A First Attempt on Online Data Stream Classifier Using Context

  • Michał WoźniakEmail author
  • Bogusław Cyganek
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9714)


The big data is characterized by 4Vs (volume, velocity, variety, and variability). In this paper we focus on the velocity, but actually it usually comes together with volume. It means, that the crucial problem of the contemporary data analytics is to answer the question how to discover useful knowledge from fast incoming data. The paper presents an online data stream classification method, which adapts the classification with context to recognize incoming examples and additionally takes into consideration the memory and processing time limitations. The proposed method was evaluated on the real medical diagnosis task. The preliminary results of the experiments encourage us to continue works on the proposed approach.


Data stream Classification with context Pattern classification 



This work was supported by EC under FP7, Coordination and Support Action, Grant Agreement Number 316097, ENGINE - European Research Centre of Network Intelligence for Innovation Enhancement ( This work was also supported by the Polish National Science Center under the grant no. DEC-2013/09/B/ST6/02264. All computer experiments were carried out using computer equipment sponsored by ENGINE project.


  1. 1.
    Widmer, G., Kubat, M.: Learning in the presence of concept drift and hidden contexts. Mach. Learn. 23(1), 69–101 (1996)Google Scholar
  2. 2.
    Domingos, P., Hulten, G.: A general framework for mining massive data streams. J. Comput. Graph. Stat. 12, 945–949 (2003)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Raviv, J.: Decision making in Markov chains applied to the problem of pattern recognition. IEEE Trans. Inf. Theor. 13(4), 536–551 (1967)CrossRefGoogle Scholar
  4. 4.
    Toussaint, G.T.: The use of context in pattern recognition. Pattern Recogn. 10(3), 189–204 (1978)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Haralick, R.M.: Decision making in context. IEEE Trans. Pattern Anal. Mach. Intell. PAMI 5(4), 417–428 (1983)CrossRefzbMATHGoogle Scholar
  6. 6.
    Żołnierek, A.: Pattern recognition algorithms for controlled Markov chains and their application to medical diagnosis. Pattern Recogn. Lett. 1(5), 299–303 (1983)zbMATHGoogle Scholar
  7. 7.
    Ramamurthy, S., Bhatnagar, R.: Tracking recurrent concept drift in streaming data using ensemble classifiers. In: Proceedings of the Sixth International Conference on Machine Learning and Applications, ICMLA 2007, Computer Society, pp. 404–409. IEEE, Washington, DC (2007)Google Scholar
  8. 8.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley, New York (2001)zbMATHGoogle Scholar
  9. 9.
    Settles, B.: Active learning. Synth. Lect. Artif. Intell. Mach. Learn. 6(1), 1–114 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Kurlej, B., Wozniak, M.: Active learning approach to concept drift problem. Log. J. IGPL 20(3), 550–559 (2012)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Goldstein, M.: \(k_n\)-nearest neighbor classification. IEEE Trans. Inf. Theor. 18(5), 627–630 (1972)CrossRefzbMATHGoogle Scholar
  12. 12.
    Bifet, A., Holmes, G., Pfahringer, B., Read, J., Kranen, P., Kremer, H., Jansen, T., Seidl, T.: MOA: a real-time analytics open source framework. In: Gunopulos, D., Hofmann, T., Malerba, D., Vazirgiannis, M. (eds.) ECML PKDD 2011, Part III. LNCS, vol. 6913, pp. 617–620. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  13. 13.
    Wozniak, M.: Proposition of common classifier construction for pattern recognition with context task. Knowl.-Based Syst. 19(8), 617–624 (2006)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1. Faculty of Electronics, Department of Systems and Computer NetworksWrocław University of Science and TechnologyWrocławPoland
  2. 2.AGH University of Science and TechnologyKrakówPoland
  3. 3.ENGINE CenterWrocław University of Science and TechnologyWrocławPoland

Personalised recommendations