Advertisement

General Non-parametric Learning Procedure for Tracking Concept Drift

  • Leszek RutkowskiEmail author
  • Maciej Jaworski
  • Piotr Duda
Chapter
Part of the Studies in Big Data book series (SBD, volume 56)

Abstract

The problems of learning in non-stationary situations has rarely been a subject of studies even in a parametric case. Historically the first papers on learning in non-stationary environments where occasionally published in the sixties and seventies. The proper tool for solving such a type of problems seemed to be the dynamic stochastic approximation technique [1, 2] as an extension of the Robbins-Monro [3] procedure for the non-stationary case. The traditional procedure of stochastic approximation was also used [4, 5] with a good effect for tracking the changing regression function root.

References

  1. 1.
    Dupač, V.: A dynamic stochastic approximation methods. Ann. Math. Stat. 36, 1695–1702 (1965)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Dupač, V.: Stochastic approximations in the presence of trend. Neural Netw. 5, 283–288 (1966)zbMATHGoogle Scholar
  3. 3.
    Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22(1) (1951)Google Scholar
  4. 4.
    Watanabe, M.: On robbins-monro stochastic approximation method with time varying observations. Bull. Math. Statist. 16, 73–91 (1974)MathSciNetzbMATHGoogle Scholar
  5. 5.
    Young, T., Westerberg, R.: Stochastic approximation with a non-stationary regression function. IEEE Trans. Inform. Theory 18, 518–519 (1972)CrossRefGoogle Scholar
  6. 6.
    Fu, K.: Sequential Methods in Pattern Recognition and Machine Learning. Academic, New York (1968)zbMATHGoogle Scholar
  7. 7.
    Tzypkin, J.: Learning algorithms of pattern recognition in non-stationary condition. In: Watanabe, S. (ed.) Frontiers of Pattern Recognitions, pp. 527–542. Academic Press, New York (1972)CrossRefGoogle Scholar
  8. 8.
    Nishida, K., Yamauchi, K.: Learning, detecting, understanding, and predicting concept changes. In: International Joint Conference on Neural Networks. IJCNN 2009, pp. 2280–2287. IEEE (2009)Google Scholar
  9. 9.
    Minku, L.L., Yao, X.: DDD: a new ensemble approach for dealing with concept drift. IEEE Trans. Knowl. Data Eng. 24(4), 619–633 (2012)CrossRefGoogle Scholar
  10. 10.
    Mahdi, O.A., Pardede, E., Cao, J.: Combination of information entropy and ensemble classification for detecting concept drift in data stream. In: Proceedings of the Australasian Computer Science Week Multiconference, p. 13. ACM (2018)Google Scholar
  11. 11.
    Liu, A., Zhang, G., Lu, J.: Fuzzy time windowing for gradual concept drift adaptation. In: IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 1–6. IEEE (2017)Google Scholar
  12. 12.
    Li, P., Wu, X., Hu, X., Wang, H.: Learning concept-drifting data streams with random ensemble decision trees. Neurocomputing 166, 68–83 (2015)CrossRefGoogle Scholar
  13. 13.
    Elwell, R., Polikar, R.: Incremental learning of concept drift in nonstationary environments. IEEE Trans. Neural Netw. 22(10), 1517–1531 (2011)CrossRefGoogle Scholar
  14. 14.
    Alippi, C., Boracchi, G., Roveri, M.: Just-in-time classifiers for recurrent concepts. IEEE Trans. Neural Netw. Learn. Syst. 24(4), 620–634 (2013)CrossRefGoogle Scholar
  15. 15.
    Zliobaite, I., Bifet, A., Pfahringer, B., Holmes, G.: Active learning with drifting streaming data. IEEE Trans. Neural Netw. Learn. Syst. 25(1), 27–39 (2014)CrossRefGoogle Scholar
  16. 16.
    Zhang, T., Zhang, Q., Wang, Q.: Model detection for functional polynomial regression. Comput. Stat. Data Anal. 70, 183–197 (2014)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Yun, U., Lee, G.: Sliding window based weighted erasable stream pattern mining for stream data applications. Futur. Gener. Comput. Syst. 59, 1–20 (2016)CrossRefGoogle Scholar
  18. 18.
    Yin, X., Huang, K., Hao, H.: De2: dynamic ensemble of ensembles for learning nonstationary data. Neurocomputing 165, 14–22 (2015)CrossRefGoogle Scholar
  19. 19.
    Ye, Y., Squartini, S., Piazza, F.: Online sequential extreme learning machine in nonstationary environments. Neurocomputing 116, 94–101 (2013)CrossRefGoogle Scholar
  20. 20.
    Souto Maior Barros, R., Carvalho Santos, S.G.T.: A large-scale comparison of concept drift detectors. Inf. Sci. 451–452, 348–370 (2018)Google Scholar
  21. 21.
    Escovedo, T., Koshiyama, A., Abs da Cruz, A., Vellasco, M.: Detecta: abrupt concept drift detection in non-stationary environments. Appl. Soft Comput. 62, 119–133 (2018)Google Scholar
  22. 22.
    Webb, G.I., Kuan Lee, L., Petitjean, F., Goethals, B.: Understanding concept drift. CoRR (2017). arXiv:1704.00362
  23. 23.
    Zambon, D., Alippi, C., Livi, L.: Concept drift and anomaly detection in graph streams. In: IEEE Transactions on Neural Networks and Learning Systems, pp. 1–14 (2018)Google Scholar
  24. 24.
    Gama, J., Žliobaitė, I., Bifet, A., Pechenizkiy, M., Bouchachia, A.: A survey on concept drift adaptation. ACM Comput. Surv. (CSUR) 46(4), 44:1–44:37 (2014)Google Scholar
  25. 25.
    Ditzler, G., Roveri, M., Alippi, C., Polikar, R.: Learning in nonstationary environments: a survey. IEEE Comput. Intell. Mag. 10(4), 12–25 (2015)CrossRefGoogle Scholar
  26. 26.
    Aizerman, M., Braverman, E., Rozonoer, L.: Theoretical foundations of the potential function method in pattern recognition learning. Autom. Remote Control 25, 821–837 (1964)zbMATHGoogle Scholar
  27. 27.
    Révész, P.: How to apply the method of stochastic approximation in the nonparametric estimation of a regression function. Mathematische Operationsforschung und Statistik Series Statistics 8, 119–126 (1977)MathSciNetCrossRefGoogle Scholar
  28. 28.
    Braverman, E., Rozonoer, L.: Convergence of random processes in machine learning theory. Autom. Remote Control 30, 44–64 (1969)zbMATHGoogle Scholar
  29. 29.
    Sorour, E.: On the convergence of the dynamic stochastic approximation method for stochastic non-linear multidimensional dynamic systems. Cybernetica 14, 28–37 (1978)MathSciNetzbMATHGoogle Scholar
  30. 30.
    Uosaki, K.: Application of stochastic approximation to the tracking of a stochastic non-linear dynamic systems. Int. J. Control 18, 1233–1247 (1973)MathSciNetCrossRefGoogle Scholar
  31. 31.
    Uosaki, K.: Some generalizations of dynamic stochastic approximation process. Ann. Stat. 2, 1042–1048 (1974)MathSciNetCrossRefGoogle Scholar
  32. 32.
    Chung, K.: On a stochastic approximation methods. Ann. Math. Stat. 25, 463–483 (1954)MathSciNetCrossRefGoogle Scholar
  33. 33.
    Watanabe, M.: On convergence of asymptotically optimal discriminant functions for pattern classification problem. Bull. Math. Statist. 16, 23–34 (1974)MathSciNetzbMATHGoogle Scholar
  34. 34.
    Tucker, H.: A Graduate Course in Probability. Academic, New York (1967)zbMATHGoogle Scholar
  35. 35.
    Efromovich, S.: Nonparametric Curve Estimation. Methods, Theory and Applications. Springer, New York (1999)Google Scholar
  36. 36.
    Duda, P., Jaworski, M., Rutkowski, L.: On ensemble components selection in data streams scenario with reoccurring concept-drift. In: 2017 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1–7 (2017)Google Scholar
  37. 37.
    Duda, P., Jaworski, M., Rutkowski, L.: Convergent time-varying regression models for data streams: tracking concept drift by the recursive Parzen-based generalized regression neural networks. Int. J. Neural Syst. 28(02), 1750048 (2018)CrossRefGoogle Scholar
  38. 38.
    Rutkowski, L.: Adaptive probabilistic neural-networks for pattern classification in time-varying environment. IEEE Trans. Neural Netw. 15, 811–827 (2004)CrossRefGoogle Scholar
  39. 39.
    Rutkowski, L.: Generalized regression neural networks in time-varying environment. IEEE Trans. Neural Netw. 15 (2004)Google Scholar
  40. 40.
    Jaworski, M.: Regression function and noise variance tracking methods for data streams with concept drift. Int. J. Appl. Math. Comput. Sci. 28(3), 559–567 (2018)CrossRefGoogle Scholar
  41. 41.
    Jaworski, M., Duda, P., Rutkowski, L., Najgebauer, P., Pawlak, M.: Heuristic regression function estimation methods for data streams with concept drift. Lecture Notes in Computer Science 10246, 726–737 (2017)CrossRefGoogle Scholar
  42. 42.
    Pietruczuk, L., Rutkowski, L., Maciej, J., Duda, P.: The Parzen kernel approach to learning in non-stationary environment. In: 2014 International Joint Conference on Neural Networks (IJCNN), pp. 3319–3323 (2014)Google Scholar
  43. 43.
    Duda, P., Pietruczuk, L., Jaworski, M., Krzyzak, A.: On the Cesaro-means-based orthogonal series approach to learning time-varying regression functions. In: Lecture Notes in Artificial Intelligence, pp. 37–48. Springer, Berlin (2016)Google Scholar
  44. 44.
    Duda, P., Jaworski, M., Rutkowski, L.: Knowledge discovery in data streams with the orthogonal series-based generalized regression neural networks. Inf. Sci. 460–461, 497–518 (2018)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Leszek Rutkowski
    • 1
    • 2
    Email author
  • Maciej Jaworski
    • 1
  • Piotr Duda
    • 1
  1. 1.Institute of Computational IntelligenceCzestochowa University of TechnologyCzęstochowaPoland
  2. 2.Information Technology InstituteUniversity of Social SciencesLodzPoland

Personalised recommendations