A novel technique for multivariate data analysis using
a two-stage genetic programming (GP) routine for
feature selection is described. The method is compared
with conventional genetic programming for the
classification of genetically modified barley.
Metabolic fingerprinting by 1H NMR spectroscopy was
used to analyse the differences between transgenic and
null-segregant plants. We show that the method has a
number of major advantages over standard genetic
programming techniques. By selecting a minimal set of
characteristic features in the data, the method
provides models that are easier to interpret. Moreover
the new method achieves better classification results
and convergence is reached significantly faster.
%0 Journal Article
%1 Davis:Nfs:06
%A Davis, Richard A.
%A Charlton, Adrian J.
%A Oehlschlager, Sarah
%A Wilson, Julie C.
%D 2006
%J Chemometrics and Intelligent Laboratory Systems
%K Feature Metabolomics, Multivariate NMR algorithms, analysis, data genetic programming, selection,
%N 1
%P 50--59
%R doi:10.1016/j.chemolab.2005.09.006
%T Novel feature selection method for genetic programming
using metabolomic 1H NMR data
%V 81
%X A novel technique for multivariate data analysis using
a two-stage genetic programming (GP) routine for
feature selection is described. The method is compared
with conventional genetic programming for the
classification of genetically modified barley.
Metabolic fingerprinting by 1H NMR spectroscopy was
used to analyse the differences between transgenic and
null-segregant plants. We show that the method has a
number of major advantages over standard genetic
programming techniques. By selecting a minimal set of
characteristic features in the data, the method
provides models that are easier to interpret. Moreover
the new method achieves better classification results
and convergence is reached significantly faster.
@article{Davis:Nfs:06,
abstract = {A novel technique for multivariate data analysis using
a two-stage genetic programming (GP) routine for
feature selection is described. The method is compared
with conventional genetic programming for the
classification of genetically modified barley.
Metabolic fingerprinting by 1H NMR spectroscopy was
used to analyse the differences between transgenic and
null-segregant plants. We show that the method has a
number of major advantages over standard genetic
programming techniques. By selecting a minimal set of
characteristic features in the data, the method
provides models that are easier to interpret. Moreover
the new method achieves better classification results
and convergence is reached significantly faster.},
added-at = {2008-06-19T17:35:00.000+0200},
author = {Davis, Richard A. and Charlton, Adrian J. and Oehlschlager, Sarah and Wilson, Julie C.},
biburl = {https://www.bibsonomy.org/bibtex/2434436748a897eb6a00f92c7f3192b4a/brazovayeye},
doi = {doi:10.1016/j.chemolab.2005.09.006},
interhash = {21c364132e394a1cdcaf936dc8f1d9d4},
intrahash = {434436748a897eb6a00f92c7f3192b4a},
journal = {Chemometrics and Intelligent Laboratory Systems},
keywords = {Feature Metabolomics, Multivariate NMR algorithms, analysis, data genetic programming, selection,},
month = {March},
number = 1,
pages = {50--59},
timestamp = {2008-06-19T17:38:26.000+0200},
title = {Novel feature selection method for genetic programming
using metabolomic {1H NMR} data},
volume = 81,
year = 2006
}