Advertisement

RandomFIS: A Fuzzy Classification System for Big Datasets

  • Oscar Samudio
  • Marley VellascoEmail author
  • Ricardo Tanscheit
  • Adriano Koshiyama
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 529)

Abstract

One of the main advantages of fuzzy classifier models is their linguistic interpretability, revealing the relation between input variables and the output class. However, these systems suffer from the curse of dimensionality when dealing with high dimensional problems (large number of attributes and instances). This paper presents a new fuzzy classifier model, named RandomFIS, that provides good performance in both classification accuracy and rule base interpretability even when dealing with databases comprising large numbers of inputs (attributes) and patterns (instances). RandomFIS employs concepts from Random Subspace and Bag of little Bootstrap (BLB), resulting in an ensemble of fuzzy classifiers. It was tested with different classification benchmarks, proving to be an accurate and interpretable model, even for problems involving big databases.

Keywords

Fuzzy inference system Classification Bootstrapping RandomSubspace Bag of little Bootstrap 

References

  1. 1.
    Kuncheva, L.I.: Fuzzy Classifier Design, vol. 49. Springer, Heidelberg (2000)zbMATHGoogle Scholar
  2. 2.
    Zhang, Y., Wu, X.B., Xing, Z.Y., Hu, W.L.: On generating interpretable and precise fuzzy systems based on Pareto multi-objective cooperative co-evolutionary algorithm. Appl. Soft Comput. J. 11(1), 1284–1294 (2011)CrossRefGoogle Scholar
  3. 3.
    Koshiyama, A.S., Vellasco, M.M.B.R., Tanscheit, R.: GPFIS-CLASS: A Genetic Fuzzy System based on Genetic Programming for classification problems. Appl. Soft Comput. 37, 561–571 (2015)CrossRefGoogle Scholar
  4. 4.
    Lemos, A., Caminhas, W., Gomide, F.: Evolving Intelligent Systems: Methods, Algorithms and Applications, pp. 117–159. Springer, Berlin, Heidelberg (2013)Google Scholar
  5. 5.
    Paredes, J., Tanscheit, R., Vellasco, M., Koshiyama, A.: Automatic synthesis of fuzzy inference systems for classification. In: Carvalho, J.P., Lesot, M.-J., Kaymak, U., Vieira, S., Bouchon-Meunier, B., Yager, R.R. (eds.) IPMU 2016. CCIS, vol. 610, pp. 486–497. Springer, Heidelberg (2016). doi: 10.1007/978-3-319-40596-4_41 CrossRefGoogle Scholar
  6. 6.
    Ishibuchi, H., Nakashima, T., Nii, M.: Classification and modeling with linguistic information granules: advanced approaches to linguistic Data Mining (2006)Google Scholar
  7. 7.
    Kuncheva, L.I.: Combining Pattern Classifiers: Methods and Algorithms (2004)Google Scholar
  8. 8.
    Panov, P., Džeroski, S.: Combining bagging and random subspaces to create better ensembles. In: International Conference on Intelligent Data Analysis, pp. 118–129 (2007)Google Scholar
  9. 9.
    Kleiner, A., Jordan, M.I.: The big data bootstrap. In: Proceedings of 29th International Conference Machine Learning, p. 8 (2012)Google Scholar
  10. 10.
    Fernández, A., Calderón, M., Barrenechea, E., Bustince, H., Herrera, F.: Solving multi-class problems with linguistic fuzzy rule based classification systems based on pairwise learning and preference relations. Fuzzy Sets Syst. 161(23), 3064–3080 (2010)MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Calvo, T., Kolesárová, A., Komorníková, M., Mesiar, R.: Aggregation operators: properties, classes and construction methods. Aggreg. Oper. New Trends Appl. 97(1), 3–104 (2002)MathSciNetzbMATHGoogle Scholar
  12. 12.
    Lichman, M.: UCI Machine Learning Repository (2013). http://archive.ics.uci.edu/ml. Accessed 01 Mar 2016
  13. 13.
    del Río, S., López, V., Benítez, J.M., Herrera, F.: A mapreduce approach to address big data classification problems based on the fusion of linguistic fuzzy rules. Int. J. Comput. Intell. Syst. 8(3), 422–437 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Oscar Samudio
    • 1
  • Marley Vellasco
    • 1
    Email author
  • Ricardo Tanscheit
    • 1
  • Adriano Koshiyama
    • 1
  1. 1.Department of Electrical EngineeringPontifical Catholic University of Rio de JaneiroRio de JaneiroBrazil

Personalised recommendations