KMOD - a new support vector machine kernel with moderate decreasing for pattern recognition. Application to digit image recognition

Ayat, N.E.; Cheriet, Mohamed; Remaki, Lakhdar; Suen, Ching Y.

doi:10.1109/icdar.2001.953976

Cited by 37 publications

(30 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The points very close to each other are strongly correlated whereas points far apart have uncorrelated image in the augmented space [4]. This correlation is rather smooth.…”

Section: Multi-scale Rbf Kernelsmentioning

confidence: 78%

“…Hence, the complexity of the separating hyperplane depends on the nature and the properties of the used kernel [4]. There are many types of kernel functions such as linear kernel, polynomial kernel, sigmoid kernel, and RBF kernel.…”

Section: Introductionmentioning

confidence: 99%

“…It has been widely used in many applications such as pattern recognitions and function approximations. Basically, SVM operates a linear separation in an augmented space by means of some defined kernels satisfying Mercer's condition [2,3,4]. These kernels map the input vectors into a very high dimensional space, possibly of infinite dimension, where linear separation is more likely [4].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evolutionary strategies for multi-scale radial basis function kernels in support vector machines

Phienthrakul

Kijsirikul

2005

Proceedings of the 7th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

In support vector machines (SVM), the kernel functions which compute dot product in feature space significantly affect the performance of classifiers. Each kernel function is suitable for some tasks. A universal kernel is not possible, and the kernel must be chosen for the tasks under consideration by hand. In order to obtain a flexible kernel function, a family of radial basis function (RBF) kernels is proposed. Multi-scale RBF kernels are combined by including weights. Then, the evolutionary strategies are used to adjust these weights and the widths of the RBF kernels. The proposed kernel is proved to be a Mercer's kernel. The experimental results show that the use of multi-scale RBF kernels result in better performance than that of a single Gaussian RBF on benchmarks.

show abstract

“…The points very close to each other are strongly correlated whereas points far apart have uncorrelated image in the augmented space [4]. This correlation is rather smooth.…”

Section: Multi-scale Rbf Kernelsmentioning

confidence: 78%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evolutionary strategies for multi-scale radial basis function kernels in support vector machines

Phienthrakul

Kijsirikul

2005

Proceedings of the 7th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…III) Depending on the choice of kernel and the kernel's parameter, the distance order among the samples may not be preserved while carrying them into the feature space by the nonlinear mapping defined by the chosen kernel [12][13][14][15]. This means that the inverse image of the optimal separating hyperplane found in the feature space may be far away from the optimal separating surface in the input data space.…”

Section: Introductionmentioning

confidence: 99%

A penalty function method for designing efficient robust classifiers with input space optimal separating surfaces

Uçar¹,

Demir²,

Güzeliş³

2014

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

This paper considers robust classification as a constrained optimization problem. Where the constraints are nonlinear, inequalities defining separating surfaces, whose half spaces include or exclude the data depending on their classes and the cost, are used for attaining robustness and providing the minimum volume regions specified by the half spaces of the surfaces. The constraints are added to the cost using penalty functions to get an unconstrained problem for which the gradient descent method can be used. The separating surfaces, which are aimed to be found in this way, are optimal in the input data space in contrast to the conventional support vector machine (SVM) classifiers designed by the Lagrange multiplier method, which are optimal in the (transformed) feature space. Two types of surfaces, namely hyperellipsoidal and Gaussian-based surfaces created by radial basis functions (RBFs), are focused on in this paper due to their generality. Ellipsoidal classifiers are trained in 2 stages: a spherical surface is found in the first stage, and then the centers and the radii found in the first stage are taken as the initial input for the second stage to find the center and covariance matrix parameters of the ellipsoids. The penalty function approach to the design of robust classifiers enables the handling of multiclass classification. Compared to SVMs, multiple-kernel SVMs, and RBF classifiers, the proposed classifiers are found to be more efficient in terms of the required training time, parameter setting time, testing time, memory usage, and generalization error, especially for medium to large datasets. RBF-based input space optimal classifiers are also introduced for problems that are far from ellipsoidal, e.g., 2 Spirals.

show abstract

“…Then, a linear separating hyper plane is found by maximizing the margin between two classes in this space. Hence, the complexity of the separating hyper plane depends on the nature and the properties of the used kernel [2]. This paper proposes hybrid approach which combines support vector classifier with particle swarm optimization, in order to improve the strength of each individual technique and compensate for each other's weaknesses.…”

mentioning

confidence: 99%

Optimization of SVM Multiclass by Particle Swarm (PSO-SVM)

Ardjani¹,

Sadouni²

2010

IJMECS

View full text Add to dashboard Cite

Abstract-In many problems of classification, the performances of a classifier are often evaluated by a factor (rate of error).the factor is not well adapted for the complex real problems, in particular the problems multiclass. Our contribution consists in adapting an evolutionary method for optimization of this factor. Among the methods of optimization used we chose the method PSO (Particle Swarm Optimization) which makes it possible to optimize the performance of classifier SVM (Separating with Vast Margin). The experiments are carried out on corpus TIMIT. The results obtained show that approach PSO-SVM gives a better classification in terms of accuracy even though the execution time is increased..

show abstract

KMOD - a new support vector machine kernel with moderate decreasing for pattern recognition. Application to digit image recognition

Abstract: Abstract

Cited by 37 publications

References 7 publications

Evolutionary strategies for multi-scale radial basis function kernels in support vector machines

Evolutionary strategies for multi-scale radial basis function kernels in support vector machines

A penalty function method for designing efficient robust classifiers with input space optimal separating surfaces

Optimization of SVM Multiclass by Particle Swarm (PSO-SVM)

Contact Info

Product

Resources

About