Projection Support Vector Machine Generators

González-Castaño, Francisco J.; García-Palomares, Ubaldo M.; Meyer, Robert R.

doi:10.1023/b:mach.0000008083.47006.86

Cited by 7 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, each original point is mapped into a new one in IR 30 . We only allow a subset of the original points in the kernel subset because this strategy produced good results in [9], for a low increase in computing load.…”

Section: Nonlinear Kernel Approachmentioning

confidence: 99%

Support Vector Machine Detection of Peer-to-Peer Traffic in High-Performance Routers with Packet Sampling: Nonlinear Kernel Approach

González-Castaño

Rodríguez-Hernández

Martinez-Alvarez

et al. 2007

Computational Science – ICCS 2007

View full text Add to dashboard Cite

Abstract. In this paper, we apply nonlinear support vector machines to identify peer-to-peer (p2p) traffic in high-performance routers with packet sampling. Due to their high port rates, those routers cannot extract the headers of all the packets that traverse them, but only a sample. The results in this paper suggest that nonlinear support vector machines are highly successful and outperform recent approaches like [1,2].

show abstract

Section: Nonlinear Kernel Approachmentioning

confidence: 99%

Support Vector Machine Detection of Peer-to-Peer Traffic in High-Performance Routers with Packet Sampling: Nonlinear Kernel Approach

González-Castaño

Rodríguez-Hernández

Martinez-Alvarez

et al. 2007

Computational Science – ICCS 2007

View full text Add to dashboard Cite

show abstract

“…Support vector machines (SVMs), introduced by Vapnik and co-workers (Cortes & Vapnik, (1995;Vapnik, 1999), are a class of highly effective machine learning models for pattern classification. SVMs are based on statistical learning theory (Trafalis & Ince, 2000;Vapnik, 1998Vapnik, , 2013González-Castano et al, 2004;Fung & Mangasarian, 2005) and have been applied extensively in relation to binary classification problems. The traditional SVM model works by margin maximisation; deriving two unique parallel supporting hyperplanes such that the distance between the samples of two classes is maximized.…”

Section: Introductionmentioning

confidence: 99%

Large-scale pinball twin support vector machines

et al. 2021

View full text Add to dashboard Cite

Twin support vector machines (TWSVMs) have been shown to be effective classifiers for a range of pattern classification tasks. However, the TWSVM formulation suffers from a range of shortcomings: (i) TWSVM uses hinge loss function which renders it sensitive to dataset outliers (noise sensitivity). (ii) It requires a matrix inversion calculation in the Wolfe-dual formulation which is intractable for datasets with large numbers of features/ samples. (iii) TWSVM minimizes the empirical risk instead of the structural risk in its formulation with the consequent risk of overfitting. This paper proposes a novel large scale pinball twin support vector machines (LPTWSVM) to address these shortcomings. The proposed LPTWSVM model firstly utilizes the pinball loss function to achieve a high level of noise insensitivity, especially in relation to data with substantial feature noise. Secondly, and most significantly, the proposed LPTWSVM formulation eliminates the need to calculate inverse matrices in the dual problem (which apart from being very computationally demanding may not be possible due to matrix singularity). Further, LPTWSVM does not employ kernel-generated surfaces for the non-linear case, instead using the kernel trick directly; this ensures that the proposed LPTWSVM is a fully modular kernel approach in contrast to the original TWSVM. Lastly, structural risk is explicitly minimized in LPT-WSVM with consequent improvement in classification accuracy (we explicitly analyze the properties of classification accuracy and noise insensitivity of the proposed LPTWSVM). Experiments on benchmark datasets show that the proposed LPTWSVM model may be effectively deployed on large datasets and that it exhibits similar or better performance on most datasets in comparison to relevant baseline methods.

show abstract

“…separated records. The definition of i η is one of the major differences between the proposed model and other existing approaches(Fung 2003, Gonzalez-Castano andMeyer 2000). s objective function and the weight b W is an arbitrary positive number.…”

mentioning

confidence: 99%

A New Multi-criteria Convex Quadratic Programming Model for Credit Analysis

Kou

Peng

Shi

et al. 2006

Computational Science – ICCS 2006

View full text Add to dashboard Cite

Mathematical programming based methods have been applied to credit risk analysis and have proven to be powerful tools. One challenging issue in mathematical programming is the computation complexity in finding optimal solutions. To overcome this difficulty, this paper proposes a Multi-criteria Convex Quadratic Programming model (MCCQP). Instead of looking for the global optimal solution, the proposed model only needs to solve a set of linear equations. We test the model using three credit risk analysis datasets and compare MCCQP results with four well-known classification methods: LDA, Decision Tree, SVMLight, and LibSVM. The experimental results indicate that the proposed MCCQP model achieves as good as or even better classification accuracies than other methods.

show abstract

Projection Support Vector Machine Generators

Cited by 7 publications

References 18 publications

Support Vector Machine Detection of Peer-to-Peer Traffic in High-Performance Routers with Packet Sampling: Nonlinear Kernel Approach

Support Vector Machine Detection of Peer-to-Peer Traffic in High-Performance Routers with Packet Sampling: Nonlinear Kernel Approach

Large-scale pinball twin support vector machines

A New Multi-criteria Convex Quadratic Programming Model for Credit Analysis

Contact Info

Product

Resources

About