Intruder Data Classification Using GM-SOM

  • Petr Gajdoš
  • Pavel Moravec
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7564)


This paper uses a simple modification of classic Kohonen network (SOM), which allows parallel processing of input data vectors or partitioning the problem in case of insufficient resources (memory, disc space, etc.) to process all input vectors at once. The algorithm has been implemented to meet a specification of modern multicore graphics processors to achieve massive parallelism. The algorithm pre-selects potential centroids of data clusters and uses them as weight vectors in the final SOM network.In this paper, the algorithm is used on a well-known KDD Cup 1999 intruders dataset.


SOM Kohonen Network parallel computation KDD Cup 1999 Data Set 


  1. 1.
    Mann, R., Haykin, S.: A parallel implementation of Kohonen’s feature maps on the warp systolic computer. In: Proc. IJCNN-90-WASH-DC, Int. Joint Conf. on Neural Networks, vol. II, pp. 84–87. Lawrence Erlbaum, Hillsdale (1990)Google Scholar
  2. 2.
    Openshaw, S., Turton, I.: A parallel Kohonen algorithm for the classification of large spatial datasets. Computers & Geosciences 22(9), 1019–1026 (1996)CrossRefGoogle Scholar
  3. 3.
    Nordström, T.: Designing parallel computers for self organizing maps. In: Forth Swedish Workshop on Computer System Architecture (1992)Google Scholar
  4. 4.
    Valova, I., Szer, D., Gueorguieva, N., Buer, A.: A parallel growing architecture for self-organizing maps with unsupervised learning. Neurocomputing 68, 177–195 (2005)CrossRefGoogle Scholar
  5. 5.
    Wei-gang, L.: A study of parallel self-organizing map. In: Proceedings of the International Joint Conference on Neural Networks (1999)Google Scholar
  6. 6.
    Fort, J., Letremy, P., Cottrel, M.: Advantages and drawbacks of the batch Kohonen algorithm. In: Proceedings of the 10th European-Symposium on Artificial Neural Networks, ESANN 2002, pp. 223–230 (2002)Google Scholar
  7. 7.
    Kohonen, T.: Self-Organizing Maps, 2nd (extended) edn. Springer, Berlin (1997)MATHCrossRefGoogle Scholar
  8. 8.
    Hager, G., Zeiser, T., Wellein, G.: Data access optimizations for highly threaded multi-core CPUs with multiple memory controllers. In: IPDPS, pp. 1–7. IEEE (2008)Google Scholar
  9. 9.
    Andrecut, M.: Parallel GPU implementation of iterative PCA algorithms. Journal of Computational Biology 16(11), 1593–1599 (2009)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Preis, T., Virnau, P., Paul, W., Schneider, J.J.: Accelerated fluctuation analysis by graphic cards and complex pattern formation in financial markets. New Journal of Physics 11(9), 093024 (21p.) (2009)Google Scholar
  11. 11.
    Patnaik, D., Ponce, S.P., Cao, Y., Ramakrishnan, N.: Accelerator-oriented algorithm transformation for temporal data mining. CoRR abs/0905.2203 (2009)Google Scholar
  12. 12.
    Platos, J., Kromer, P., Snasel, V., Abraham, A.: Scaling IDS construction based on non-negative matrix factorization using GPU computing. In: 2010 Sixth International Conference on Information Assurance and Security (IAS), pp. 86–91 (August 2010)Google Scholar
  13. 13.
    Gajdos, P., Platos, J., Moravec, P.: Iris recognition on GPU with the usage of non-negative matrix factorization. In: 2010 10th International Conference on Intelligent Systems Design and Applications (ISDA), November 29-December 1, pp. 894–899 (2010)Google Scholar
  14. 14.
    Stolfo, S., Fan, W., Lee, W., Prodromidis, A., Chan, P.: Cost-based modeling for fraud and intrusion detection: results from the jam project. In: Proceedings of the DARPA Information Survivability Conference and Exposition, DISCEX 2000, vol. 2, pp. 130–144 (2000)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2012

Authors and Affiliations

  • Petr Gajdoš
    • 1
  • Pavel Moravec
    • 1
  1. 1.Department of Computer Science, FEECSVŠB - Technical University of OstravaOstrava-PorubaCzech Republic

Personalised recommendations