Twin SVM with a reject option through ROC curve

Dongyun Lin, Lei Sun, Kar Ann Toh, Jing Bo Zhang, Zhiping Lin

Research output: Contribution to journalArticle

Abstract

This paper proposes a new method which embeds a reject option in twin support vector machine (RO-TWSVM) through the Receiver Operating Characteristic (ROC) curve for binary classification. The proposed RO-TWSVM enhances the classification robustness through inclusion of an effective rejection rule for potentially misclassified samples. The method is formulated based on a cost-sensitive framework which follows the principle of minimization of the expected cost of classification. Extensive experiments are conducted on synthetic and real-world data sets to compare the proposed RO-TWSVM with the original TWSVM without a reject option (TWSVM-without-RO) and the existing SVM with a reject option (RO-SVM). The experimental results demonstrate that our RO-TWSVM significantly outperforms TWSVM-without-RO, and in general, performs better than RO-SVM.

Original languageEnglish
Pages (from-to)1710-1732
Number of pages23
JournalJournal of the Franklin Institute
Volume355
Issue number4
DOIs
Publication statusPublished - 2018 Mar

Fingerprint

Receiver Operating Characteristic Curve
Support vector machines
Support Vector Machine
Costs
Binary Classification
Rejection
Inclusion
Robustness
Experiments
Experimental Results
Demonstrate
Experiment

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications
  • Applied Mathematics

Cite this

Lin, Dongyun ; Sun, Lei ; Toh, Kar Ann ; Zhang, Jing Bo ; Lin, Zhiping. / Twin SVM with a reject option through ROC curve. In: Journal of the Franklin Institute. 2018 ; Vol. 355, No. 4. pp. 1710-1732.
@article{a918fad2f8e34fb99d13d53a9d7effc0,
title = "Twin SVM with a reject option through ROC curve",
abstract = "This paper proposes a new method which embeds a reject option in twin support vector machine (RO-TWSVM) through the Receiver Operating Characteristic (ROC) curve for binary classification. The proposed RO-TWSVM enhances the classification robustness through inclusion of an effective rejection rule for potentially misclassified samples. The method is formulated based on a cost-sensitive framework which follows the principle of minimization of the expected cost of classification. Extensive experiments are conducted on synthetic and real-world data sets to compare the proposed RO-TWSVM with the original TWSVM without a reject option (TWSVM-without-RO) and the existing SVM with a reject option (RO-SVM). The experimental results demonstrate that our RO-TWSVM significantly outperforms TWSVM-without-RO, and in general, performs better than RO-SVM.",
author = "Dongyun Lin and Lei Sun and Toh, {Kar Ann} and Zhang, {Jing Bo} and Zhiping Lin",
year = "2018",
month = "3",
doi = "10.1016/j.jfranklin.2017.05.003",
language = "English",
volume = "355",
pages = "1710--1732",
journal = "Journal of the Franklin Institute",
issn = "0016-0032",
publisher = "Elsevier Limited",
number = "4",

}

Twin SVM with a reject option through ROC curve. / Lin, Dongyun; Sun, Lei; Toh, Kar Ann; Zhang, Jing Bo; Lin, Zhiping.

In: Journal of the Franklin Institute, Vol. 355, No. 4, 03.2018, p. 1710-1732.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Twin SVM with a reject option through ROC curve

AU - Lin, Dongyun

AU - Sun, Lei

AU - Toh, Kar Ann

AU - Zhang, Jing Bo

AU - Lin, Zhiping

PY - 2018/3

Y1 - 2018/3

N2 - This paper proposes a new method which embeds a reject option in twin support vector machine (RO-TWSVM) through the Receiver Operating Characteristic (ROC) curve for binary classification. The proposed RO-TWSVM enhances the classification robustness through inclusion of an effective rejection rule for potentially misclassified samples. The method is formulated based on a cost-sensitive framework which follows the principle of minimization of the expected cost of classification. Extensive experiments are conducted on synthetic and real-world data sets to compare the proposed RO-TWSVM with the original TWSVM without a reject option (TWSVM-without-RO) and the existing SVM with a reject option (RO-SVM). The experimental results demonstrate that our RO-TWSVM significantly outperforms TWSVM-without-RO, and in general, performs better than RO-SVM.

AB - This paper proposes a new method which embeds a reject option in twin support vector machine (RO-TWSVM) through the Receiver Operating Characteristic (ROC) curve for binary classification. The proposed RO-TWSVM enhances the classification robustness through inclusion of an effective rejection rule for potentially misclassified samples. The method is formulated based on a cost-sensitive framework which follows the principle of minimization of the expected cost of classification. Extensive experiments are conducted on synthetic and real-world data sets to compare the proposed RO-TWSVM with the original TWSVM without a reject option (TWSVM-without-RO) and the existing SVM with a reject option (RO-SVM). The experimental results demonstrate that our RO-TWSVM significantly outperforms TWSVM-without-RO, and in general, performs better than RO-SVM.

UR - http://www.scopus.com/inward/record.url?scp=85019881276&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019881276&partnerID=8YFLogxK

U2 - 10.1016/j.jfranklin.2017.05.003

DO - 10.1016/j.jfranklin.2017.05.003

M3 - Article

AN - SCOPUS:85019881276

VL - 355

SP - 1710

EP - 1732

JO - Journal of the Franklin Institute

JF - Journal of the Franklin Institute

SN - 0016-0032

IS - 4

ER -