Advertisement

Intelligent Identification of Dangerous Situations Based on Fuzzy Classifiers

  • Aleksandra Maksimova
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 287)

Abstract

This paper deals with a method of dangerous situations identification based on fuzzy classifiers composition. In this article a formal hierarchical model of the situation presentation is offered. The security problem in a bank is given as an example. Dangerous situations can be recognized by analysis of pictures from security cameras. This applied problem is reduced to the problem of pattern recognition that can be efficiently solved by fuzzy classifiers. It is suggested to use conception of fuzzy portraits of pattern classes for creating inference rules. The scheme of fuzzy classifiers connection that allows to estimate information from security cameras is presented. The advantage of such method is the possibility of linguistic interpretation of results. The prototype of intelligent information systems for identification of dangerous situations is developed on the basis of suggested approach.

Keywords

pattern recognition fuzzy classifier fuzzy inference data analysis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ishibuchi, H., Nakashima, T., Nii, M.: Classification and modeling with linguistic information granules: Advanced approaches to linguistic data mining. Springer, Heidelberg (2004)Google Scholar
  2. 2.
    Bezdek, J.C., Keller, J.M., Krishnapuram, R., Pal, N.R.: Fuzzy Models and Algorithms for Pattern Recognition and Image Processing. Springer, New York (2005)Google Scholar
  3. 3.
    Zhuravlev, Y.I.: An algebraic approach to the solution of pattern recognition and identification problems. Probl. Kibernet. 33 (1978) (in Russian)Google Scholar
  4. 4.
    Konor, A.: Computational Intelligence: Principles, Techniques and Applications. Springer, Heidelberg (2005)Google Scholar
  5. 5.
    Żywicki, M., Matiolański, A., Orzechowski, T.M., Dziech, A.: Knife detection as a subset of object detection approach based on Haar cascades. In: Proceedings of 11th International Conference Pattern Recognition and Information Processing, Minsk, pp. 139–142 (2011)Google Scholar
  6. 6.
    Łukańko, T., Orzechowski, T.M., Dziech, A., Wassermann, J.: Testing fusion of LDA and PCA algorithms for face recognition with images preprocessed with Two-Dimensional Discrete Cosine Transform. In: Proceedings of the 15th WSEAS International Conference on Computers (2011)Google Scholar
  7. 7.
    Kozlovskii, V.A., Yu, A.: Maksimova Algorithm of Pattern Recognition with intra-class clustering. In: Proceedings of 11th International Conference Pattern Recognition and Information Processing, Minsk, pp. 54–57 (2011)Google Scholar
  8. 8.
    Kozlovskii, V.A., Maksimova, A.Y.: Solution of pattern recognition problem using fuzzy portraits of classes. Artificial Intelligence 4, 221–228 (2010) (in Russian)Google Scholar
  9. 9.
    Kozlovskii, V.A., Maksimova, A.Y.: Fuzzy system of pattern recognition for liquid petrochemical products classification. The Scientific Works of the DNTU: Series Informatics, Cybernetics and Computer Engineering 13(185), 200–205 (2011) (in Russian)Google Scholar
  10. 10.
    Kozlovskii, V.A., Maksimova, A.Y.: Pattern Recognition Algorithm based on fuzzy approach. Artifical Intelligentce 4, 594–599 (2008) (in Russian)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Aleksandra Maksimova
    • 1
  1. 1.Institute of Applied Mathematics and MechanicsNational Academy of Science of UkraineDonetskUkraine

Personalised recommendations