Skip to main content
SpringerLink
Log in

Temporal representation learning for time series classification

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Recent years have witnessed the exponential growth of time series data as the popularity of sensing devices and development of IoT techniques; time series classification has been considered as one of the most challenging studies in time series data mining, attracting great interest over the last two decades. According to the empirical evidences, temporal representation learning-based time series classification has more superiority of accuracy, efficiency and interpretability as compared to hundreds of existing time series classification methods. However, due to the high time complexity of feature process, the performance of these methods has been severely restricted. In this paper, we first presented an efficient shapelet transformation method to improve the overall efficiency of time series classification, and then, we further developed a novel enhanced recurrent neural network model for deep representation learning to further improve the classification accuracy. Experimental results on typical real-world datasets have justified the superiority of our models over several shallow and deep representation learning competitors.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Anthony B, Jason L, Jon H, Aaron B (2015) Time-series classification with cote: the collective of transformation-based ensembles. IEEE Trans Knowl Data Eng 27:2522–2535

    Article  Google Scholar 

  2. Anthony B, Jason L, William V, Eamonn K (2016) The uea & ucr time series classification repository. www.timeseriesclassification.com

  3. Anthony B, Jason L, Aaron B, James L, Eamonn K (2017) The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min Knowl Disc 31:606–660

    Article  MathSciNet  Google Scholar 

  4. Chaoran C, Jun M, Tao L, Zhumin C, Shuaiqiang W (2015) Improving image annotation via ranking-oriented neighbor search and learning-based keyword propagation. J Assoc Inf Sci Technol 66:82–98

    Article  Google Scholar 

  5. Chaoran C, Jialie S, Liqiang N, Richang H, Jun M (2017) Augmented collaborative filtering for sparseness reduction in personalized poi recommendation. ACM Trans Intell Syst Technol 8:1–23

    Google Scholar 

  6. Chaoran C, Huihui L, Tao L, Liqiang N, Lei Z, Yilong Y (2019) Distribution-oriented aesthetics assessment with semantic-aware hybrid network. IEEE Trans Multim 21:1209–1220

    Article  Google Scholar 

  7. Cun J, Chao Z, Shijun L, Chenglei Y, Li P, Lei W, Xiangxu M (2019) A fast shapelet selection algorithm for time series classification. Comput Netw 148:231–240

    Article  Google Scholar 

  8. Dan S, Lei Z, Yikun L, Jingjing L, Xiushan N (2019) Robust structured graph clustering. IEEE Trans Neural Netw Learn Syst. https://doi.org/10.1109/TNNLS.2019.2955209

    Article  Google Scholar 

  9. Daniel G, Danny H, Lior R (2015) Fast and space-efficient shapelets-based time-series classification. Intell Data Anal 19:953–981

    Article  Google Scholar 

  10. Fazle K, Somshubra M, Houshang D (2019) Insights into lstm fully convolutional networks for time series classification. IEEE Access 7:67718–67725

    Article  Google Scholar 

  11. Grabocka J, Schilling N, Wistuba M, Schmidt-Thieme L (2014) Learning time-series shapelets. In: International conference on Knowledge discovery and data mining, pp 392–401

  12. Grabocka J, Wistuba M, Schmidt-Thieme L (2016) Fast classification of univariate and multivariate time series through shapelet discovery. Knowl Inf Syst 49:429–454

    Article  Google Scholar 

  13. Isak K, Panagiotis P, Henrik B (2016) Generalized random shapelet forests. Data Min Knowl Disc 30:1053–1085

    Article  MathSciNet  Google Scholar 

  14. Jason L, Luke MD, Jon H, Anthony B (2012) A shapelet transform for time series classification. In: International conference on Knowledge discovery and data mining, pp 289–297

  15. Jason L, Sarah T, Anthony B (2016) Hive-cote: the hierarchical vote collective of transformation-based ensembles for time series classification. In: International conference on data mining

  16. Jingjing L, Ke L, Zi H, Lei Z, Hengtao S (2019) Heterogeneous domain adaptation through progressive alignment. IEEE Trans Neural Netw 30:1381–1391

    Article  MathSciNet  Google Scholar 

  17. Jingjing L, Ke L, Zi H, Lei Z, Hengtao S (2019) Transfer independently together: a generalized framework for domain adaptation. IEEE Trans Cybern 49:2144–2155

    Article  Google Scholar 

  18. Jon H, Jason L, Edgaras B, James M, Anthony B (2014) Classification of time series by shapelet transformation. Data Min Knowl Disc 28:851–881

    Article  MathSciNet  Google Scholar 

  19. Lexiang Y, Eamonn K (2009) Time series shapelets: a new primitive for data mining. In: International conference on Knowledge discovery and data mining, pp 947–956

  20. Lexiang Y, Eamonn K (2011) Time series shapelets: a novel technique that allows accurate, interpretable and fast classification. Data Min Knowl Disc 22:149–182

    Article  MathSciNet  Google Scholar 

  21. Mit S, Josif G, Nicolas S, Martin W, Lars S (2016) Learning DTW-shapelets for time-series classification. In: International conference on data science

  22. Mueen A, Keogh E, Young N (2011) Logical-shapelets: an expressive primitive for time series classification. In: International conference on Knowledge discovery and data mining, pp 1154–1162

  23. Qi Z, Yupeng H, Cun J, Peng Z, Xueqing L (2018) Edge computing application: real-time anomaly detection algorithm for sensing data. J Comput Res Dev 55:524–536

    Google Scholar 

  24. Qing H, Zhi D, Fuzhen Z, Tianfeng S, Zhongzhi S (2012) Fast time series classification based on infrequent shapelets. In: International conference on machine learning and applications. IEEE, pp 215–219

  25. Sangdi L, George CR (2018) GCRNN: group-constrained convolutional recurrent neural network. IEEE Trans Neural Netw 29:4709–4718

    Article  Google Scholar 

  26. Thanawin R, Eamonn K (2013) Fast shapelets: a scalable algorithm for discovering time series shapelets. In: International conference on data mining, pp 668–676

  27. Xavier R, Maria R, Walid E, Marcin D (2015) Random-shapelet: an algorithm for fast shapelet discovery. In: International conference on data science and advanced analytics, pp 1–10

  28. Yudong H, Lei Z, Zhiyong C, Jingjing L, Xiaobai L (2020) Discrete optimal graph clustering. IEEE Trans Cybern 50:1697–1710

    Article  Google Scholar 

  29. Yupeng H, Cun J, Ming J, Xueqing L (2016) A k-motifs discovery approach for large time-series data analysis. In: Asia-pacific web conference, pp 492–496

  30. Yupeng H, Cun J, Ming J, Yiming D, Shuo K, Xueqing L (2016) A continuous segmentation algorithm for streaming time series. In: International conference on collaborative computing: networking, applications and worksharing, pp 140–151

  31. Yupeng H, Cun J, Qingke Z, Lin C, Peng Z, Xueqing L (2019) A novel multi-resolution representation for time series sensor data analysis. Soft Comput: 1–26

  32. Yupeng H, Peiyuan G, Peng Z, Yiming D, Xueqing L (2019b) A novel segmentation and representation approach for streaming time series. IEEE Access 7:184423–184437

    Article  Google Scholar 

  33. Yupeng H, Pengjie R, Wei L, Peng Z, Xueqing L (2019c) Multi-resolution representation with recurrent neural networks application for streaming time series in iot. Comput Netw 152:114–132

    Article  Google Scholar 

  34. Zhiguang W, Weizhong Y, Tim O (2017) Time series classification from scratch with deep neural networks: a strong baseline. In: International joint conference on neural networks, pp 1578–1585

  35. Zhiyong C, Xiaojun C, Lei Z, Catherine Rose K, Mohan SK (2019) MMALFM: explainable recommendation by leveraging reviews and images. ACM Trans Inf Syst 37:16:1–16:28

    Google Scholar 

Download references

Acknowledgements

The authors would like to thank the anonymous reviewers and the editors for their insightful comments and suggestions, which are greatly helpful for improving the quality of this paper. This work is supported by the National Natural Science Foundation of China, Nos.: 61772310, 61702300, 61702302, 61802231; the Key Research and Development Program of China, Nos.: 2017YFC0803400, 2018YFC0831000; the project of CERNET Innovation (NGII20190109); and the project of Qingdao Postdoctoral Applied Research.

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Shandong University, Qingdao, 266237, Shandong, China

    Yupeng Hu

  2. School of Information Science and Engineering, Shandong Normal University, Jinan, 250358, Shandong, China

    Yang Xu

  3. School of Information Science and Engineering, Shandong University, Qingdao, 266237, Shandong, China

    Jia Zhao & Yujun Li

  4. School of Software, Shandong University, Jinan, 250101, Shandong, China

    Peng Zhan & Xueqing Li

Authors
  1. Yupeng Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Peng Zhan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yang Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jia Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yujun Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Xueqing Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yujun Li.

Ethics declarations

Conflict of interest

All authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Informed consent

Informed consent was obtained from all individual participants included in the study.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hu, Y., Zhan, P., Xu, Y. et al. Temporal representation learning for time series classification. Neural Comput & Applic 33, 3169–3182 (2021). https://doi.org/10.1007/s00521-020-05179-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-020-05179-w

Keywords

Search

Navigation