Twin Parametric Margin Support Vector Regression Model with Huber Loss Function
Mathematical Methods in the Applied Sciences · 2026-08 · 49 (12) · 13444-13468
DOI: 10.1002/mma.70748 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematical Methods in the Applied Sciences, online erschienen am 16.04.2026. Verfasst von Urairat Deepan und 3 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben.
Abstract (Originalsprache)
Although there are some recent methods, such as SVR, TSVR, and TPSVR, that enhance training speed by using nonparallel hyperplanes, they remain sensitive to outliers and non‐Gaussian noise, like the ‐insensitive loss function‐based methods. We propose a method to tackle this issue, namely the Huberized TPSVR framework. This model offers a dual protection mechanism: the parametric margins adapt to the local density in the data, while the integrated Huber loss function guides the learning process through robust noise and extreme outliers. Our experiments on complex chemical and clinical data reveal the remarkable superiority of Huberized TPSVR over standard models in terms of both stability and accuracy, which provides an efficient approach for addressing the messy nature of real‐world multidimensional data.
Zitieren
APA
Deepan, U., Seangwattana, T., Jirakitpuwapat, W., & Suttiarporn, P. (2026). Twin Parametric Margin Support Vector Regression Model with Huber Loss Function. Mathematical Methods in the Applied Sciences, 49(12), 13444-13468. https://doi.org/10.1002/mma.70748
Vancouver
Deepan U, Seangwattana T, Jirakitpuwapat W, Suttiarporn P. Twin Parametric Margin Support Vector Regression Model with Huber Loss Function. Mathematical Methods in the Applied Sciences. 2026;49(12):13444-13468. doi:10.1002/mma.70748
BibTeX
@article{Deepan2026,
author = {Deepan, Urairat and Seangwattana, Thidaporn and Jirakitpuwapat, Wachirapong and Suttiarporn, Panawan},
title = {Twin Parametric Margin Support Vector Regression Model with Huber Loss Function},
journal = {Mathematical Methods in the Applied Sciences},
year = {2026},
volume = {49},
number = {12},
pages = {13444--13468},
doi = {10.1002/mma.70748}
}
EUVIMED