TPMSVM: A novel twin parametric-margin support vector machine for pattern recognition

Peng, Xinjun

doi:10.1016/j.patcog.2011.03.031

Cited by 187 publications

(57 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A rough marginbased ν-TWSVM incorporating the rough set theory [36] was proposed in [37] to give the different penalties to the misclassified points. The twin parametric-margin SVM (TPMSVM) [38], motivated by the TWSVM and the par-ν-SVM [39], determines a pair of parametric-margin hyperplanes, which can automatically adjust a flexible margin and are suitable for the heteroscedastic error structure. Its least squares version can be found in [40].…”

Section: Variants and Extensions Of Twsvmsmentioning

confidence: 99%

“…Peng and Xu [74] constructed two Mahalanobis distancebased kernels according to the covariance matrices of two classes of data for optimizing the nonparallel hyperplanes, the Mahalanobis distance-based SVM (TMSVM) is suitable especially for the case that the covariance matrices of two classes of data are obviously different. For the TPMSVM [38], Peng et al [75] presented a structural version (STPMSVM) by focusing on the structural information of the corresponding classes based on the cluster granularity.…”

Section: Structural Twsvmsmentioning

confidence: 99%

See 1 more Smart Citation

Review on: Twin Support Vector Machines

Tian

2014

Ann. Data. Sci.

View full text Add to dashboard Cite

Twin support vector machine (TWSVM), an useful extension of the traditional SVM, becomes the current researching hot spot in machine learning during the last few years. For the binary classification problem, the basic idea of TWSVM is to seek two nonparallel proximal hyperplanes such that each hyperplane is closer to one of the two classes and is at least one distance from the other. TWSVM has lower computational complexity and better generalization ability, therefore in the last few years it has been studied extensively and developed rapidly. Considering the many variants of TWSVM, a systematic survey is needed and helpful to understand and use this family of data mining techniques more easily. The purpose of this paper is to closely review TWSVMs and provide an insightful understanding of current developments, at the same time point out their limitations and highlight the major opportunities and challenges, as well as potential important research directions.

show abstract

Section: Variants and Extensions Of Twsvmsmentioning

confidence: 99%

Section: Structural Twsvmsmentioning

confidence: 99%

Review on: Twin Support Vector Machines

Tian

2014

Ann. Data. Sci.

View full text Add to dashboard Cite

show abstract

“…This TPMSVM, in the spirit of the twin support vector machine (TWSVM), determines indirectly the separating hyperplane through a pair of nonparallel parametric-margin hyperplanes solved by two smaller sized support vector machine (SVM)-type problems [17]. This TPMSVM is suitable for many cases, especially when the data has heteroscedastic error structure.…”

Section: Data Mining and Svmmentioning

confidence: 99%

Data Mining and Soft Computing using Support Vector Machine: A Survey

Das¹,

Saha²

2013

IJCA

View full text Add to dashboard Cite

“…In terms of generalizations, TWSVM favorably compare with SVM and GEPSVM. Recently, some extensions have been proposed that includes the least square TWSVM [7]- [8], Smooth TWSVM [9], improvements on TWSVM (TBSVM) [10], TPMSVM [11], TSVR [12] and LTSVR [13]. Finally, on the recent study of 1-norm TWSVM the interested reader is referred to [14], [15].…”

Section: Introductionmentioning

confidence: 99%

Smoothing Technique on Linear Programming Twin Support Vector Machines

Tanveer¹

2013

IJMLC

View full text Add to dashboard Cite

Abstract-In this paper, a new smoothing technique on linear programming TWSVM formulation is proposed whose solution is obtained by solving a pair of dual exterior penalty problems as unconstrained minimization problems using Newton method. Our approach has the advantage that a pair of matrix equation of order equals to the number of input examples is solved at each iteration of the algorithm and can be easily implemented in MATLAB without using any optimization toolbox. Computational comparisons of our proposed method against original TWSVM, GEPSVM and SVM indicate that our method is not only fast, but also shows good generalization performance.

show abstract

TPMSVM: A novel twin parametric-margin support vector machine for pattern recognition

Cited by 187 publications

References 33 publications

Review on: Twin Support Vector Machines

Review on: Twin Support Vector Machines

Data Mining and Soft Computing using Support Vector Machine: A Survey

Smoothing Technique on Linear Programming Twin Support Vector Machines

Contact Info

Product

Resources

About