Research of a New SVM Kernel Function

Juan Du; Wen Long Zhang; Meng Meng Xie

doi:10.4028/www.scientific.net/AMM.543-547.1659

Paper Titles

Research on the Classification Based on Naïve Bayes
p.1643

A New Hybridization Method Using in NEAT
p.1647

An Classifying Approach Based on Fuzzy Cognitive Maps
p.1651

Comparative Analysis on Kernel Based Probability Density Estimation
p.1655

Research of a New SVM Kernel Function
p.1659

Ant Colony Optimization Applied to the Three Gorges Ship Lock Arrangement Optimization
p.1663

An Efficient SPH Approach for Nearly Incompressible Fluid Simulation
p.1667

The Early Warning and Algorithm Implementation of Urban Road Submergence in Heavy Rains
p.1671

Illumination Uniformity Research Based on Quasi-Sine Particle Swarm Optimization
p.1677

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 543-547Research of a New SVM Kernel Function

Research of a New SVM Kernel Function

Abstract:

The kernel was the key technology of SVM; the kernel affected the learning ability and generalization ability of support vector machine. Aiming at the specific application of harmful text information recognition, combining traditional kernel function the paper structured a new combination kernel, modeling for the independent harmful vocabulary and co-occur vocabularies, and then evaluation the linear kernel, homogeneous polynomial kernel, non homogeneous polynomial kernel and combination kernel function in the sample experiment. The experimental results of combination kernel function showed that the effect has increased greatly than other kernel functions for the application of harmful text information filtering. Especially the Rcall value achieved satisfactory results.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 543-547)

Pages:

1659-1662

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.543-547.1659

Citation:

Cite this paper

Online since:

March 2014

Authors:

Juan Du*, Wen Long Zhang, Meng Meng Xie

Keywords:

Combination Kernel, Combination Semantic Information, Harmful Text Filtering, SVM

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Vapnik V N. An overview of statistical learning theory [J]. IEEE Transactions on Neural Networks, 1999, 10(5)：988-999.

DOI: 10.1109/72.788640

Google Scholar

[2] Li Zhi-feng. Using support vector machines to enhance the perfor－mance [J]. IEEE Transactions on Infor－mation Forensics and Security, 2007, 2(2)：174-180.

Google Scholar

[3] ZHANG G, LIU T, QIN B. Conent security oriented filtering system[A]. Proceedings of JSCL 2001[C]. (2001).

Google Scholar

[4] MIN J, HUANG X J. Text filtering system based on topic and sentiment classification[J]. Computer Engineering, 2007, 33(2): 163-164.

Google Scholar

[5] AMARI S, WU S. Improving support vector machine classifiers by modifying kernel functions[J]. Neural Networks, 1999, 12: 783-789.

DOI: 10.1016/s0893-6080(99)00032-5

Google Scholar

[6] Chen Rung-Ching, Hsieh Chia-Fen, Huang Yung-Fa. An isolation intrusion detection system for hierarchical wireless sensor networks [J]. Journal of Networks. 2010(5). 335-3420.

DOI: 10.4304/jnw.5.3.335-342

Google Scholar

[7] GAO Zhijun, LI Yi, YAO Ping, et al. Mining model of color ring customers based on fuzzy rough set and SVM[J]. Computer Engineering and Applications, 2013, 49(4): 125-128.

Google Scholar