Development of Fuzzy Learning Vector Quantization Neural Network for Artificial Odor Discrimination System

  • B. Kusumoputro
Conference paper


The author had developed an artificial odor discrimination system for mimicking a function of human odor experts. The system used a back-propagation neural network and shows high recognition capability, however, the system work efficiently if it is used to discriminate a limited number of odors. The back-propagation learning algorithm will force the unlearned odor to the one of the already learned class-category. To improve the system’s capability, a fuzzy learning vector quantization (FLVQ) neural network is developed, in which LVQ neural network will be used together with fuzzy theory. In the experiments on four different ethanol concentrations and three different kinds of fragrance odor from Martha Tilaar Cosmetics, it is found that the FLVQ shows high recognition capability, comparable with the back propagation neural network, however, the FLVQ can cluster the unlearned sample to different class of odor.


Vector Quantization Back Propagation Neural Network Reference Vector Learning Vector Quantization Recognition Probability 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    B. Kusumoputro and M. Rivai, ‘Discrimination of fragrance odor by arrayed quartz resonator and a neural network’, ICCIMA-98, H. Selvaraj and B. Verma (Eds), Singapore: Word Scientific, pp. 264–270, 1998.Google Scholar
  2. [2]
    L. A. Zadeh, ‘Similarity relations and fuzzy ordering’, Information Sciences, 3, pp. 177–200, 1971.MathSciNetMATHCrossRefGoogle Scholar
  3. [3]
    L. T. Koczy, ‘Fuzzy if then rule models and their transformation into one another’, IEEE Trans. Syst.Man, Cybern., vol. 26, 5, pp.621–637, 1996.CrossRefGoogle Scholar
  4. [4]
    T. Kohonen, G. Barna and R. Chrisley, ‘Statistical pattern recognition with neural networks: Benchmarking studies’, IEEE Proc. of ICNN, pp.61–68, 1987.Google Scholar
  5. [5]
    T. Kohonen, ‘Improved versions of learning vector quantization’, IEEE Proc. of IJCNN, I, pp. 545–550, 1990.Google Scholar
  6. [6]
    N. R. Pal, J. C. Bezdek and E. Tsao, ‘Generalized clustering networks and Kohonen’s self-organizing sheme’, IEEE Trans. Neural Networks, vol. 4, 4, pp. 549–558, 1993.CrossRefGoogle Scholar
  7. [7]
    J. C. Bezdek and N. R. Pal, ‘Two soft relatives of learning vector quantization’, Neural Networks, vol. 8, no. 5, pp. 729–743, 1995.CrossRefGoogle Scholar
  8. [8]
    Y. Sakuraba, T. Nakamoto and T. Moriizumi, ‘New method of learning vector quantization’, Systems and Computers in Japan, vol. 22, 13, pp.93–102, 1991.CrossRefGoogle Scholar
  9. [9]
    G. Sauerbrey, ‘Vermendung von schwingquaren zur wagung dunner schichten und zur wagung’, Z.Phys., 155, pp. 206–209, 1959.CrossRefGoogle Scholar
  10. [10]
    W.H. King, ‘Piezoelectric Sorption detector’, Anal. Chem., pp. 206–222, 1964.Google Scholar
  11. [11]
    D.E. Rumelhart, J.L. Mc.Cleland, and The PDP Research Group, Parallel Distributed Processing, MIT Press, 1996Google Scholar

Copyright information

© Springer-Verlag Wien 1999

Authors and Affiliations

  • B. Kusumoputro
    • 1
  1. 1.Faculty of Computer ScienceUniversity of Indonesia Depok CampusJakartaIndonesia

Personalised recommendations