๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Robustified least squares support vector classification

โœ Scribed by Michiel Debruyne; Sven Serneels; Tim Verdonck

Publisher
John Wiley and Sons
Year
2009
Tongue
English
Weight
274 KB
Volume
23
Category
Article
ISSN
0886-9383

No coin nor oath required. For personal study only.

โœฆ Synopsis

Abstract

Support vector machine (SVM) algorithms are a popular class of techniques to perform classification. However, outliers in the data can result in bad global misclassification percentages. In this paper, we propose a method to identify such outliers in the SVM framework. A specific robust classification algorithm is proposed adjusting the least squares SVM (LSโ€SVM). This yields better classification performance for heavily tailed data and data containing outliers. Copyright ยฉ 2009 John Wiley & Sons, Ltd.

๐Ÿ“œ SIMILAR VOLUMES

Chaos control using least-squares suppor
Chaos control using least-squares support vector machines
โœ Suykens, J. A. K.; Vandewalle, J. ๐Ÿ“‚ Article ๐Ÿ“… 1999 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 118 KB

In this paper we apply a recently proposed technique of optimal control by support vector machines (SVMs) to chaos control. Vapnik's support vector method, which is based on the structural risk minimization principle and has been very successful in classi"cation and function estimation problems, is

Knowledge discovery in a direct marketin
Knowledge discovery in a direct marketing case using least squares support vector machines
โœ S. Viaene; B. Baesens; T. Van Gestel; J. A. K. Suykens; D. Van den Poel; J. Vant ๐Ÿ“‚ Article ๐Ÿ“… 2001 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 111 KB

We study the problem of repeat-purchase modeling in a direct marketing setting using Belgian data. More specifically, we investigate the detection and qualification of the most relevant explanatory variables for predicting purchase incidence. The analysis is based on a wrapped form of input selectio

Optimizing the tuning parameters of leas
Optimizing the tuning parameters of least squares support vector machines regression for NIR spectra
โœ T. Coen; W. Saeys; H. Ramon; J. De Baerdemaeker ๐Ÿ“‚ Article ๐Ÿ“… 2006 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 323 KB

## Abstract Partial least squares (PLS) is one of the most used tools in chemometrics. Other data analysis techniques such as artificial neural networks and least squares support vector machines (LSโ€SVMs) have however made their entry in the field of chemometrics. These techniques can also model no