DIVIDING OUTLIERS INTO VALUABLE AND NOISE POINTS

Authors

  • Vladimir E. Podolskiy

DOI:

https://doi.org/10.47839/ijc.11.1.547

Keywords:

fuzzy sets, outlier analysis, data classification.

Abstract

A great number of different clustering algorithms exists in computer science. These algorithms solve the task of dividing data set into clusters. Data points which were not included into one of these clusters are called ‘outliers’. But such data points can be used for the discovery of unusual behavior of the analyzed systems. In this article we present a novel fuzzy based optimization approach for division these outliers into two classes: interesting (usable for solving the problem) outliers and noise.

References

F. Rehm, F. Klawonn, R. Kruse, A novel approach to noise clustering for outliers detection, Soft Computing, (11) 5 (2007), pp. 489-494.

J. Han, M. Kamber, Data Mining: Concepts and Techniques, Morgan Kaufmann Publishers, USA, 2006, 743 p.

D. Viattchenin, Direct algorithms of fuzzy clustering based on the transitive closure operation and their application to outliers detection, Artificial Intelligence, (3) (2007), pp. 205-216. (in Russian)

A. Kaufmann, Introduction to Fuzzy Sets Theory, Radio and Contact, Moscow, 1982, 432 p. (in Russian)

D. Viattchenin, Fuzzy Methods of Automatic Classification, Minsk, Technoprint, 2004, 219 p. (in Russian)

M. Gautam, R. Levkovitz, Interior Point Methods for Linear Programming Optimization: Theory and Practice, John Wiley & Sons, USA, 1996, 300 p.

M. Daszykowski, B. Walczak, D.L. Massart, Looking for Natural Patterns in Data. Part 1: Density Based Approach. Chemom. Intell. Lab. Syst. (56) (2001), pp. 83-92.

V.E. Podolskiy, Simple fuzzy based optimization approach to the problem of dividing outliers into classes of valuable and noise points, Pattern Recognition and Information Processing (PRIP’2011): proceedings of the 11th International Conference (18-20 May, Minsk, Republic of Belarus), Minsk: BSUIR, 2011, pp. 176-179.

Downloads

Published

2014-08-01

How to Cite

Podolskiy, V. E. (2014). DIVIDING OUTLIERS INTO VALUABLE AND NOISE POINTS. International Journal of Computing, 11(1), 25-31. https://doi.org/10.47839/ijc.11.1.547

Issue

Section

Articles