Analysing a Periodical and Multi-dimensional Time Series

  • Octavian Lucian HasnaEmail author
  • Rodica PotoleaEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11308)


Time series analysis has become an important field of data mining in the last decade. Dynamics of real-world processes are important in domains like seismology, medicine, astrophysics, meteorology, economics and industry. In this article we develop a methodology for analysing a periodical and multi-dimensional time series so as to extract new features that improve the performance of time series classification. Our aim is to have a methodology which is independent on the measurement errors and on the level of noise. For this we analyse three methods for extracting a period, both from the perspective of methodology and performance. We experimentally compare these strategies in order to identify the minimal quantity of labelled time series required for training so as to obtain a good classification accuracy.


Time series analysis Fault diagnosis Data mining 


  1. 1.
    Ahmed, N., Natarajan, T., Rao, K.R.: Discrete cosine transform. IEEE. Trans. Comput. 100(1), 90–93 (1974)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Bagnall, A., Bostrom, A., Large, J., Lines, J.: The great time series classification bake off: An experimental evaluation of recently proposed algorithms. extended version (2016)Google Scholar
  3. 3.
    Cardoso, A.M., Cruz, S., Carvalho, J., Saraiva, E.: Rotor cage fault diagnosis in three-phase induction motors, by park’s vector approach. In: IEEE Industry Applications Conference, vol. 1, pp. 642–646. IEEE (1995)Google Scholar
  4. 4.
    Faloutsos, C., Ranganathan, M., Manolopoulos, Y.: Fast subsequence matching in time-series databases, vol. 23. ACM (1994)Google Scholar
  5. 5.
    Fu, T.: A review on time series data mining. Eng. Appl. Artif. Intell. 24(1), 164–181 (2011)CrossRefGoogle Scholar
  6. 6.
    Fulcher, B.D.: Feature-based time-series analysis (2017)Google Scholar
  7. 7.
    Haar, A.: Zur theorie der orthogonalen funktionensysteme 69(3), 331–371 (1910)Google Scholar
  8. 8.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. ACM SIGKDD Explor. Newslett. 11(1), 10–18 (2009)CrossRefGoogle Scholar
  9. 9.
    Hasna, O.L., Potolea, R.: Time series–a taxonomy based survey. In: Intelligent Computer Communication and Processing (ICCP), pp. 231–238. IEEE (2017)Google Scholar
  10. 10.
    Martin-Diaz, I., Morinigo-Sotelo, D., Duque-Perez, O., Osornio-Rios, R.A., Romero-Troncoso, R.J.: Hybrid algorithmic approach oriented to incipient rotor fault diagnosis on induction motors. ISA Trans. 80, 427–438 (2018)CrossRefGoogle Scholar
  11. 11.
    Mitsa, T.: Temporal Data Mining. Chapman and Hall/CRC, Boca Raton (2010)CrossRefGoogle Scholar
  12. 12.
    Nandi, S., Toliyat, H., Li, X.: Condition monitoring and fault diagnosis of electrical motors-a review. IEEE Trans. Energy Convers. 20(4), 719–729 (2005)CrossRefGoogle Scholar
  13. 13.
    Rajakarunakaran, S., Venkumar, P., Devaraj, D., Rao, K.S.P.: Artificial neural network approach for fault detection in rotary system. Appl. Soft Comput. 8(1), 740–748 (2008)CrossRefGoogle Scholar
  14. 14.
    Timmer, J., Gantert, C., Deuschl, G., Honerkamp, J.: Characteristics of hand tremor time series. Biol. Cybern. 70(1), 75–80 (1993)CrossRefGoogle Scholar
  15. 15.
    Wang, X., Mueen, A., Ding, H., Trajcevski, G., Scheuermann, P., Keogh, E.: Experimental comparison of representation methods and distance measures for time series data. Data Min. Knowl. Disc. 26(2), 275–309 (2013)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Xu, B., Sun, L., Xu, L., Xu, G.: Improvement of the hilbert method via esprit for detecting rotor fault in induction motors at low slip. IEEE Trans. Energy Convers. 28(1), 225–233 (2013)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Technical University of Cluj-NapocaCluj-NapocaRomania

Personalised recommendations