DOI QR코드

DOI QR Code

Import Vector Voting Model for Multi-pattern Classification

다중 패턴 분류를 위한 Import Vector Voting 모델

  • 최준혁 (김포대학 컴퓨터계열) ;
  • 김대수 (한신대학교 컴퓨터학과) ;
  • 임기욱 (선문대학교 지식정보산업공학과)
  • Published : 2003.12.01

Abstract

In general, Support Vector Machine has a good performance in binary classification, but it has the limitation on multi-pattern classification. So, we proposed an Import Vector Voting model for two or more labels classification. This model applied kernel bagging strategy to Import Vector Machine by Zhu. The proposed model used a voting strategy which averaged optimal kernel function from many kernel functions. In experiments, not only binary but multi-pattern classification problems, our proposed Import Vector Voting model showed good performance for given machine learning data.

일반적으로 Support Vector Machine은 이진 분류 모형에 있어 우수한 성능을 보이지만 모델의 한계로 인하여 다중 패턴의 분류 문제에는 쉽게 적용하기가 어렵다. 본 논문에서는 이진 분류를 포함한 다중 레이블을 갖는 데이터의 정확한 패턴 분류를 위하여 Zhu가 제안한 Import Vector Machine에 커널 Bagging 전략을 적용하여 분류의 정확성을 향상시키기 위한 Import Vector Voting 모형을 제안한다. 이러한 Import Vector Voting 모형은 다수의 커널함수를 적용한 결과 중에서 가장 성능이 우수한 커널함수를 이용하여 최종 분류를 수행하기 위한 voting 전략으로 사용한다. 본 논문에서 제안하는 Import Vector Voting 모형은 이진 분류를 포함한 3개 이상의 다중 패턴 데이터에 대한 분류 문제에 있어 매우 정확한 분류 성능을 보임을 실험을 통해 입증한다.

Keywords

References

  1. T. Hastie, R. Tibshirani, Generalized Additive Models, Chapman and Hall, 1990.
  2. L. Breiman, "Bagging predictors," Mach. Learn. 24(2), 123-140, 1996.
  3. C. Burges, "A tutorial on support vector machines for pattern recognition," In Data Mining and Knowledge Discovery, 1998.
  4. A. C. Davison, D. V. Hinkley, "Bootstrap methods and their application," Cambridge University Press, 1998.
  5. T. Evgeniou, M. Pontil, T. Poggio, Regularization networks and support vector machines, MIT Press, 1999.
  6. P. Green, B. Yandell, "Semi-parametric generalized linear models," Proceedings of 2nd International GLIM Conference, 1985.
  7. T. Hastie, R. Tibshirani, J. Friedman, The elements of statistical learning, Springer, 2001.
  8. G. Kimeldorf, G. Wahba, Some results on Tchebycheffian spline functions, Math. Anal. Applic. 1971.
  9. X. Lin, G. Wahba, D. Xiang, F. Gao, R. Klein, B. Klein, "Smoothing spline ANOVA models for large data sets with Bernoulli observations and the randomized GACV", Technical Report 998, Department of Statistics, University of Wisconsin, Madison, 1998.
  10. B. D. Marx, P. H. C. Eilers, "Direct generalized additive modeling with penalized likelihood", Computational Statistics and Data Analysis 28(2), pp. 193-209, 1998. https://doi.org/10.1016/S0167-9473(98)00033-4
  11. A. Smola, B. Scholkopf, "Sparse Greedy Matrix Approximation for Machine Learning," In Proceedings of the Seventeenth International Conference on Machine Learning, 2000.
  12. G. Wahba, "Support Vector Machine, Reproducing Kernel Hilbert Spaces and the Randomized," GACV. Technical Report 984, Department of Statistics, University of Wisconsin, Madison, 1998.
  13. G. Wahba, C, Gu, Y. Wang, R. Chappell, Soft Classification, a.k.a. Risk Estimation, via Penalized Log Likelihood and Smoothing Spline Analysis of Variance, The Mathematics of Generalization, Santa Fe Institute Studies in the Sciences of Complexity, Addison-Wesley Publisher, 1995.
  14. C. Williams. M. Seeger, "Using the Nystrom Method to Speed Up Kernel Machines," Advances in Neural Information Processing Systems 13, MIT Press, 2001.
  15. J. Zhu, T. Hastie, "Kernel Logistic Regression and the Import Vector Machine," NIPS2001 Conference, 2001.
  16. http://www.ics.uci.edu/~mleam/MLRepository.html
  17. http://www.sas.com