Building Hybrid Fuzzy Classifier Trees by Additive/Subtractive Composition of Sets

@inproceedings{Hempel2014BuildingHF,
  title={Building Hybrid Fuzzy Classifier Trees by Additive/Subtractive Composition of Sets},
  author={Arne-Jens Hempel and Holger H{\"a}hnel and Gernot Herbst},
  booktitle={IPMU},
  year={2014}
}
Especially for one-class classification problems, an accurate model of the class is necessary. Since the shape of a class might be arbitrarily complex, it is hard to choose an approach that is generic enough to cope with the variety of shapes, while delivering an interpretable model that remains as simple as possible and thus applicable in practice. In this article, this problem is tackled by combining convex building blocks both additively and subtractively in a tree-like structure. The convex… CONTINUE READING

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 16 REFERENCES

Learning non-convex fuzzy classifiers using single-class SVMs

VIEW 10 EXCERPTS

Integration of Statistical Analyses for Parameterisation of the Fuzzy Pattern Classification

  • H. Hähnel, Hempel, A.-J., U. Mönks, V. Lohweg
  • 22. Workshop Computational Intelligence, pp. 115–131. KIT, Karlsruhe
  • 2012
VIEW 1 EXCERPT

SVM-integrated Fuzzy Pattern Classification for Nonconvex Data-inherent Structures Applied to Banknote Authentication

  • Hempel, A.-J., H. Hähnel, U. Mönks, V. Lohweg
  • Bildverarbeitung in der Automation. inIT, Lemgo
  • 2012
VIEW 1 EXCERPT

Top-Down Induction of Fuzzy Pattern Trees

VIEW 1 EXCERPT

Applying Expert Experience to Interpretable Fuzzy Classification System Using Genetic Algorithms

VIEW 1 EXCERPT

Classification of Imbalanced and Overlapping Classes using Intuitionistic Fuzzy Sets

VIEW 1 EXCERPT