Outlier Detection Using Ball Descriptions with Adjustable Metric

  • David M. J. Tax
  • Piotr Juszczak
  • Elżbieta Pękalska
  • Robert P. W. Duin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4109)


Sometimes novel or outlier data has to be detected. The outliers may indicate some interesting rare event, or they should be disregarded because they cannot be reliably processed further. In the ideal case that the objects are represented by very good features, the genuine data forms a compact cluster and a good outlier measure is the distance to the cluster center. This paper proposes three new formulations to find a good cluster center together with an optimized ℓ p -distance measure. Experiments show that for some real world datasets very good classification results are obtained and that, more specifically, the ℓ1-distance is particularly suited for datasets containing discrete feature values.


one-class classification outlier detection robustness p-ball 


  1. 1.
    Tax, D.: One-class classification. PhD thesis, Delft University of Technology (2001),
  2. 2.
    Koch, M., Moya, M., Hostetler, L., Fogler, R.: Cueing, feature discovery and one-class learning for synthetic aperture radar automatic target recognition. Neural Networks 8(7/8), 1081–1102 (1995)CrossRefGoogle Scholar
  3. 3.
    Huber, P.: Robust statistics: a review. Ann. Statist. 43, 1041 (1972)CrossRefzbMATHMathSciNetGoogle Scholar
  4. 4.
    Rousseeuw, P., Van Driessen, K.: A fast algorithm for the minimum covariance determinant estimator. Technometrics 41, 212–223 (1999)CrossRefGoogle Scholar
  5. 5.
    Pisier, G.: The volume of convex bodies and Banach space geometry. Cambridge University Press, Cambridge (1989)CrossRefzbMATHGoogle Scholar
  6. 6.
    Tax, D., Duin, R.: Uniform object generation for optimizing one-class classifiers. Journal for Machine Learning Research, 155–173 (2001)Google Scholar
  7. 7.
    Barnett, V., Lewis, T.: Outliers in statistical data, 2nd edn. Wiley series in probability and mathematical statistics. John Wiley & Sons Ltd, Chichester (1978)zbMATHGoogle Scholar
  8. 8.
    Nelder, J., Mead, R.: A simplex method for function minimization. Computer journal 7(4), 308–311 (1965)zbMATHGoogle Scholar
  9. 9.
    He, X., Simpson, D., Portnoy, S.: Breakdown robustness of tests. Journal of the American Statistical Association 85(40), 446–452 (1990)CrossRefzbMATHMathSciNetGoogle Scholar
  10. 10.
    Blake, C., Merz, C.: UCI repository of machine learning databases (1998)Google Scholar
  11. 11.
    Duin, R.: On the choice of the smoothing parameters for Parzen estimators of probability density functions. IEEE Transactions on Computers C-25(11), 1175–1179 (1976)CrossRefMathSciNetGoogle Scholar
  12. 12.
    Tax, D., Duin, R.: Support vector data description. Machine Learning 54(1), 45–66 (2004)CrossRefzbMATHGoogle Scholar
  13. 13.
    Bradley, A.: The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition 30(7), 1145–1159 (1997)CrossRefGoogle Scholar
  14. 14.
    Lloyd, S.: Least squares quantization in PCM. IEEE Transactions on Information Theory 28(2), 129–137 (1982)CrossRefzbMATHMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • David M. J. Tax
    • 1
  • Piotr Juszczak
    • 1
  • Elżbieta Pękalska
    • 2
  • Robert P. W. Duin
    • 1
  1. 1.Information and Communication Theory GroupDelft University of TechnologyDelftThe Netherlands
  2. 2.School of Computer ScienceUniversity of ManchesterManchesterUnited Kingdom

Personalised recommendations