Genetic programming (GP) is a stochastic process for
automatically generating computer programs. In this
paper, three GP-based approaches for solving
multi-class classification problems in roller bearing
fault detection are proposed. Single-GP maps all the
classes onto the one-dimensional GP output.
Independent-GPs singles out each class separately by
evolving a binary GP for each class independently.
Bundled-GPs also has one binary GP for each class, but
these GPs are evolved together with the aim of
selecting as few features as possible. The
classification results and the features each algorithm
has selected are compared with genetic algorithm (GA)
based approaches GA/ANN and GA/SVM. Experiments show
that bundled-GPs is strong in feature selection while
retaining high performance, which equals or outperforms
the two previous GA-based approaches.
%0 Journal Article
%1 Zhang:2007:MSSP
%A Zhang, Liang
%A Nandi, Asoke K.
%D 2007
%J Mechanical Systems and Signal Processing
%K Condition Fault Multi-class Roller algorithms, bearing classification, genetic monitoring, programming,
%N 3
%P 1273--1284
%R doi:10.1016/j.ymssp.2006.04.004
%T Fault classification using genetic programming
%V 21
%X Genetic programming (GP) is a stochastic process for
automatically generating computer programs. In this
paper, three GP-based approaches for solving
multi-class classification problems in roller bearing
fault detection are proposed. Single-GP maps all the
classes onto the one-dimensional GP output.
Independent-GPs singles out each class separately by
evolving a binary GP for each class independently.
Bundled-GPs also has one binary GP for each class, but
these GPs are evolved together with the aim of
selecting as few features as possible. The
classification results and the features each algorithm
has selected are compared with genetic algorithm (GA)
based approaches GA/ANN and GA/SVM. Experiments show
that bundled-GPs is strong in feature selection while
retaining high performance, which equals or outperforms
the two previous GA-based approaches.
@article{Zhang:2007:MSSP,
abstract = {Genetic programming (GP) is a stochastic process for
automatically generating computer programs. In this
paper, three GP-based approaches for solving
multi-class classification problems in roller bearing
fault detection are proposed. Single-GP maps all the
classes onto the one-dimensional GP output.
Independent-GPs singles out each class separately by
evolving a binary GP for each class independently.
Bundled-GPs also has one binary GP for each class, but
these GPs are evolved together with the aim of
selecting as few features as possible. The
classification results and the features each algorithm
has selected are compared with genetic algorithm (GA)
based approaches GA/ANN and GA/SVM. Experiments show
that bundled-GPs is strong in feature selection while
retaining high performance, which equals or outperforms
the two previous GA-based approaches.},
added-at = {2008-06-19T17:46:40.000+0200},
author = {Zhang, Liang and Nandi, Asoke K.},
biburl = {https://www.bibsonomy.org/bibtex/27a3d6939636ea8cfc63040977e061dfe/brazovayeye},
doi = {doi:10.1016/j.ymssp.2006.04.004},
interhash = {eccf3bdf145547d027c059e2d08144c3},
intrahash = {7a3d6939636ea8cfc63040977e061dfe},
journal = {Mechanical Systems and Signal Processing},
keywords = {Condition Fault Multi-class Roller algorithms, bearing classification, genetic monitoring, programming,},
month = {April},
number = 3,
pages = {1273--1284},
timestamp = {2008-06-19T17:55:30.000+0200},
title = {Fault classification using genetic programming},
volume = 21,
year = 2007
}