Robust kernel-based regression

Budi Santosa; Theodore B. Trafalis

Robust kernel-based regression

Budi Santosa^*
, Theodore B. Trafalis

^*Corresponding author for this work

University of Oklahoma

Research output: Contribution to journal › Article › peer-review

Abstract

In this research, a robust optimization approach applied to support vector regression (SVR) is investigated. A novel kernel based-method is developed to address the problem of data uncertainty where each data point is inside a sphere. The model is called robust SVR. Computational results show that the resulting robust SVR model is better than traditional SVR in terms of robustness and generalization error.

Original language	English
Pages (from-to)	424-429
Number of pages	6
Journal	WSEAS Transactions on Systems
Volume	5
Issue number	2
Publication status	Published - Feb 2006

Keywords

Kernel Method
Regression
Robust Optimization
Support Vector Machine
Uncertainty

Cite this

@article{45d12d1053154fefbc4dd16e05255feb,

title = "Robust kernel-based regression",

abstract = "In this research, a robust optimization approach applied to support vector regression (SVR) is investigated. A novel kernel based-method is developed to address the problem of data uncertainty where each data point is inside a sphere. The model is called robust SVR. Computational results show that the resulting robust SVR model is better than traditional SVR in terms of robustness and generalization error.",

keywords = "Kernel Method, Regression, Robust Optimization, Support Vector Machine, Uncertainty",

author = "Budi Santosa and Trafalis, \{Theodore B.\}",

year = "2006",

month = feb,

language = "English",

volume = "5",

pages = "424--429",

journal = "WSEAS Transactions on Systems",

issn = "1109-2777",

publisher = "World Scientific and Engineering Academy and Society",

number = "2",

}

TY - JOUR

T1 - Robust kernel-based regression

AU - Santosa, Budi

AU - Trafalis, Theodore B.

PY - 2006/2

Y1 - 2006/2

N2 - In this research, a robust optimization approach applied to support vector regression (SVR) is investigated. A novel kernel based-method is developed to address the problem of data uncertainty where each data point is inside a sphere. The model is called robust SVR. Computational results show that the resulting robust SVR model is better than traditional SVR in terms of robustness and generalization error.

AB - In this research, a robust optimization approach applied to support vector regression (SVR) is investigated. A novel kernel based-method is developed to address the problem of data uncertainty where each data point is inside a sphere. The model is called robust SVR. Computational results show that the resulting robust SVR model is better than traditional SVR in terms of robustness and generalization error.

KW - Kernel Method

KW - Regression

KW - Robust Optimization

KW - Support Vector Machine

KW - Uncertainty

UR - https://www.scopus.com/pages/publications/29744433313

M3 - Article

AN - SCOPUS:29744433313

SN - 1109-2777

VL - 5

SP - 424

EP - 429

JO - WSEAS Transactions on Systems

JF - WSEAS Transactions on Systems

IS - 2

ER -

Robust kernel-based regression

Abstract

Keywords

Other files and links

Fingerprint

Cite this