An Improved SVM Based on Feature Extension and Feature Selection

Wei Feng Yao; Xiao Bao Jia

doi:10.4028/www.scientific.net/AMM.552.128

Paper Titles

The Overview of the Development of Wind Energy
p.107

An Overview of Active Power Filter
p.111

Technological Progress in the Material Research & Development for Gen-IV SCWR Advanced Reactors
p.115

Research Effect of Four-Quadrant Detector Detection Spot in Atmospheric Turbulence
p.123

An Improved SVM Based on Feature Extension and Feature Selection
p.128

A Review of Residual Life Prediction for Remanufacturing of Machine Tool
p.133

Development and Application of Composite Submarine Cable Online Monitoring System
p.139

Monitoring Corrosion Fatigue Damage Process of LY12CZ Aluminum Alloy with and without Coating by Acoustic Emission
p.145

The Method of On-Line Detection of Antiicing Additive Concentration in Jet Fuel
p.149

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 552An Improved SVM Based on Feature Extension and...

An Improved SVM Based on Feature Extension and Feature Selection

Abstract:

Support Vector Machine (SVM) implicitly maps samples from the lower-dimensional feature space to a higher-dimensional space, and designs a non-linear classifier via optimize the linear classifier in the higher-dimensional space. This paper proposed an improved SVM method based on feature extension and feature selection. The method explicitly maps the samples to a higher-dimensional feature space, perform the feature selection in the space, and finally design a linear classifier with a selected feature set. This paper illustrated the reason why the generalization ability is improved by this technique. The experiment results on benchmark datasets show that the improved SVM greatly decreases the error rate compared with other classifiers, which proves the feasibility of the proposed SVM.

You might also be interested in these eBooks

Process Equipment, Mechatronics Engineering and Material Science II

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 552)

Pages:

128-132

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.552.128

Citation:

Cite this paper

Online since:

June 2014

Authors:

Wei Feng Yao*, Xiao Bao Jia

Keywords:

Feature Extension, Feature Selection, Feature Space, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions:

Request Permissions

* - Corresponding Author

References

[1] Vapnik V forward . The nature of statistical learning theory . In translation, Zhang workers translated . Beijing : Tsinghua University Press, 2000.

Google Scholar

[2] Guyon I, Weston J, Barnhill S, et al. Gene Selection for Cancer Classifier using Support Vector Machines. Machine Learning, 2002, 46 (1), 389-422.

Google Scholar

[3] Müller KR, Mika S, Rätsch G, et al. An Introduction to Kernel-Based Learning Algorithms. IEEE Trans. Neural Networks, 2001, 12 (2): 181-201.

Google Scholar

[4] Xu Jianhua , Zhang workers , Li Yanda . Kernel -based nonlinear perception algorithm . Computer Engineering , July (2002).

Google Scholar

[5] Xu Jianhua , Zhang workers . Classical linear algorithm for nonlinear kernel form . Control and Decision, 2006 01.

Google Scholar

[6] University of California Irvine. UCI Repository of Machine Learning Databases. Internet: http: /www. ics. uci. edu/ ~ mlearn / MLRepository. html.

Google Scholar

[7] GMD FIRST, IDA benchmark repository used in several Boosting, KFD and SVM papers. Internet: http: /ida. first. gmd. de/ ~ raetsch / data / benchmarks. htm.

Google Scholar

[8] Rätsch G., Onoda T and Müller KR, Soft Margins for AdaBoost, Machine Learning, vol. 42, 287-320, March (2004).

Google Scholar

[9] ZHOU Yong-quan , Zhao Bin . Nonlinear weighting function of a linear perceptron learning algorithm fast , Computer Applications and Software , 2004 01.

Google Scholar