A Novel Sparse Weighted Least Squares Support Vector Classifier

Bo Yang; Liang Zhang

doi:10.4028/www.scientific.net/AMR.842.746

Paper Titles

The Flooding Tolerance and Growth Characteristics of 2 Woody Species by Flooding Durations for Aquatic Ecosystem Restoration
p.729

Comparative and Study the Influence of Sand Depth for Liquefied Evaluation
p.733

Investigation of Silicone Oil Leaching in PDMS Fouling Release Coating by Confocal Laser Scanning Microscope
p.737

Research on Surface Roughness Measurement of ACSR Using Light-Section Microscope
p.742

A Novel Sparse Weighted Least Squares Support Vector Classifier
p.746

Inverse Generalized Harmonic Numbers with Riordan Arrays
p.750

Empirical Research on Business Intelligence Success
p.754

Exploring the Effect of Organizational Dynamic Capability on Data Quality-BI Success Relationship
p.759

Solving the Lower Reliability Confidence Limit of Binomial Distribution by Using Numeric Iteration Method
p.764

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 842A Novel Sparse Weighted Least Squares Support...

A Novel Sparse Weighted Least Squares Support Vector Classifier

Abstract:

A novel sparse weighted LSSVM classifier is proposed in this paper, which is based on Suykens weighted LSSVM. Unlike Suykens weighted LSSVM, the proposed weighted method is more suitable for classification. The distance between sample and classification border is used as the sample importance measure in our weighted method. Based on this importance measure, a new weight calculating function, using which can adjust the sparseness of weight, is designed. In order to solve the imbalance problem, a kind of normalization weights calculating method is proposed. Finally, the proposed method is used on digit recognition. Comparative experiment results show that the proposed sparse weighted LSSVM can improve the recognition correct rate effectively.

You might also be interested in these eBooks

Materials, Mechanical and Manufacturing Engineering

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 842)

Pages:

746-749

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.842.746

Citation:

Cite this paper

Online since:

November 2013

Authors:

Bo Yang*, Liang Zhang

Keywords:

Least Squares Support Vector Machine (LSSVM), Sparse Weighted LSSVM, Weighted LSSVM

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] V. Vapnik. The nature of statistical learning theory. John Wiley, New-York, (1998).

Google Scholar

[2] J. A. K. Suykens, J. Vandewalle. Least square support vector machine classifier. Neural Processing Letters. Vol. 9(1999), pp.293-300.

Google Scholar

[3] J. A. K. Suykens, etc. Optimal control by least squares support vector machines. Neural Networks. Vol. 14(2001), pp.23-35.

DOI: 10.1016/s0893-6080(00)00077-0

Google Scholar

[4] R.O. Duda, P.E. Hart, etc. Pattern Classification. Wiley-Interscience, New-York, (2000).

Google Scholar

[5] J. A. K. Suykens, etc. Weighted Least Squares Support Vector Machines: robustness and sparse approximation. Neurocomputing. Vol. 48(2002), pp.85-105.

DOI: 10.1016/s0925-2312(01)00644-0

Google Scholar