Hossein Moosaei, Milan Hladík, Ahmad Mousavi, Zheming Gao, and Haojie Fu. Quadratic surface twin support vector machine for imbalanced data. Int. J. Mach. Learn. Cyber., 17(5):250:1–18, May 2026.
[PDF] [gzipped postscript] [postscript] [HTML]
Binary classification tasks with imbalanced classes pose significant challenges in machine learning. Traditional classifiers often struggle to accurately capture the characteristics of the minority class, resulting in biased models with subpar predictive performance. In this paper, we introduce a novel approach to tackle this issue by leveraging Universum points to support the minority class within quadratic twin support vector machine models. Unlike traditional classifiers, our models utilize quadratic surfaces instead of hyperplanes for binary classification, providing greater flexibility in modeling complex decision boundaries. By incorporating Universum points, our approach enhances classification accuracy and generalization performance on imbalanced datasets. We generated four artificial datasets to demonstrate the flexibility of the proposed methods. Additionally, we validated the effectiveness of our approach through empirical evaluations on benchmark datasets, demonstrating superior performance compared to conventional classifiers and existing methods for imbalanced classification.
@article{MooHla2026a,
author = "Hossein Moosaei and Milan Hlad\'{\i}k and Ahmad Mousavi and Zheming Gao and Haojie Fu",
title = "Quadratic surface twin support vector machine for imbalanced data",
journal = "Int. J. Mach. Learn. Cyber.",
fjournal = "International Journal of Machine Learning and Cybernetics",
volume = "17",
number = "5",
pages = "250:1-18",
month = "May",
year = "2026",
doi = "10.1007/s13042-026-03059-8",
issn = "1868-8071",
issnonline = "1868-808X",
url = "https://doi.org/10.1007/s13042-026-03059-8",
bib2html_dl_html = "https://link.springer.com/article/10.1007/s13042-026-03059-8",
bib2html_dl_pdf = "https://rdcu.be/fc3F5",
abstract = "Binary classification tasks with imbalanced classes pose significant challenges in machine learning. Traditional classifiers often struggle to accurately capture the characteristics of the minority class, resulting in biased models with subpar predictive performance. In this paper, we introduce a novel approach to tackle this issue by leveraging Universum points to support the minority class within quadratic twin support vector machine models. Unlike traditional classifiers, our models utilize quadratic surfaces instead of hyperplanes for binary classification, providing greater flexibility in modeling complex decision boundaries. By incorporating Universum points, our approach enhances classification accuracy and generalization performance on imbalanced datasets. We generated four artificial datasets to demonstrate the flexibility of the proposed methods. Additionally, we validated the effectiveness of our approach through empirical evaluations on benchmark datasets, demonstrating superior performance compared to conventional classifiers and existing methods for imbalanced classification.",
keywords = "Binary classification; Quadratic support vector machine; Twin support vector machine; Class imbalance; Universum data",
}
Generated by bib2html.pl (written by Patrick Riley ) on Mon Sep 21, 2026 09:42:18