Elsevier

Fuzzy Sets and Systems

Volume 183, Issue 1, 16 November 2011, Pages 26-43
Fuzzy Sets and Systems

Robust fuzzy rough classifiers

https://doi.org/10.1016/j.fss.2011.01.016Get rights and content

Abstract

Fuzzy rough sets, generalized from Pawlak's rough sets, were introduced for dealing with continuous or fuzzy data. This model has been widely discussed and applied these years. It is shown that the model of fuzzy rough sets is sensitive to noisy samples, especially sensitive to mislabeled samples. As data are usually contaminated with noise in practice, a robust model is desirable. We introduce a new model of fuzzy rough set model, called soft fuzzy rough sets, and design a robust classification algorithm based on the model. Experimental results show the effectiveness of the proposed algorithm.

References (56)

  • M. Sarkar

    Fuzzy-rough nearest neighbor algorithms in classification

    Fuzzy Sets and Systems

    (2007)
  • Q. Shen et al.

    A rough-fuzzy approach for generating classification rules

    Pattern Recognition

    (2002)
  • W.-Z. Wu et al.

    Constructive and axiomatic approaches of fuzzy approximation operators

    Information Sciences

    (2004)
  • W.-Z. Wu et al.

    Generalized fuzzy rough sets

    Information Sciences

    (2003)
  • L.A. Zadeh

    A computational approach to fuzzy quantifiers in natural languages

    Computers and Mathematics with Applications

    (1983)
  • F. Angiulli et al.

    Fast outlier detection in high dimensional spaces

  • C.L. Blake, C.J. Merz, UCI Repository of Machine Learning Databases, 1998. Available:...
  • R.B. Bhatt et al.

    FRCT: fuzzy-rough classification trees

    Pattern Analysis and Applications

    (2008)
  • D.R. Chen et al.

    Support vector machine soft margin classifiers: error analysis

    Journal of Machine Learning Research

    (2004)
  • Y. Chen et al.

    Outlier detection with the kernelized spatial depth function

    IEEE Transactions on Pattern Analysis and Machine Intelligence

    (2009)
  • C. Cornelis et al.

    Vaguely quantified rough sets

  • T.M. Cover et al.

    Nearest neighbor pattern classification

    IEEE Transactions on Information Theory

    (1967)
  • B.V. Dasarathy (Ed.), Nearest Neighbor NN Norms: NN Pattern Classification Techniques, IEEE Computer Society,...
  • D. Dubois et al.

    Rough fuzzy sets and fuzzy rough sets

    International Journal of General Systems

    (1990)
  • M. Ester et al.

    A density-based algorithm for discovering clusters in large spatial databases with noise

  • H. Fan et al.

    Noise tolerant classification by chi emerging patterns

  • ...
  • ...
  • Cited by (51)

    • A relative uncertainty measure for fuzzy rough feature selection

      2021, International Journal of Approximate Reasoning
      Citation Excerpt :

      For classification tasks, fuzzy rough set (FRS) theory is a popular mathematical tool for uncertainty measure [9]. This theory is extensively used in machine learning algorithms such as data reduction [16][26][28][29][34], classification [4][5][13][34] and regression [1]. To improve the generalization of classical FRSs in measuring the uncertainty of data, a series of FRS models are proposed, namely variable precision-based FRSs [32][35], fuzzy quantified rough sets [6], soft FRSs [12][13], robust statistics-based FRSs [14], and granular computing theory-based FRSs [3][10].

    • Key energy-consumption feature selection of thermal power systems based on robust attribute reduction with rough sets

      2020, Information Sciences
      Citation Excerpt :

      Zhao et al. and Lynn et al. proposed a variable precision fuzzy rough set model [25,36], and designed a more robust attribute reduction [23,37]. Hu et al. proposed softening the distance to calculate the membership degree [13,14], and designed robust fuzzy rough classifiers [12]. Hu et al. studied the instability of the lower approximation calculation caused by the disturbance of the indiscernible relation in rough sets [10,11].

    View all citing articles on Scopus
    View full text