Reseach on Feature Selection Algorithm Based on the Margin of Support Vector Machine

Lin Fang Hu; Lei Qiao; Min De Huang

doi:10.4028/www.scientific.net/AMM.333-335.1430

Paper Titles

An Improved Heuristic Algorithm for a Hybrid Flow-Shop Scheduling
p.1414

A Modified Fuzzy C-Mean Algorithm for Automatic Clustering Number
p.1418

Using Hybrid Fuzzy Neural Network to Improve the Accuracy of Air Traffic Flow Forecasts
p.1422

Swarm Automated Planning Algorithm with Repairing Operators
p.1426

Reseach on Feature Selection Algorithm Based on the Margin of Support Vector Machine
p.1430

A Fast and Robust Adaptive Blind Equalization Algorithm in High Speed Satellite Channel
p.1435

A Solution to Best Itinerary Problem Based on Strategy Set under Dijkstra Algorithm
p.1442

Automatic Well Selection Method for Acid-Fracturing in Kazakhstan R Oilfield Carbonate Reservoir
p.1446

On the Adjacent Vertex Distinguishing Proper Edge Colorings of Several Classes of Complete 5-Partite Graphs
p.1452

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 333-335Reseach on Feature Selection Algorithm Based on...

Reseach on Feature Selection Algorithm Based on the Margin of Support Vector Machine

Abstract:

A feature selection algorithm based on the optimal hyperplane of SVM is raised. Using the algorithm, the contribution to the classification of each feature in the candidate feature set is test, and then the feature subset with best classification ability will be selected. The algorithm is used in the recognition process of storm monomers in weather forecast, and experimental data show that the classification ability of the features can be effectively evaluated; the optimal feature subset is selected to enhance the working performance of the classifier.

You might also be interested in these eBooks

Measurement Technology and Engineering Researches in Industry

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 333-335)

Pages:

1430-1434

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.333-335.1430

Citation:

Cite this paper

Online since:

July 2013

Authors:

Lin Fang Hu, Lei Qiao, Min De Huang

Keywords:

Feature Selection, Optimal Hyperplane, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] SunZ. H, BebisZ. H, et al. Object detection using feature subset selection. Pattern recognition. 2004. 37(2165-2176).

DOI: 10.1016/j.patcog.2004.03.013

Google Scholar

[2] (Jain A. ，Duin R. ，et al. Statistical Pattern Recognition: a review. IEEE Transaction on Pattern Analysis and Machine Intelligence . 2000. 22(1): 4-37.

DOI: 10.1109/34.824819

Google Scholar

[3] Zhou X. ，wang X. ，et al. A Bayesian approach to nonlinear profit gene selection and classification. Journal of Franklin institute . 2004. 341: 137-156.

DOI: 10.1016/j.jfranklin.2003.12.010

Google Scholar

[4] Zhou X. ，Wang X. ，et al. Nonlinear-profit gene classification using mutual-information and wavelet-based feature selection. Journal of biological systems. 2004. 12(3): 371-386.

DOI: 10.1142/s0218339004001178

Google Scholar

[5] Furey T.S. ，Cristianini N. ，et al. Support vector machine classification and validation of cancer tissue samples using micro array expression data. " Bioinformatics . 2000. 16(10): 906-914.

DOI: 10.1093/bioinformatics/16.10.906

Google Scholar

[6] Michael M. and Lin W.C. Experimental study information measure and inter-intra class distance ration on feature selection and orderings. IEEE transaction on system，man and cybernetics. 1973. 3(2): 172-181.

DOI: 10.1109/tsmc.1973.5408500

Google Scholar

[7] Sindhwani V. ，Rakshit S. ，et al Feature selection in MLPs and SVMs based on maximum output information. IEEE transaction on neural networks. 2004. 15(4): 937-948.

DOI: 10.1109/tnn.2004.828772

Google Scholar

[8] Haering N. and Lobo N.D.V. Feature and classification method to locate deciduous in images. Computer vision image understanding. 1999. 75(1-2): (133-149.

DOI: 10.1006/cviu.1999.0769

Google Scholar