Bagging and Induction of Decision Rules

  • Jerzy Stefanowski
Part of the Advances in Soft Computing book series (AINSC, volume 17)


An application of the rule induction algorithm MODLEM to bagging is discussed. Bagging is a recent approach to construct multiple classifiers that combines homogeneous classifiers generated from different distributions of training examples. The basic characteristics of bagging and the MODLEM are given. This paper reports an experimental study of using bagging composite classifier and the single MODLEM based classifier on a representative collection of datasets. The results show that bagging substantially improve predictive accuracy.


Predictive Accuracy Elementary Condition Rule Induction Matching Rule Multiple Classifier System 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Blake C., Koegh E., Mertz C.J. (1999) Repository of Machine Learning, University of California at Irvine [URL:].
  2. 2.
    Breiman L. (1996) Bagging predictors. Machine Learning, 24 (2), 123–140MathSciNetMATHGoogle Scholar
  3. 3.
    Bauer E., Kohavi R. (1999) An empirical comparison of voting classification algorithms: Bagging, boosting, and variants. Machine Learning 36 (1/2), 105139.Google Scholar
  4. 4.
    Dietrich T.G. (2000) Ensemble methods in machine learning. In: Proc. of 1st Int. Workshop on Multiple Classifier Systems, 1–15.CrossRefGoogle Scholar
  5. 5.
    Freund Y., Schapire R.E. (1996) Experiments with a new boosting algorithm. In: Proc. 13th Int. Conference on Machine Learning, 148–156.Google Scholar
  6. 6.
    Gama J. (1999) Combining classification algorithms. Ph.D. Thesis, University of Porto.Google Scholar
  7. 7.
    Grzymala-Busse J.W. (1992) LERS–a system for learning from examples based on rough sets. In: Slowinski R. (Ed.), Intelligent Decision Support, Kluwer Academic Publishers, 3–18.CrossRefGoogle Scholar
  8. 8.
    Grzymala-Busse J.W. (1994) Managing uncertainty in machine learning from examples. In: Proc. 3rd Int. Symp. in Intelligent Systems, Wigry, Poland, IPI PAN Press, 70–84.Google Scholar
  9. 9.
    Grzymala-Busse J.W., Stefanowski J. (2001) Three approaches to numerical attribute discretization for rule induction. International Journal of Intelligent Systems, 16 (1), 29–38.CrossRefMATHGoogle Scholar
  10. 10.
    Michalski R.S., Tecuci G. (Eds) (1994) Machine Learning. A multistrategy approach. Volume IV. Morgan KaufmannGoogle Scholar
  11. 11.
    Quinlan J.R. (1996) Bagging, boosting and C4.5. In: Proceedings of the 13th National Conference on Artificial Intelligence, 725–730.Google Scholar
  12. 12.
    Stefanowski J. (1998) The rough set based rule induction technique for classification problems. In: Proceedings of 6th Euorpean Conference on Intelligent Techniques and Soft Computing Aaachen EUFIT 98, 7–10 Sept. 109–113.Google Scholar
  13. 13.
    Stefanowski J. (2001) Multiple and hybrid classifiers. In: Polkowski L. (Ed.) Formal Methods and Intelligent Techniques in Control, Decision Making, Multimedia and Robotics, Post-Proceedings of 2nd Int. Conference, Warszawa, 174-188.Google Scholar
  14. 14.
    Stefanowski J. (2001) Algorithims of rule induction for knowledge discovery. (In Polish), Habilitation Thesis published as Series Rozprawy no. 361, Poznan Univeristy of Technology Press, Poznan.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Jerzy Stefanowski
    • 1
  1. 1.Institute of Computing SciencePoznan University of TechnologyPoznanPoland

Personalised recommendations