Minimum Within-Class and Maximum Between-Class Scatter Support Vector Machine

Zhong Bao Liu; Shi Tong Wang

doi:10.4028/www.scientific.net/AMM.58-60.79

Paper Titles

A Robust Spectrum Sensing Method Using Filter Bank
p.54

Technological Competency and New Product Development Performance: The Moderating Role of Environmental Turbulence
p.60

An Investigation of Innovation Capability in Small and Medium-Sized Enterprises of China
p.66

Study on the Topology Structure and Evolvement Analysis of Nonlinear Model under Superharmonic Resonance
p.73

Minimum Within-Class and Maximum Between-Class Scatter Support Vector Machine
p.79

Effectual Geometrical Lightweight for Large Mechanical Assemblies
p.85

Simply Research on Enterprises’ Product Development in Innovative Value Chain
p.91

Scheme Design of Glass-Stacker Machinery Based on Module Design Method
p.97

Research on Business Intelligence-Based Supply Chain Management
p.103

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 58-60Minimum Within-Class and Maximum Between-Class...

Minimum Within-Class and Maximum Between-Class Scatter Support Vector Machine

Abstract:

Classification is one of most important tasks in pattern recognition. Support vector machine (SVM) and its improved algorithms are quite important to classification. Although these approaches perform well in practice, they can’t take within-class and between-class scatter into consideration. Inspired from the Fisher’s discriminant ratio in linear discriminant analysis (LDA), a minimum within-class and maximum between-class scatter support vector machine (MMSVM) is proposed. MMSVM has the advantages of SVM and LDA and reflects distributions of classes, therefore, classification accuracy is improved in most cases. Experiments on many datasets verify the effectiveness of the proposed algorithm.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 58-60)

Pages:

79-84

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.58-60.79

Citation:

Cite this paper

Online since:

June 2011

Authors:

Zhong Bao Liu, Shi Tong Wang

Keywords:

Between-Class Scatter, Classification, Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Within-Class Scatter

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Vapnik V. The nature of statistical learning theory [M]. New York: Springer-Verlag, (1995).

Google Scholar

[2] Mahesh Pal and Giles M. Foody. Feature selection for classification of hyper spectral data by SVM [J]. IEEE Trans. on Geoscience and Remote Sensing, 2010, 48 (5): 2297-2307.

DOI: 10.1109/tgrs.2009.2039484

Google Scholar

[3] Scholkopf B, Smola A, Bartlet P. New support vector algorithms [J]. Neural Computation, 2000, 12: 1207-1245.

Google Scholar

[4] Scholkopf B, Platt J, Shawe-Taylor J, et a1. Estimating the support of high-dimensional distribution [J]. Neural Computation, 2001, 13: 1443-1471.

DOI: 10.1162/089976601750264965

Google Scholar

[5] Tsang I W, Kwok J T and Cheung P M. Core vector machines: fast SVM training on very large data sets [J] Journal of Machine Learning Research, 2005, 6: 363-392.

Google Scholar

[6] Suykens J. A, Vandewalle J. Least squares support vector machines classifiers [J]. Neural Processing Letters, 1999, 19 (3): 293-300.

Google Scholar

[7] Mangasarian O, Musicant D. Lagrange support vector machines [J]. Journal of Machine Learning Research, 200l, 1: 161-177.

Google Scholar

[8] Lee Y J, Mangasarian O. SSVM: A smooth support vector machines [J]. Computationa Optimization and Applications, 2001, 20 (1): 5-22.

Google Scholar

[9] Belhumeur P N. Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19 (7): 711-720.

DOI: 10.1109/34.598228

Google Scholar

[10] Muller K. R., Mika S., et al. An introduction to kernel-based learning algorithms [J]. IEEE Trans. On Neural Networks, 2001, 12 (1): 181-201.

DOI: 10.1109/72.914517

Google Scholar