Advertisement

CT-EXT: An Algorithm for Computing Typical Testor Set

  • Guillermo Sanchez-Díaz
  • Manuel Lazo-Cortés
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4756)

Abstract

Typical testors are a useful tool for feature selection and for determining feature relevance in supervised classification problems, especially when quantitative and qualitative features are mixed. Nowadays, computing all typical testors is a highly costly procedure; all described algorithms have exponential complexity. Existing algorithms are not acceptable methods owing to several problems (particularly run time) which are dependent on matrix size. Because of this, different approaches, such as sequential algorithms, parallel processing, genetic algorithms, heuristics and others have been developed. This paper describes a novel external type algorithm that improves the run time of all other reported algorithms. We analyze the behaviour of the algorithm in some experiments, whose results are presented here.

Keywords

feature selection pattern recognition typical testors 

References

  1. 1.
    Aguila Feroz, L., Ruiz Shulcloper, J.: Algorithm CC for the elaboration of k-valued information on pattern recognition problems. Cuba 5(3), 89–101 (1984) (In Spanish)Google Scholar
  2. 2.
    Ayaquica Martinez, I.Y., Jimenez Jacinto, V.: A new external type algorithm for the calculation of tipical testors. In: Proc. TIARP 1997, pp. 141–148 (1997) (In Spanish)Google Scholar
  3. 3.
    Bravo, A.: Algorithm CT for calculating the typical testors of k-valued matrix. Revista Ciencias Matematicas, Cuba 4(2), 123–144 (1983)MathSciNetGoogle Scholar
  4. 4.
    Dmitriev, A.N., Zhuravlev, Y.I., Krendeliev, F.: About mathematical principles and phenomena classification. Diskretni Analiz 7, 3–15 (1966)Google Scholar
  5. 5.
    Lazo-Cortes, M., Ruiz-Shulcloper, J., Alba Cabrera, E.: An Overview of the evolution of the concept of testor. Pattern Recognition 34(4), 753–762 (2001)zbMATHCrossRefGoogle Scholar
  6. 6.
    Martinez-Trinidad, J.F., Guzman Arenas, A.: The Logical Combinatorial approach for pattern recognition an overview through selected Works. Pattern Recognition 34(4), 741–751 (2001)zbMATHCrossRefGoogle Scholar
  7. 7.
    Morales, R.: A classification system and pattern recognition. B. Sh. Thesis, Mexico, UNAM (1988) (In Spanish)Google Scholar
  8. 8.
    Ruiz-Shulcloper, J., Abidi, M.: Logical Combinatorial Pattern Recognition: A Review. Recent Research Developments in Pattern Recognition. In: Pandalai, S.G. (ed.) Recent Research Developments in Pattern Recognition, Transworld Research Networks, Kerala, India, pp. 133–176 (2002)Google Scholar
  9. 9.
    Shulcloper, J.R., Bravo, M.A.Y., Aguila, F.L.: Algorithms BT and TB for calculating all typical tests. Revista Ciencias Matematicas, Cuba 6(2), 11–18 (1982) (In Spanish)Google Scholar
  10. 10.
    Ruiz Shulcloper, J., Guzman Arenas, A., y Martinez Trinidad J.: Logical combinatorial pattern recognition approach”. Advances on pattern recognition series, Edit. Instituto Politecnico Nacional, Mexico (1999) (In Spanish)Google Scholar
  11. 11.
    Sanchez Diaz, G,: Developing and implementing efficient algorithms (batch and parallel) for calculating typical testors of a basic matrix. Master Thesis, BUAP, Puebla, Mexico (1997) (In Spanish)Google Scholar
  12. 12.
    Sanchez Diaz, G., y Lazo Cortes, M.: Modifications to BT algorithm for improving its run time execution. Revista Ciencias Matematicas, Cuba 20(2), 129–136 (2002) (In Spanish)Google Scholar
  13. 13.
    Sanchez Diaz, G., Lazo Cortes, M., y Fuentes Chavez, O.: Genetic algorithm for calculating typical testors of minimal cost. In: Proc. SIARP 1999, pp. 207–213 (1999) (In Spanish)Google Scholar
  14. 14.
    Sanchez Diaz, G., Lazo Cortes, M., Garcia Fernandez, J.: Parallel and distributed models for calculating typical testors. In: Proc. TIARP 1997, pp. 135–140 (1997) (In Spanish)Google Scholar
  15. 15.
    Santiesteban Alganza, Y., Pons Porrata, A.: LEX: A new algorithm for calculating typical testors. Revista Ciencias Matematicas, Cuba 21(1), 85–95 (2003) (In Spanish)MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Guillermo Sanchez-Díaz
    • 1
  • Manuel Lazo-Cortés
    • 2
  1. 1.Center of Technologies Research on Information and Systems, UAEH, Carr. Pachuca-Tulancingo Km. 4.5, C.P. 42084, Pachuca, Hgo.Mexico
  2. 2.Institute of Cybernetics, Mathematics and Physics, 15 No. 551 Vedado, C.P. 10400, HavanaCuba

Personalised recommendations