Classifier Selection Based on Support Vector Technique

  • Dajin Gao
  • Xiang-Sheng Rong
  • Xiang-Yang You
  • Ming Xu
  • Fujiang Huo
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 209)

Abstract

This paper presents an ensemble approach consisting of global SVM and local SVM. Global SVM is estimated according to its decision confidence. Local SVM handles the query whose global decision is of low confidence. Local SVM is constructed over query’s neighborhood, which is developed under the guidance of an informative metric. And its training is based on a query-based objective function. Global SVM helps to define the new metric. Some heuristics proposed to specify neighborhood size and hyper parameters. We present experimental evidence of classification performance improved by our schema over state of the arts on real datasets.

Keywords

Local classifier Global classifier Support vector technique New metric 

References

  1. 1.
    Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines, vol 10. Cambridge University Press, London, pp 381–388Google Scholar
  2. 2.
    Richard MD, Lippmann RP (1991) Neural network classifiers estimate bayesian a posteriori probabilities. Neural Comput 1(3):461–483CrossRefGoogle Scholar
  3. 3.
    Craven M, DiPasquo D, Freitag D (1998) Learning to extract symbolic knowledge from the World Wide Web. In: Proceedings of 15th national conference on artificial intelligence, 8:880–886Google Scholar
  4. 4.
    Milgram J, Mohamed CSR (2005) Estimating accurate multi-class probabilities with support vector machines. In: Proceedings of IEEE international joint conference on neural networks, 3:1906–1911Google Scholar
  5. 5.
    Kwork TJ (1999) Moderate the outputs of support vector machine classifiers. IEEE Trans Neural Networks 10:1018–1032CrossRefGoogle Scholar
  6. 6.
    Friedman JH (1994) Flexible metric nearest neighbor classification. In: Technical report, department of statistics, vol 6. Stanford University, pp 95–104Google Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • Dajin Gao
    • 1
  • Xiang-Sheng Rong
    • 1
  • Xiang-Yang You
    • 1
  • Ming Xu
    • 2
  • Fujiang Huo
    • 2
  1. 1.Training DepartmentXuzhou Air Force College of P. L. AXuzhouChina
  2. 2.Department of Logistic CommandXuzhou Air Force College of P. L. AXuzhouChina

Personalised recommendations