Skip to main content
SpringerLink
Log in

Multivariate time-series classification using memory and attention for long and short-term dependence\(^{\star }\)

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Time series classification (TSC) is one of the most challenging research topics in data mining, and can finds its wide applications in biomedical engineering and clinical prediction. In recent years, deep learning (DL) has shown impressive performance in TSC research due to its end-to-end capabilities. In contrast to univariate TSC (UTSC), multivariable TSC (MTSC) is more prevalent and its effectiveness depends on long and short-term dependencies to a certain degree. However, mainstream DL models mainly construct various complex frameworks to extract features, and with the over-fitting problem. This paper proposes a comprehensive DL structure, namely the Multivariable Multi-Scale Attention Gated Cycle Unit Fully Convolutional Network (MMAGRU-FCN), which can effectively address the long and short-term dependence in MTSC by integrating memory and attention mechanisms at multiple scales. The proposed model can achieve adaptive characteristic calibration and capture significant features simultaneously. Extensive experiments demonstrate the superior performance of our model over state-of-the-art DL networks in terms of faster convergence, better stability, and in the case that parameters are close to the minimum threshold of comparison. Moreover, the proposed model consistently achieves the highest classification accuracy across different time series lengths. Finally, we verify the performance of the proposed model for various classification scenarios.

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
Algorithm 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Anand A, Padmanabhan V (2013) Time series qlet: Invariant approach for data mining. in: 2013 Sixth International Conference on Contemporary Computing (IC3), pp. 24–29

  2. Rajkomar A, Oren E, Chen K et al. (2018) Scalable and accurate deep learning with electronic health records. npj Dig Med 1:18

  3. Nweke HF, Teh YW, Al-Garadi MA, Alo UR (2018) Deep learning algorithms for human activity recognition using mobile and wearable sensor networks: State of the art and research challenges. Exp Syst Appl 105:233–261

    Article  Google Scholar 

  4. Wang J, Chen Y, Hao S, Peng X, Hu L (2019) Deep learning for sensor-based activity recognition: A survey. Pattern Recognit Lett 119:3–11

    Article  Google Scholar 

  5. Nwe TL, Dat TH, Ma B (2017) Convolutional neural network with multi-task learning scheme for acoustic scene classification. in: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1347–1350

  6. Susto GA, Cenedese A, Terzi M (2018) Time-series classification methods: Review and applications to power systems data. Big Data Appl Power Syst 179–220

  7. Anwar T, Liu C, Vu HL, Islam MS, Sellis T (2018) Capturing the spatiotemporal evolution in road traffic networks. IEEE Trans Knowl Data Eng 30:1426–1439

    Article  Google Scholar 

  8. Pei W, Dibeklioğlu H, Tax DM, van der Maaten L (2017) Multivariate time-series classification using the hidden-unit logistic model. IEEE Trans Neural Netw Learn Syst 29:920–931

    Article  Google Scholar 

  9. He C, Huo X, Gao H (2023) FT-FVC: fast transformation-based feature vector concatenation for time series classification. Appl Intell 53:17778–17795

    Article  Google Scholar 

  10. Zhang W, Wan Y (2022) Early classification of time series based on trend segmentation and optimization cost function. Appl Intell 52:6782–6793

    Article  Google Scholar 

  11. Jastrzebska A, Nápoles G, Homenda W, Vanhoof K (2023) Fuzzy cognitive map-driven comprehensive time-series classification. IEEE Trans Cybernet 53:1348–1359

    Article  Google Scholar 

  12. Chen J, Wan Y, Wang X et al (2022) Learning-based shapelets discovery by feature selection for time series classification. Appl Intell 52:9460–9475

    Article  Google Scholar 

  13. Herrmann M, Tan CW, Webb GI (2023) Parameterizing the cost function of dynamic time warping with application to time series classification. Data Min Knowl Discov 1–22

  14. Ruiz AP, Flynn M, Large J et al (2021) The great multivariate time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min Knowl Discov 35:401–449

    Article  MathSciNet  Google Scholar 

  15. Wang K, Wang C, Wang Y, Luo W, Zhan P, Hu Y, Li X (2021) Time series classification via enhanced temporal representation learning. in: 2021 IEEE 6th International Conference on Big Data Analytics (ICBDA), pp. 188–192

  16. Du M, Wei Y, Zheng X, Ji C (2023) Multi-feature based network for multivariate time series classification. Inf Sci 639:119009

    Article  Google Scholar 

  17. Hssayni EH, Joudar NE, Ettaouil M (2022) A deep learning framework for time series classification using normal cloud representation and convolutional neural network optimization. Comput Intell 38:2056–2074

    Article  Google Scholar 

  18. Fauvel K, Lin T, Masson V, Fromont É, Termier A (2021) Xcm: An explainable convolutional neural network for multivariate time series classification. Math 9:3137

    Article  Google Scholar 

  19. Qian B, Xiao Y, Zheng Z, Zhou M, Zhuang W, Li S, Ma Q (2020) Dynamic multi-scale convolutional neural network for time series classification. IEEE Access 8:109732–109746

    Article  Google Scholar 

  20. Guo Z, Liu P, Yang J, Hu Y (2020) Multivariate time series classification based on MCNN-LSTMs network. in: Proceedings of the 2020 12th International Conference on Machine Learning and Computing (ICMLC 2020). Association for Computing Machinery, New York, NY, USA, pp. 510–517

  21. Ouyang K, Hou Y, Zhou S, Zhang Y (2021) Convolutional neural network with an elastic matching mechanism for time series classification. Algorithms 14:192

    Article  Google Scholar 

  22. Zhang Y, Mo C, Ma J, Zhao L (2021) Random subspace ensembles of fully convolutional network for time series classification. Appl Sci 11:10957

    Article  Google Scholar 

  23. Wang Z, Yan W, Oates T (2017) Time series classification from scratch with deep neural networks: A strong baseline. in: 2017 International joint conference on neural networks (IJCNN), pp. 1578–1585

  24. Liu CL, Hsaio W, Tu YC (2019) Time series classification with multivariate convolutional neural network. IEEE Trans Ind Electron 66:4788–4797

    Article  Google Scholar 

  25. Assaf R, Giurgiu I, Bagehorn F, Schumann A (2019) Mtex-cnn: Multivariate time series explanations for predictions with convolutional neural networks. IEEE Int Conf Data Min (ICDM) 2019:952–957

    Google Scholar 

  26. Zou X, Wang Z, Li Q, Sheng W (2019) Integration of residual network and convolutional neural network along with various activation functions and global pooling for time series classification. Neurocomput 367:39–45

    Article  Google Scholar 

  27. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nat 323:533–536

    Google Scholar 

  28. Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735–1780

    Article  Google Scholar 

  29. Karim F, Majumdar S, Darabi H, Harford S (2019) Multivariate lstm-fcns for time series classification. Neural Netw 116:237–245

  30. Zheng W, Zhao P, Huang K, Chen G (2021) Understanding the property of long term memory for the lstm with attention mechanism. in: Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pp. 2708–2717

  31. Tripathi AM, Baruah RD (2020) Multivariate time series classification with an attention-based multivariate convolutional neural network. Int Joint Conf Neural Netw (IJCNN) 2020:1–8

    Google Scholar 

  32. Cheng X, Han P, Li G, Chen S, Zhang H (2020) A novel channel and temporal-wise attention in convolutional networks for multivariate time series classification. IEEE Access 8:212247–212257

    Article  Google Scholar 

  33. Chen W, Shi K (2021) Multi-scale attention convolutional neural network for time series classification. Neural Netw: Offic J Int Neural Netw Soc 136:126–140

    Article  Google Scholar 

  34. Gong X, Si YW, Tian Y, Lin C, Zhang X, Liu X (2022) KDCTime: Knowledge distillation with calibration on InceptionTime for time-series classification. Inf Sci 613:184–203

    Article  Google Scholar 

  35. Azar J, Makhoul A, Couturier R (2020) Using densenet for iot multivariate time series classification. IEEE Symp Comput Commun (ISCC) 2020:1–6

    Google Scholar 

  36. Längkvist M, Karlsson L, Loutfi A (2014) A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recognit Lett 42:11–24

    Article  Google Scholar 

  37. Szegedy C, Liu W, Jia Y, Sermanet P, Reed SE, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015:1–9

    Google Scholar 

  38. Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958

    MathSciNet  Google Scholar 

  39. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536

    Article  Google Scholar 

  40. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778

  41. Zhang X, Gao Y, Lin J, Lu CT (2020) Tapnet: Multivariate time series classification with attentional prototypical network. Proceedings of the AAAI Conference on Artificial Intelligence 34:6845–6852

  42. Ismail Fawaz H, Lucas B, Forestier G, Pelletier C, Schmidt DF, Weber J, Webb GI, Idoumghar L, Muller PA, Petitjean F (2020) Inceptiontime: Finding alexnet for time series classification. Data Min Knowl Discov 34:1936–1962

  43. Zerveas G, Jayaraman S, Patel D, Bhamidipaty A, Eickhoff C (2021) A transformer-based framework for multivariate time series representation learning. in: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 2114–2124

  44. Wang Z, Yan W, Oates T (2017) Time series classification from scratch with deep neural networks: A strong baseline. in: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 1578–1585

  45. Dau HA, Bagnall AJ, Kamgar K, Yeh C-CM, Zhu Y, Gharghabi S, Ratanamahatana C, Keogh EJ (2019) The ucr time series archive. IEEE/CAA J Automatica Sinica 6:1293–1305

    Article  Google Scholar 

  46. Bagnall A, Dau HA, Lines J, Flynn M, Large J, Bostrom A, Southam P, Keogh E (2018) The uea multivariate time series classification archive, 2018. arXiv:1811.00075

  47. He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. IEEE Int Conf Comput Vision (ICCV) 2015:1026–1034

    Google Scholar 

  48. Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. CoRR abs/1412.6980

  49. Chollet F (2018) Keras: The python deep learning library

  50. Ballabio D, Grisoni F, Grisoni F, Todeschini R (2017) Multivariate comparison of classification performance measures. Chemom Intell Lab Syst 174:33–44

    Article  Google Scholar 

Download references

Acknowledgements

This work is supported by Fundamental Research Funds for the Central Universities (No. XDJK2020B033).

Author information

Authors and Affiliations

  1. College of Artificial Intelligence, Southwest University, Tiansheng Road No.2, 400715, Chongqing, China

    Jianjun Yuan, Fujun Wu & Hong Wu

Authors
  1. Jianjun Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fujun Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hong Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Jianjun Yuan, Fujun Wu or Hong Wu.

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yuan, J., Wu, F. & Wu, H. Multivariate time-series classification using memory and attention for long and short-term dependence\(^{\star }\). Appl Intell 53, 29677–29692 (2023). https://doi.org/10.1007/s10489-023-05079-1

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-023-05079-1

Keywords

Search

Navigation