Journal of Institute of Control, Robotics and Systems (제어로봇시스템학회논문지)

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Non-linear Data Classification Using Partial Least Square and Residual Compensator

부분 최소 자승법과 잔차 보상기를 이용한 비선형 데이터 분류

  • 김경훈 (울산대학교 전기전자정보시스템공학부) ;
  • 김태영 (알칸 대한 주식회사) ;
  • 최원호 (울산대학교 전기전자정보시스템공학부)
  • Published : 2004.02.01
Download PDF
⟨ Previous Next ⟩

Abstract

Partial least squares(PLS) is one of multiplicate statistical process methods and has been developed in various algorithms with the characteristics of principal component analysis, dimensionality reduction, and analysis of the relationship between input variables and output variables. But it has been limited somewhat by their dependency on linear mathematics. The algorithm is proposed to classify for the non-linear data using PLS and the residual compensator(RC) based on radial basis function network (RBFN). It compensates for the error of the non-linear data using the RC based on RBFN. The experimental result is given to verify its efficiency compared with those of previous works.

Keywords

References

  1. P. Geladi and B. R. Kowalski. 'Partial least-squares re-gression: a tutorial', Anal. Chim. Acta., vol. 195, pp. 1-17, 1986 https://doi.org/10.1016/S0003-2670(00)85646-9
  2. W. Xun, U. Kruger, B. Lennox, and P. Goulding, 'A novel multiblock method using latent vciable partial least squares', Proc. Conf. on American Control, vol. 4, pp. 3136-3141, 2001
  3. U. Kruger, X. Wang, Q. Chen, and S. J. Qin, 'An alternative PLS algorithm for the monitoring of industrial process', Proc. Conf. on American Control, vol. 6, pp. 4455-4459, 2001 https://doi.org/10.1109/ACC.2001.945680
  4. M. J. Huang, H. Ye, and G. Z. Wang 'A new PLS approach with hybrid internal models', Proc. Int. Conf. on Machine Learning and Cybernetics, vol. I, pp. 161-164, 2002 https://doi.org/10.1109/ICMLC.2002.1176730
  5. Y. S. Kim, B. J. Yum, and M. Kim 'A hybrid model of partial least squares and artificial neural network for analyzing process monitoring data', Proc. Int. Joint Conf. on Neural Networks, vol. 3, pp. 2292-2297, 2001 https://doi.org/10.1109/IJCNN.2001.938524
  6. D. J. H. Wilson and G. W Irwin, 'PLS modeling and fault detection on the Tennessee Eastman benchmark', Proc. Conf. on American Control, vol. 6, pp. 3975-3979, 1999 https://doi.org/10.1109/ACC.1999.786264
  7. D. J. H. Wilson, G. W Irwin, and G. Lightbody, 'Nonlinear PLS modelling using radial basis functions',Proc. Conf. on American Control, vol. 5, pp. 3275-3276, 1997 https://doi.org/10.1109/ACC.1997.612069
  8. J. A. Leonard and MA Kramer, 'Radial basis function networks for classifying process faults', IEEE Control Systems Magazine, vol. 11, pp.31-38. 1991 https://doi.org/10.1109/37.75576
  9. Y. Li and J.-M. Deng, 'WAV-a weight adaptation algorithm for normalized radial basis function networks', Proc. IEEE Int. Conf. on Electronics, Circuits and Systems, vol. 2, pp. 177-120, 1998 https://doi.org/10.1109/ICECS.1998.814845
  10. F. Heimes and B. Heuveln, 'The normalized radial basis function neural network', Proc. IEEE Int. Conf. On Systems, Man, and Cybernetics, vol. 2, pp. 1609-1614, 1998 https://doi.org/10.1109/ICSMC.1998.728118
  11. M. D. Brown, GW. Irwin, and G. Lightbody, 'Local model networks for nonlinear internal model control', EURACO workshop on Robust and Adaptive Control of Integrated systems, Munich, Germany, 1996
  12. R. A. Fisher, 'The use of multiple measurements in taxonomic problems,' Annals of Eugenics, vol. 7, pp. 179-188, 1936 https://doi.org/10.1111/j.1469-1809.1936.tb02137.x
  13. http://www.ics.uci.edu/-mleam/MLRepositoly.html
  14. P. Lutzt, 'Probenl-a set of neural network benchmark problems and benchmarking rules', Tech. Rep. 21/94, Fakultat fur Informatik, Universitat Karlsruhe, 1994. http://ftp.ira.uka.de/pub/papers/techreports/1994/1994-21.ps.Z