Relative Reduct-Based Selection of Features for ANN Classifier

  • Urszula Stańczyk
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 59)


Artificial neural networks hold the established position of efficient classifiers used in decision support systems, yet to be efficient an ANN-based classifier requires careful selection of features. The excessive number of conditional attributes is not a guarantee of high classification accuracy, it means gathering and storing more data, and increasing the size of the network. Also the implementation of the trained network can become complex and the classification process takes more time. This line of reasoning leads to conclusion that the number of features should be reduced as far as possible without diminishing the power of the classifier. The paper presents investigations on attribute reduction process performed by exploiting the concept of reducts from the rough set theory and employed within stylometric analysis of literary texts that belongs with automatic categorisation tasks.


ANN rough sets classifier feature selection stylometry 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Cyran, K.A., Mrózek, A.: Rough sets in hybrid methods for pattern recognition. International Journal of Intelligent Systems 16, 149–168 (2001)zbMATHCrossRefGoogle Scholar
  2. 2.
    Cyran, K.A., Stańczyk, U.: Indiscernibility relation for continuous attributes: application in image recognition. In: Kryszkiewicz, M., Peters, J.F., Rybiński, H., Skowron, A. (eds.) RSEISP 2007. LNCS (LNAI), vol. 4585, pp. 726–735. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  3. 3.
    Doumpos, M., Salappa, A.: Feature selection algorithms in classification problems: an experimental evaluation. WSEAS Transactions on Information Science & Applications 2(2), 77–82 (2005)Google Scholar
  4. 4.
    Matthews, R.A.J., Merriam, T.V.N.: Distinguishing literary styles using neural networks. In: Fiesler, E., Beale, R. (eds.) Handbook of neural computation, pp. G8.1.1–6. Oxford University Press, Oxford (1997)Google Scholar
  5. 5.
    Moshkow, M.J., Skowron, A., Suraj, Z.: On covering attribute sets by reducts. In: Kryszkiewicz, M., Peters, J.F., Rybiński, H., Skowron, A. (eds.) RSEISP 2007. LNCS (LNAI), vol. 4585, pp. 175–180. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  6. 6.
    Pawlak, Z.: Rough set rudiments. Tech. rep., Institute of Computer Science Report, Warsaw University of Technology, Warsaw, Poland (1996)Google Scholar
  7. 7.
    Peng, R.D., Hengartner, H.: Quantitative analysis of literary styles. The American Statistician 56(3), 15–38 (2002)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Shen, Q.: Rough feature selection for intelligent classifiers. In: Peters, J.F., Skowron, A., Marek, V.W., Orłowska, E., Słowiński, R., Ziarko, W.P. (eds.) Transactions on Rough Sets VII. LNCS, vol. 4400, pp. 244–255. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  9. 9.
    Słowiński, R., Greco, S., Matarazzo, B.: Dominance-based rough set approach to reasoning about ordinal data. In: Kryszkiewicz, M., Peters, J.F., Rybiński, H., Skowron, A. (eds.) RSEISP 2007. LNCS (LNAI), vol. 4585, pp. 5–11. Springer, Heidelberg (2007)Google Scholar
  10. 10.
    Smolinski, T.G., Chenoweth, D.L., Zurada, J.M.: Application of rough sets and neural networks to forecasting university facility and administrative cost recovery. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS (LNAI), vol. 3070, pp. 538–543. Springer, Heidelberg (2004)Google Scholar
  11. 11.
    Stańczyk, U., Cyran, K.A.: On employing elements of rough set theory to stylometric analysis of literary texts. International Journal on Applied Mathematics and Informatics 1(2), 159–166 (2007)Google Scholar
  12. 12.
    Stefanowski, J.: On combined classifiers, rule induction and rough sets. In: Peters, J.F., Skowron, A., Düntsch, I., Grzymała-Busse, J.W., Orłowska, E., Polkowski, L. (eds.) Transactions on Rough Sets VI. LNCS, vol. 4374, pp. 329–350. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Urszula Stańczyk
    • 1
  1. 1.Institute of InformaticsSilesian University of TechnologyGliwice

Personalised recommendations