Skip to main content
SpringerLink
Log in

Nearest-Neighbours for Time Series

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

This paper presents an application of lazy learning algorithms in the domain of industrial processes. These processes are described by a set of variables, each corresponding a time series. Each variable plays a different role in the process and some mutual influences can be discovered.

A methodology to study the different variables and their roles in the process are described. This methodology allows the structuration of the study of the time series.

The prediction methodology is based on a k-nearest neighbour algorithm. A complete study of the different parameters of this kind of algorithm is done, including data preprocessing, neighbour distance, and weighting strategies. An alternative to Euclidean distance called shape distance is presented, this distance is insensitive to scaling and translation. Alternative weighting strategies based on time series autocorrelation and partial autocorrelation are also presented.

Experiments using autorregresive models, simulated data and real data obtained from an industrial process (Waste water treatment plants) are presented to show the feasabilty of our approach.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. G.E.P. Box and F.M. Jenkins, Time Series Analysis: Forecasting and Control, 2nd edition Holden-Day: Oakland, CA, 1976.

    Google Scholar 

  2. R.E. Kalman, “A new approach to linear filtering and prediction problems,” Transactions of the ASME-Journal of Basic Engineering, pp. 35–45, 1960.

  3. S. Mukherjee, E. Osuna, and F. Girosi, “Nonlinear prediction of chaotic time series using support vector machines,” in Proceedings of the IEEE NNSP'97, Florida, 1997.

  4. M. Sànchez-Marré, DAI-DEPUR: An Integrated Supervisory Multi-Level Architecture for Wastewater Treatment Plants, PhD Thesis, Universitat Politècnica de Catalunya, 1996.

  5. A. Aamodt and E. Plaza, “Case-based reasoning: Fundamental issues, methodological variations and system approaches,” AI Communications, vol. 7, no. 1, pp. 39–59, 1994.

    Google Scholar 

  6. D.W. Aha (Ed.), Artificial Intelligence Review, vol. 11, pp. 1–6, 1997.

  7. T. Mitchell, Machine Learning. Prentice-Hall, 1997.

  8. G. Das, D. Lin, H. Mannila, G. Renganathan, and P. Smyth. “Rule discovery from time series,” in Proc. of the Fourth International Conference on Knowledge Discovery and Data Mining (KDD-98). AAAI Press, 1998, pp. 16–22.

  9. E.J. Keogh and M.J. Pazzani, “An enhanced representation of time series which allows fast and accurate classification and relevance feedback,” International Conference of Knowledge Discovery and Data Mining, 1998, pp. 239–241.

  10. M.W. Kadou, “Learning comprehensible descriptions of multivariate time series,” in Proceedings of the Sixteenth International Conferrence(ICML'99), Morgan Kaufmann, 1999, pp. 454–463.

  11. J.D. Farmer and J.J. Sidorowich, “Predicting chaotic time series,” Physical Review Letters, vol. 58, no. 8, 1987.

    Google Scholar 

  12. G. Bontempi, M. Birattari, and H. Bersini, “Local learning for iterated time series prediction,” in Proceedings of the Sixteenth International Conference. Morgan Kaufmann Publishers: San Francisco, CA, 1999, pp. 32–38.

    Google Scholar 

  13. S. Cost and S. Salzberg, “A weighted nearest neighbor algorithm for learning with symbolic features,” Machine Learning, vol. 10, pp. 57–78, 1993.

    Google Scholar 

  14. F. Fernández-Rodríguez, S. Sosvilla-Rivero, and J. Andrada-Félix, “Exchange-rate forecasts with simultaneous nearest-neighbour methods: Evidence from the EMS,” International Journal of Forecasting, vol. 15, pp. 383–392, 1999.

    Google Scholar 

  15. S.K. Lam and M.H. Wong, “A fast projection algorithm for sequence data searching,” Data & Knowledge Engineering, vol. 28, pp. 312–339, 1998. Nearest-Neighbours for Time Series 35

    Google Scholar 

  16. D. Wettschereck, A Study of Distance-Based Machine Learning Algorithms, PhD Thesis, Oregon State University, 1994.

  17. Y. Bengio, Markovian Models for Sequential Data, Dept. Informatique et Recherche Opérationnelle, Université de Montréal.

  18. J.M. Gimeno, J. Béjar, M. Sànchez-Marrè, U. Cortés, I. R.-Roda, M. Poch, and J. Lafuente, “Providing WWTP with predictive knowledge based on transition networks,” in Proc. of Int. Conference on Intelligent Information Systems (IIS'97). The Bahamas, 1997.

  19. Operation of Municipal Wastewater Treatment Plants, Manual of practice No. 11, Water Pollution Control Federation, 1994.

Download references

Author information

Authors and Affiliations

  1. Departament d'Informàtica i Enginyeria Industrial, Universitat de Lleida, Spain

    Juan Manuel Gimeno Illa

  2. Departament de Llenguatges i Sistemes Informàtics, Universitat Politècnica de Catalunya, Spain

    Javier Béjar Alonso & Miquel Sànchez Marré

Authors
  1. Juan Manuel Gimeno Illa
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Javier Béjar Alonso
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Miquel Sànchez Marré
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Illa, J.M.G., Alonso, J.B. & Marré, M.S. Nearest-Neighbours for Time Series. Applied Intelligence 20, 21–35 (2004). https://doi.org/10.1023/B:APIN.0000011139.94055.7a

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/B:APIN.0000011139.94055.7a

Search

Navigation