Hossein Moosaei, Saeed Khosravi, Fatemeh Bazikar, Milan Hladík, and Mario Rosario Guarracino. A novel method for solving universum twin bounded support vector machine in the primal space. Ann. Math. Artif. Intell., 93:131–150, 2025.
[PDF] [gzipped postscript] [postscript] [HTML]
In supervised learning, the Universum, a third class that is not a part of either class in the classification task, has proven to be useful. In this study we propose (N$ \mathfrakU $TBSVM), a Newton-based approach for solving in the primal space the optimization problems related to Twin Bounded Support Vector Machines with Universum data ($\mathfrakU $TBSVM). In the N$ \mathfrakU $TBSVM, the constrained programming problems of $\mathfrakU $TBSVM are converted into unconstrained optimization problems, and a generalization of Newton’s method for solving the unconstrained problems is introduced. Numerical experiments on synthetic, UCI, and NDC data sets show the ability and effectiveness of the proposed N$ \mathfrakU $TBSVM. We apply the suggested method for gender detection from face images, and compare it with other methods.
@article{MooKho2025a,
author = "Hossein Moosaei and Saeed Khosravi and Fatemeh Bazikar and Milan Hlad\'{\i}k and Mario Rosario Guarracino",
title = "A novel method for solving universum twin bounded support vector machine in the primal space",
journal = "Ann. Math. Artif. Intell.",
fjournal = "Annals of Mathematics and Artificial Intelligence",
volume = "93",
pages = "131-150",
year = "2025",
doi = "10.1007/s10472-023-09896-5",
issn = "1573-7470",
url = "https://link.springer.com/article/10.1007/s10472-023-09896-5",
bib2html_dl_html = "https://doi.org/10.1007/s10472-023-09896-5",
bib2html_dl_pdf = "https://rdcu.be/eqNTy",
abstract = "In supervised learning, the Universum, a third class that is not a part of either class in the classification task, has proven to be useful. In this study we propose (N$ \mathfrak{U} $TBSVM), a Newton-based approach for solving in the primal space the optimization problems related to Twin Bounded Support Vector Machines with Universum data ($\mathfrak{U} $TBSVM). In the N$ \mathfrak{U} $TBSVM, the constrained programming problems of $\mathfrak{U} $TBSVM are converted into unconstrained optimization problems, and a generalization of Newton’s method for solving the unconstrained problems is introduced. Numerical experiments on synthetic, UCI, and NDC data sets show the ability and effectiveness of the proposed N$ \mathfrak{U} $TBSVM. We apply the suggested method for gender detection from face images, and compare it with other methods.",
keywords = "Twin bounded support vector machine; Universum; Newton’s method; Unconstrained optimization problem",
}
Generated by bib2html.pl (written by Patrick Riley ) on Fri Nov 07, 2025 16:53:24