote = {A method of generating features optimal to a particular dataset and classifier is disclosed. A dataset of messages is inputted and a classifier is selected. An algebra of features is encoded. Computable features that are capable of describing the dataset from the algebra of features are selected. Irredundant features that are optimal for the classifier and the dataset are selected.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2016},
month = {10}
}

Works referenced in this record:

Crossover and mutation operators for grammar-guided genetic programming
journal, December 2006


Object Detection via Feature Synthesis Using MDL-Based Genetic Programming
journal, June 2005


Genetic Programming with a Genetic Algorithm for Feature Construction and Selection
journal, August 2005


Automatic Feature Generation for Machine Learning Based Optimizing Compilation
conference, March 2009

  • Leather, Hugh; Bonilla, Edwin; O'Boyle, Michael
  • 2009 7th Annual IEEE/ACM International Symposium on Code Generation and Optimization (CGO), 2009 International Symposium on Code Generation and Optimization
  • https://doi.org/10.1109/CGO.2009.21