International Journal of Computational Intelligence Systems

Volume 7, Issue 1, February 2014, Pages 12 - 24

A DC programming approach for feature selection in the Minimax Probability Machine

Authors
Liming Yang, Ribo Ju
Corresponding Author
Liming Yang
Received 5 May 2011, Accepted 21 July 2013, Available Online 3 February 2014.
DOI
https://doi.org/10.1080/18756891.2013.864471How to use a DOI?
Keywords
Feature selection, Minimax probability machine, DC programming
Abstract
This paper presents a new feature selection framework based on the -norm, in which data are summarized by their moments of the class conditional densities. However, discontinuity of the -norm makes it difficult to find the optimal solution. We apply a proper approximation of the -norm and a bound on the misclassification probability involving the mean and covariance of the dataset, to derive a robust difference of convex functions (DC) program formulation, while the DC optimization algorithm is used to solve the problem effectively. Furthermore, a kernelized version of this problem is also presented in this work. Experimental results on both real and synthetic datasets show that the proposed formulations can select fewer features than the traditional Minimax Probability Machine and the -norm state.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Journal
International Journal of Computational Intelligence Systems
Volume-Issue
7 - 1
Pages
12 - 24
Publication Date
2014/02
ISSN (Online)
1875-6883
ISSN (Print)
1875-6891
DOI
https://doi.org/10.1080/18756891.2013.864471How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - JOUR
AU  - Liming Yang
AU  - Ribo Ju
PY  - 2014
DA  - 2014/02
TI  - A DC programming approach for feature selection in the Minimax Probability Machine
JO  - International Journal of Computational Intelligence Systems
SP  - 12
EP  - 24
VL  - 7
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.1080/18756891.2013.864471
DO  - https://doi.org/10.1080/18756891.2013.864471
ID  - Yang2014
ER  -