Decision Fusion Methods in a Dispersed Decision System - A Comparison on Medical Data

  • Małgorzata Przybyła-Kasperek
  • Agnieszka Nowak-Brzezińska
  • Roman Simiński
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10449)


A dispersed decision-making system that use knowledge accumulated in separate knowledge bases is considered in this paper. The system has complex and dynamic structure. In previous papers, different fusion methods were applied in this system. The novelty of this paper is to examine an approach in which many different fusion methods from the rank or from the measurement level are used simultaneously in one decision-making process. The obtained results were compared with the results obtained when fusion methods are used individually. In addition, the results were compared with an approach in which a dispersed system is not used, but the classifications generated based on each local base are directly aggregated using fusion methods. The conclusions indicated the legitimacy of the use of a dispersed system.


Dispersed system Fusion methods Combining classifiers 


  1. 1.
    Bazan, J.G.: Hierarchical classifiers for complex spatio-temporal concepts. In: Peters, J.F., Skowron, A., Rybiński, H. (eds.) Transactions on Rough Sets IX: Journal Subline. LNCS, vol. 5390, pp. 474–750. Springer, Heidelberg (2008). doi: 10.1007/978-3-540-89876-4_26CrossRefGoogle Scholar
  2. 2.
    Gatnar, E.: Multiple-Model Approach to Classification and Regression. PWN, Warsaw (2008). (in Polish)Google Scholar
  3. 3.
    Ga̧golewski, M.: Data fusion: theory, methods, and applications. Institute of Computer Science Polish Academy of Sciences (2015)Google Scholar
  4. 4.
    Kittler, J., Hatef, M., Duin, R.P.W., Matas, J.: On combining classifiers. IEEE Trans. Pattern Anal. Mach. Intell. 20(3), 226–239 (1998)CrossRefGoogle Scholar
  5. 5.
    Kuncheva, L., Bezdek, J.C., Duin, R.P.W.: Decision templates for multiple classifier fusion: an experimental comparison. Pattern Recogn. 34(2), 299–314 (2001)CrossRefGoogle Scholar
  6. 6.
    Kuncheva, L.: Combining Pattern Classifiers Methods and Algorithms. Wiley, Hoboken (2004)CrossRefGoogle Scholar
  7. 7.
    Nowak-Brzezińska, A.: Mining rule-based knowledge bases inspired by rough set theory. Fundamenta Informaticae 148(1–2), 35–50 (2016)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Przybyła-Kasperek, M., Wakulicz-Deja, A.: A dispersed decision-making system - the use of negotiations during the dynamic generation of a systems structure. Inf. Sci. 288, 194–219 (2014)CrossRefGoogle Scholar
  9. 9.
    Przybyła-Kasperek, M.: Comparison of four methods of combining classifiers on the basis of dispersed medical data. In: Czarnowski, I., Caballero, A.M., Howlett, R.J., Jain, L.C. (eds.) IDT 2016. SIST, vol. 57, pp. 3–13. Springer, Cham (2016). doi: 10.1007/978-3-319-39627-9_1CrossRefzbMATHGoogle Scholar
  10. 10.
    Przybyła-Kasperek, M.: Dispersed decision-making system with selected fusion methods from the measurement level - case study with medical data. Ann. Comput. Sci. Inf. Syst. 8, 129–136 (2016)CrossRefGoogle Scholar
  11. 11.
    Przybyła-Kasperek, M., Nowak-Brzezińska, A.: Intersection method, union method, product rule and weighted average method in a dispersed decision-making system - a comparative study on medical data. In: Nguyen, N.-T., Manolopoulos, Y., Iliadis, L., Trawiński, B. (eds.) ICCCI 2016. LNCS, vol. 9876, pp. 451–461. Springer, Cham (2016). doi: 10.1007/978-3-319-45246-3_43CrossRefGoogle Scholar
  12. 12.
    Przybyła-Kasperek, M., Wakulicz-Deja, A.: Comparison of fusion methods from the abstract level and the rank level in a dispersed decision-making system. Int. J. General Systems 46(4), 386–413 (2017)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Simiński, R.: Multivariate approach to modularization of the rule knowledge bases. In: Gruca, A., Brachman, A., Kozielski, S., Czachórski, T. (eds.) MMI 4. AISC, vol. 391, pp. 473–483. Springer, Cham (2016). doi: 10.1007/978-3-319-23437-3_40CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Małgorzata Przybyła-Kasperek
    • 1
  • Agnieszka Nowak-Brzezińska
    • 1
  • Roman Simiński
    • 1
  1. 1.Institute of Computer ScienceUniversity of SilesiaSosnowiecPoland

Personalised recommendations