Advertisement

The Journal of Supercomputing

, Volume 63, Issue 3, pp 800–815 | Cite as

Learning cellular automata rules for binary classification problem

  • Anna Piwonska
  • Franciszek Seredynski
  • Miroslaw Szaban
Article

Abstract

This paper proposes a cellular automata-based solution of a binary classification problem. The proposed method is based on a two-dimensional, three-state cellular automaton (CA) with the von Neumann neighborhood. Since the number of possible CA rules (potential CA-based classifiers) is huge, searching efficient rules is conducted with use of a genetic algorithm (GA). Experiments show an excellent performance of discovered rules in solving the classification problem. The best found rules perform better than the heuristic CA rule designed by a human and also better than one of the most widely used statistical method: the k-nearest neighbors algorithm (k-NN). Experiments show that CAs rules can be successfully reused in the process of searching new rules.

Keywords

Cellular automata Binary classification problem Genetic algorithm 

Notes

Acknowledgements

This research was supported by the grant S/WI/2/2008 from Bialystok University of Technology.

References

  1. 1.
    Bailey T, Jain A (1978) A note on distance-weighted k-nearest neighbor rules. IEEE Trans Syst Man Cybern 8(4):311–313 zbMATHCrossRefGoogle Scholar
  2. 2.
    Breukelaar R, Back T (2004) Evolving transition rules for multi dimensional cellular automata. In: Lecture notes in computer science, vol 3305. Springer, Berlin, pp 182–191 Google Scholar
  3. 3.
    Das R, Crutchfield J, Mitchell M (1995) Evolving globally synchronized cellular automata. In: Proceedings of the 6th international conference on genetic algorithms, pp 336–343 Google Scholar
  4. 4.
    Fawcett T (2008) Data mining with cellular automata. ACM SIGKDD Explor Newsl 10(1):32–39 CrossRefGoogle Scholar
  5. 5.
    Gacs P, Kurdyumov G, Levin L (1978) One dimensional uniform arrays that wash out finite islands. Probl Pereda Inf 12:92–98 Google Scholar
  6. 6.
    Ishibuchi H, Nozaki K, Yamamoto N (1993) Selecting fuzzy rules by genetic algorithm for classification problems. Fuzzy Sets Syst 2:1119–1124 Google Scholar
  7. 7.
    Maji P, Sikdar B, Chaudhuri P (2004) Cellular automata evolution for pattern classification. In: Lecture notes in computer science, vol 3305. Springer, Berlin, pp 660–669 Google Scholar
  8. 8.
    Mitchell M, Hraber P, Crutchfield J (1993) Revisiting the edge of chaos: evolving cellular automata to perform computations. Complex Syst 7:89–130 zbMATHGoogle Scholar
  9. 9.
    Oliveira C Jr., de Oliveira P (2008) An approach to searching for two-dimensional cellular automata for recognition of handwritten digits. In: Lecture notes in artificial intelligence, vol 5317. Springer, Berlin, pp 462–471 Google Scholar
  10. 10.
    Omohundro S (1984) Modelling cellular automata with partial differential equations. Physica 10D, 10(1–2):128–134 MathSciNetGoogle Scholar
  11. 11.
    Piwonska A, Seredynski F (2010) Learning cellular automata rules for pattern reconstruction task. In: Lecture notes in computer science, vol 6457. Springer, Berlin, pp 240–249 Google Scholar
  12. 12.
    Povalej P, Lenic M, Kokol P (2004) Improving ensembles with classificational cellular automata. In: Lecture notes in computer science, vol 3305. Springer, Berlin, pp 242–249 Google Scholar
  13. 13.
    Sipper M (1997) The evolution of parallel cellular machines toward evolware. Biosystems 42(1):29–43 CrossRefGoogle Scholar
  14. 14.
    Wolfram S (2002) A new kind of science. Wolfram Media, Champain zbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  • Anna Piwonska
    • 1
  • Franciszek Seredynski
    • 2
  • Miroslaw Szaban
    • 3
  1. 1.Computer Science FacultyBialystok University of TechnologyBialystokPoland
  2. 2.Poland and Polish-Japanese Institute of Information TechnologyCardinal Stefan Wyszynski UniversityWarsawPoland
  3. 3.Institute of Computer ScienceUniversity of Natural Sciences and HumanitiesSiedlcePoland

Personalised recommendations