Advertisement

Simultaneous Features and Objects Selection for Mixed and Incomplete Data

  • Yenny Villuendas-Rey
  • Milton García-Borroto
  • Miguel A. Medina-Pérez
  • José Ruiz-Shulcloper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4225)

Abstract

In this paper a new simultaneous editing and feature selection method for the Most Similar Neighbor classifier is proposed. It is designed for databases with objects described by features no exclusively numeric or categorical. It is based on Testor Theory and the Compact Set Editing method, mixing edited projections until a good accuracy is achieved. Experimental results with several databases show a good performance compared to previous methods and the classifier using the original sample.

Keywords

Training Sample Feature Selection Method Classifier Accuracy Object Selection Neighbor Rule 
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.

References

  1. 1.
    Duda, R.O., Hart, P.E.: Pattern Classification and Scene Analysis. John Wiley, New York (1973)MATHGoogle Scholar
  2. 2.
    Dasarathy, B.V.: Concurrent Feature and Prototype Selection in the Nearest Neighbor Decision Process. In: 4th World Multiconference on Systemics, Cybernetics and Informatics, Orlando, USA, vol. VII, pp. 628–633 (2000)Google Scholar
  3. 3.
    Ishibushi, H., Nakashima, T.: Evolution of reference sets in nearest neighbor classification. In: McKay, B., Yao, X., Newton, C.S., Kim, J.-H., Furuhashi, T. (eds.) SEAL 1998. LNCS (LNAI), vol. 1585, pp. 82–89. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  4. 4.
    Kuncheva, L.I., Jain, L.C.: Nearest neighbor classifier: Simultaneous editing and feature selection. Pattern Recognition Letters (1999)Google Scholar
  5. 5.
    Skalak, D.B.: Prototype and Feature Selection by Sampling and Random Mutation Hill Climbing Algorithms. In: Eleventh International Conference on Machine Learning (1994)Google Scholar
  6. 6.
    Kittler, J.: Feature set search algorithms. In: Chen, C.H. (ed.) Pattern recognition and signal proccessing. Sijthoff and Noordhoff, The Netherlands (1978)Google Scholar
  7. 7.
    Toussaint, G.T.: Proximity Graphs for Nearest Neighbor Decision Rules: Recent Progress. In: 34 Symposium on Computing and Statistics INTERFACE-2002, Montreal, Canada (2002)Google Scholar
  8. 8.
    Dasarathy, B.D.: Minimal consistent set (MCS) identification for optimal nearest neighbor decision systems design. IEEE Transactions on systems, man and cybernetics 24, 511–517 (1994)CrossRefGoogle Scholar
  9. 9.
    Ruiz-Shulcloper, J., Abidi, M.A.: Logical combinatorial pattern recognition: A Review. In: Pandalai, S.G. (ed.) Recent Research Developments in Pattern Recognition. Transword Research Networks, USA, pp. 133–176 (2002)Google Scholar
  10. 10.
    García-Borroto, M., Ruiz-Shulcloper, J.: Selecting Prototypes in Mixed Incomplete Data. In: Sanfeliu, A., Cortés, M.L. (eds.) CIARP 2005. LNCS, vol. 3773, pp. 450–459. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  11. 11.
    Santiesteban, Y., Pons, A.: Un nuevo algoritmo para el cálculo de los testores típicos. Revista de Ciencias Matemáticas 21, 85–95 (2003)Google Scholar
  12. 12.
    Lazo-Cortés, M., Ruiz-Shulcloper, J.: Determining the feature informational weight for non-classical described objects and new algorithm to calculate fuzzy testors. Pattern Recognition Letters 16, 1259–1265 (1995)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yenny Villuendas-Rey
    • 1
  • Milton García-Borroto
    • 2
  • Miguel A. Medina-Pérez
    • 1
  • José Ruiz-Shulcloper
    • 3
  1. 1.University of Ciego de ÁvilaCuba
  2. 2.Bioplants CenterUNICA, C. de ÁvilaCuba
  3. 3.Advanced Technologies Applications CenterMINBASCuba

Personalised recommendations