Variable Selection for Support Vector Machines

Bierman, Surette; Steel, S. J.

doi:10.1080/03610910903072391

Cited by 11 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among all these modeling methods, SVM is gaining popularity in a wide variety of the metabolomics study due to its prediction performance. However, many researchers have pointed out that SVM also suffered from the problem of feature subset selection [16][17][18]. Typically, redundant feature may destroy the patterns contained in the metabolomics data.…”

Section: Introductionmentioning

confidence: 99%

Weighted variable kernel support vector machine classifier for metabolomics data analysis

Huang

Yun

et al. 2015

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Weighted variable kernel support vector machine classifier for metabolomics data analysis

Huang

Yun

et al. 2015

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

“…How to effectively extract the patterns and improve the prediction ability appear to be still very necessary in SAR studies. To date, several SAR modeling approaches have been reported to describe and construct the relationship, including multivariate linear regression, principal component analysis, partial least squares discriminant analysis (PLSDA), classification and regression tree (CART), and recently support vector machines [7][8][9][10][11][12][13][14][15]34,35], and so on.…”

Section: Introductionmentioning

confidence: 99%

A novel tree kernel partial least squares for modeling the structure–activity relationship

Huang¹,

Cao

et al. 2013

Journal of Chemometrics

View full text Add to dashboard Cite

Kernel partial least squares (KPLS) has become a popular technique for regression and classification of complex data sets, which is a nonlinear extension of linear PLS in which training samples are transformed into a feature space via a nonlinear mapping. The PLS algorithm can then be carried out in the feature space. In the present study, we attempt to develop a novel tree KPLS (TKPLS) classification algorithm by constructing an informative kernel on the basis of decision tree ensembles. The constructed tree kernel can effectively discover the similarities of samples and select informative features by variable importance ranking in the process of building the kernel. Simultaneously, TKPLS can also handle nonlinear relationships in the structure–activity relationship data by such a kernel. Finally, three data sets related to different categorical bioactivities of compounds are used to evaluate the performance of TKPLS. The results show that the TKPLS algorithm can be regarded as an alternative and promising classification technique. Copyright © 2013 John Wiley & Sons, Ltd.

show abstract

“…Accuracy of classifiers can be substantially improved if a smaller subset of variables is used [2]. It can be done by using a procedure called feature selection which can be viewed as a process of determining what inputs should be presented to a classification algorithm.…”

Section: Introductionmentioning

confidence: 99%

An Ensemble-Based Feature Selection Algorithm Using Combination of Support Vector Machine and Filter Methods for Solving Classification Problems

Utkin¹,

Zhuk²,

Chekh³

2013

European Journal of Technology and Design

View full text Add to dashboard Cite

A new feature selection algorithm for solving classification problems is proposed. The algorithm exploits the ensemble-based methodology and iteratively combines classifiers in order to assign weights to features characterizing their importance in classification. The algorithm is based on the joint use of a filter method and the well known support vector machine. Moreover, the filter method uses only support vectors instead of the total training set to calculate the feature weights. Numerical experiments with publicly available data sets show that the proposed algorithm improves the classification accuracy.

show abstract

Variable Selection for Support Vector Machines

Cited by 11 publications

References 14 publications

Weighted variable kernel support vector machine classifier for metabolomics data analysis

Weighted variable kernel support vector machine classifier for metabolomics data analysis

A novel tree kernel partial least squares for modeling the structure–activity relationship

An Ensemble-Based Feature Selection Algorithm Using Combination of Support Vector Machine and Filter Methods for Solving Classification Problems

Contact Info

Product

Resources

About