Advertisement

Data Mining and Knowledge Discovery

, Volume 33, Issue 1, pp 252–291 | Cite as

Exact mean computation in dynamic time warping spaces

  • Markus Brill
  • Till Fluschnik
  • Vincent FroeseEmail author
  • Brijnesh Jain
  • Rolf Niedermeier
  • David Schultz
Article

Abstract

Averaging time series under dynamic time warping is an important tool for improving nearest-neighbor classifiers and formulating centroid-based clustering. The most promising approach poses time series averaging as the problem of minimizing a Fréchet function. Minimizing the Fréchet function is NP-hard and so far solved by several heuristics and inexact strategies. Our contributions are as follows: we first discuss some inaccuracies in the literature on exact mean computation in dynamic time warping spaces. Then we propose an exponential-time dynamic program for computing a global minimum of the Fréchet function. The proposed algorithm is useful for benchmarking and evaluating known heuristics. In addition, we present an exact polynomial-time algorithm for the special case of binary time series. Based on the proposed exponential-time dynamic program, we empirically study properties like uniqueness and length of a mean, which are of interest for devising better heuristics. Experimental evaluations indicate substantial deficits of state-of-the-art heuristics in terms of their output quality.

Keywords

Time series analysis Fréchet function Dynamic programming Exact exponential-time algorithm Empirical evaluation of heuristics 

Notes

Acknowledgements

This work was supported by the Deutsche Forschungsgemeinschaft under Grants JA 2109/4-1 and NI 369/13-2, and by a Feodor Lynen return fellowship of the Alexander von Humboldt Foundation. The work on the theoretical part of this paper started at the research retreat of the Algorithmics and Computational Complexity group, TU Berlin, held at Boiensdorf, Baltic Sea, April 2017, with MB, TF, VF, and RN participating. We also thank the authors of the UCR Time Series Classification Archive for providing the data sets which we used in our experiments.

References

  1. Aach J, Church GM (2001) Aligning gene expression time series with time warping algorithms. Bioinformatics 17(6):495–508CrossRefGoogle Scholar
  2. Abdulla WH, Chow D, Sin G (2003) Cross-words reference template for DTW-based speech recognition systems. In: Proceedings of the IEEE conference on convergent technologies for the Asia-Pacific region (TENCON 2003), vol 4. IEEE, pp 1576–1579Google Scholar
  3. Aghabozorgi S, Shirkhorshidi AS, Wah TY (2015) Time-series clustering—a decade review. Inf Syst 53:16–38CrossRefGoogle Scholar
  4. Alon J, Athitsos V, Yuan Q, Sclaroff S (2009) A unified framework for gesture recognition and spatiotemporal gesture segmentation. IEEE Trans Pattern Anal Mach Intell 31(9):1685–1699CrossRefGoogle Scholar
  5. Blondel M (2017) Python implementation of soft-DTW. https://github.com/mblondel/soft-dtw
  6. Bonizzoni P, Della Vedova G (2001) The complexity of multiple sequence alignment with SP-score that is a metric. Theor Comput Sci 259(1–2):63–79MathSciNetCrossRefzbMATHGoogle Scholar
  7. Bringmann K, Künnemann M (2015) Quadratic conditional lower bounds for string problems and dynamic time warping. In: Proceedings of the 56th annual IEEE symposium on foundations of computer science (FOCS ’15). IEEE, pp 79–97Google Scholar
  8. Bulteau L, Froese V, Niedermeier R (2018) Tight hardness results for consensus problems on circular strings and time series. CoRR arXiv:1804.02854
  9. Chen Y, Keogh E, Hu B, Begum N, Bagnall A, Mueen A, Batista G (2015) The UCR time series classification archive. www.cs.ucr.edu/~eamonn/time_series_data/
  10. Clarke FH (1990) Optimization and nonsmooth analysis. SIAM, PhiladelphiaCrossRefzbMATHGoogle Scholar
  11. Cuturi M, Blondel M (2017) Soft-DTW: a differentiable loss function for time-series. In: Proceedings of the 34th international conference on machine learning (ICML ’17), PMLR, proceedings of machine learning research, vol 70, pp 894–903Google Scholar
  12. Cuturi M, Vert JP, Birkenes O, Matsui T (2007) A kernel for time series based on global alignments. In: Acoustics, speech and signal processing, 2007. ICASSP 2007. IEEE international conference on, vol 2. IEEE, pp 2–413Google Scholar
  13. Dolan E, Moré J (2002) Benchmarking optimization software with performance profiles. Math Program 91(2):201–213MathSciNetCrossRefzbMATHGoogle Scholar
  14. Fahiman F, Bezdek JC, Erfani SM, Leckie C, Palaniswami M (2017) Fuzzy c-Shape: a new algorithm for clustering finite time series waveforms. In: Proceeding of the 2017 IEEE international conference on fuzzy systems (FUZZ-IEEE). IEEE, pp 1–8Google Scholar
  15. Fréchet M (1948) Les éléments aléatoires de nature quelconque dans un espace distancié. Ann Inst Henri Poincaré 10:215–310zbMATHGoogle Scholar
  16. Fu T (2011) A review on time series data mining. Eng Appl Artif Intell 24(1):164–181CrossRefGoogle Scholar
  17. Gold O, Sharir M (2018) Dynamic time warping and geometric edit distance: breaking the quadratic barrier. ACM Trans Algorithms 14(4):50:1–50:17MathSciNetCrossRefGoogle Scholar
  18. Gupta L, Molfese DL, Tammana R, Simos PG (1996) Nonlinear alignment and averaging for estimating the evoked potential. IEEE Trans Biomed Eng 43(4):348–356CrossRefGoogle Scholar
  19. Gusfield D (1997) Algorithms on strings, trees and sequences. Cambridge University Press, CambridgeCrossRefzbMATHGoogle Scholar
  20. Hautamaki V, Nykanen P, Franti P (2008) Time-series clustering by approximate prototypes. In: Proceedings of the 19th international conference on pattern recognition (ICPR ’08). IEEE, pp 1–4Google Scholar
  21. Huang B, Kinsner W (2002) ECG frame classification using dynamic time warping. In: Canadian conference on electrical and computer engineering (CCECE), vol 2. IEEE, pp 1105–1110Google Scholar
  22. Jain B, Schultz D (2017) Optimal warping paths are unique for almost every pair of time series. CoRR arXiv:1705.05681
  23. Jain B, Schultz D (2018) On the existence of a sample mean in dynamic time warping spaces. CoRR arXiv:1610.04460v3
  24. Keogh EJ, Pazzani MJ (2001) Derivative dynamic time warping. In: Proceedings of the 2001 SIAM international conference on data mining. SIAM, Philadelphia, pp 1–11Google Scholar
  25. Lummis R (1973) Speaker verification by computer using speech intensity for temporal registration. IEEE Trans Audio Electroacoust 21(2):80–89CrossRefGoogle Scholar
  26. Marteau PF (2018) Times series averaging and denoising from a probabilistic perspective on time-elastic kernels. Int J Appl Math Comput Sci. arXiv:1611.09194
  27. Moon TK (1996) The expectation-maximization algorithm. IEEE Signal Process Mag 13(6):47–60CrossRefGoogle Scholar
  28. Morel M, Achard C, Kulpa R, Dubuisson S (2018) Time-series averaging using constrained dynamic time warping with tolerance. Pattern Recogn 74:77–89CrossRefGoogle Scholar
  29. Myers CS, Rabiner LR (1981) A comparative study of several dynamic time-warping algorithms for connected-word recognition. Bell Syst Tech J 60(7):1389–1409CrossRefGoogle Scholar
  30. Nicolas F, Rivals E (2005) Hardness results for the center and median string problems under the weighted and unweighted edit distances. J Discrete Algorithms 3(2):390–415MathSciNetCrossRefzbMATHGoogle Scholar
  31. Niennattrakul V, Ratanamahatana CA (2007) Inaccuracies of shape averaging method using dynamic time warping for time series data. In: International conference on computational science. Springer, Berlin, pp 513–520Google Scholar
  32. Niennattrakul V, Ratanamahatana CA (2009) Shape averaging under time warping. In: Shi Y, van Albada GD, Dongarra J, Sloot P (eds) Proceedings of the 6th international conference on electrical engineering/electronics, computer, telecommunications and information technology (ECTI-CON ’09), vol 02, pp 626–629Google Scholar
  33. Oates T, Firoiu L, Cohen PR (1999) Clustering time series with hidden Markov models and dynamic time warping. In: Proceedings of the IJCAI’99 workshop on neural, symbolic and reinforcement learning methods for sequence learning, pp 17–21Google Scholar
  34. Paparrizos J, Gravano L (2017) Fast and accurate time-series clustering. ACM Trans Database Syst 42(2):8:1–8:49MathSciNetCrossRefGoogle Scholar
  35. Petitjean F, Gançarski P (2012) Summarizing a set of time series by averaging: from Steiner sequence to compact multiple alignment. Theor Comput Sci 414(1):76–91MathSciNetCrossRefzbMATHGoogle Scholar
  36. Petitjean F, Ketterlin A, Gançarski P (2011) A global averaging method for dynamic time warping, with applications to clustering. Pattern Recogn 44(3):678–693CrossRefzbMATHGoogle Scholar
  37. Petitjean F, Forestier G, Webb GI, Nicholson AE, Chen Y, Keogh E (2014) Dynamic time warping averaging of time series allows faster and more accurate classification. In: Proceeding of the 2014 IEEE international conference on data mining (ICDM’14). IEEE, pp 470–479Google Scholar
  38. Petitjean F, Forestier G, Webb GI, Nicholson AE, Chen Y, Keogh E (2016) Faster and more accurate classification of time series by exploiting a novel dynamic time warping averaging algorithm. Knowl Inf Syst 47(1):1–26CrossRefGoogle Scholar
  39. Rabiner L, Wilpon J (1979) Considerations in applying clustering techniques to speaker-independent word recognition. J Acoust Soc Am 66(3):663–673CrossRefGoogle Scholar
  40. Reyes M, Dominguez G, Escalera S (2011) Feature weighting in dynamic timewarping for gesture recognition in depth data. In: Proceedings of the 2011 IEEE international conference on computer vision workshops (ICCV Workshops). IEEE, pp 1182–1188Google Scholar
  41. Sakoe H, Chiba S (1978) Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans Acoust Speech Signal Process 26(1):43–49CrossRefzbMATHGoogle Scholar
  42. Sankoff D, Kruskal J (1999) Time warps, string edit and macromolecules: the theory and practice of sequence comparison. CSLI Publications, StanfordGoogle Scholar
  43. Schultz D, Jain BJ (2016) Sample mean algorithms for averaging in dynamic time warping spaces.  https://doi.org/10.5281/zenodo.216233
  44. Schultz D, Jain B (2018) Nonsmooth analysis and subgradient methods for averaging in dynamic time warping spaces. Pattern Recogn 74(Supplement C):340–358CrossRefGoogle Scholar
  45. Soheily-Khah S, Douzal-Chouakria A, Gaussier E (2015) Progressive and iterative approaches for time series averaging. In: Proceedings of the 1st international conference on advanced analytics and learning on temporal data, vol 1425, pp 111–117Google Scholar
  46. Soheily-Khah S, Douzal-Chouakria A, Gaussier E (2016) Generalized \(k\)-means-based clustering for temporal data under weighted and kernel time warp. Pattern Recogn Lett 75:63–69CrossRefGoogle Scholar
  47. Sun T, Liu H, Yu H, Chen CP (2017) Degree-pruning dynamic programming approaches to central time series minimizing dynamic time warping distance. IEEE Trans Cybern 47(7):1719–1729CrossRefGoogle Scholar
  48. Zhao J, Itti L (2018) shapeDTW. Pattern Recogn 74(C):171–184CrossRefGoogle Scholar

Copyright information

© The Author(s), under exclusive licence to Springer Science+Business Media LLC, part of Springer Nature 2018

Authors and Affiliations

  • Markus Brill
    • 1
  • Till Fluschnik
    • 2
  • Vincent Froese
    • 2
    Email author
  • Brijnesh Jain
    • 3
  • Rolf Niedermeier
    • 2
  • David Schultz
    • 3
  1. 1.Efficient AlgorithmsTU BerlinBerlinGermany
  2. 2.Algorithmics and Computational ComplexityTU BerlinBerlinGermany
  3. 3.Distributed Artificial Intelligence LaboratoryTU BerlinBerlinGermany

Personalised recommendations