CoChat
Sign Up
Cited by 1,138Time Series Analysis and ForecastingContext-Aware Activity Recognition SystemsStock Market Forecasting Methods

Multivariate LSTM-FCNs for time series classification

Open access
Karim, Fazle, Majumdar, Somshubra, Darabi, Houshang, Harford, Samuel·2019·Neural Networks
DOI 10.1016/j.neunet.2019.04.014
Open this paper in CoChat — free accountOpen PDF

Abstract

Over the past decade, multivariate time series classification has received great attention. We propose transforming the existing univariate time series classification models, the Long Short Term Memory Fully Convolutional Network (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN), into a multivariate time series classification model by augmenting the fully convolutional block with a squeeze-and-excitation block to further improve accuracy. Our proposed models outperform most state-of-the-art models while requiring minimum preprocessing. The proposed models work efficiently on various complex multivariate time series classification tasks such as activity recognition or action recognition. Furthermore, the proposed models are highly efficient at test time and small enough to deploy on memory constrained systems.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.neunet.2019.04.014

Cites

4 of 4 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Multiple-instance configurations limit simultaneously capturing evolving patterns and dependencies of MTS.

    “the limitations in simultaneously capturing the evolving patterns and dependencies of MTS due to the restriction of each instance's hypothesis space to its individual inputs [22,23]”

    From TVGeAN: Tensor Visibility Graph-Enhanced Attention Network for Versatile Multivariant Time Series Learning Tasks (2024) · cites this paper as [22]

    The Introduction (p. 2) describes multivariate time-series methods, including one that finds dependencies between segments, but does not state that multiple-instance configurations limit the simultaneous capture of evolving patterns and dependencies. Searches for the claimed hypothesis-space restriction and for multiple-instance limitations found no passage addressing that point. (LLM, conf=0.72)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 27

  1. [2][2] A. Sharabiani, H. Darabi, A. Rezaei, S. Harford, H. Johnson, F. Karim, Efficient classification of long time series by 3-d dynamic time warping, IEEE Transactions on Systems, Man, and Cybernetics: Systems. -
  2. [6][6] S. Spiegel, J. Gaebler, A. Lommatzsch, E. De Luca, S. Albayrak, Pattern recognition and classification for multivariate time series, in: Proceedings of the fifth international workshop on knowledge discovery from sensor data, ACM, 2011, pp. 34-42. -
  3. [10][10] Y. Fu, Human Activity Recognition and Prediction, Springer, 2015. -
  4. [11][11] P. Geurts, Pattern extraction for time series classification, in: PKDD, Vol. 1, Springer, 2001, pp. 115-127. -
  5. [12][12] V. Pavlovic, B. J. Frey, T. S. Huang, Time-series classification using mixed-state dynamic bayesian networks, in: Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on., Vol. 2, IEEE, 1999, pp. 609-615. -
  6. [15][15] S. Seto, W. Zhang, Y. Zhou, Multivariate time series classification using dynamic time warping template selection for human activity recognition, in: Computational Intelligence, 2015 IEEE Symposium Series on, IEEE, 2015, pp. 1399-1406. -
  7. [16][16] Z. Xing, J. Pei, E. Keogh, A brief survey on sequence classification, ACM Sigkdd Explorations Newsletter 12 (1) (2010) 40-48. -
  8. [17][17] Y. Zheng, Q. Liu, E. Chen, Y. Ge, J. L. Zhao, Time series classification using multi-channels deep convolutional neural networks, in: International Conference on Web-Age Information Management, Springer, 2014, pp. 298-310. -
  9. [18][18] W. Pei, H. Dibeklio˘ glu, D. M. Tax, L. van der Maaten, Multivariate time-series classification using the hidden-unit logistic model, IEEE Transactions on Neural Networks and Learning Systems. -
  10. [19][19] A. Quattoni, S. Wang, L.-P. Morency, M. Collins, T. Darrell, Hidden conditional random fields, IEEE transactions on pattern analysis and machine intelligence 29 (10). -
  11. [20][20] T. Jaakkola, M. Diekhans, D. Haussler, A discriminative framework for detecting remote protein homologies, Journal of computational biology 7 (1-2) (2000) 95-114. -
  12. [21][21] L. Maaten, Learning discriminative fisher kernels, in: Proceedings of the 28th International Conference on Machine Learning (ICML-11), 2011, pp. 217-224. -
  13. [24][24] M. Wistuba, J. Grabocka, L. Schmidt-Thieme, Ultra-fast shapelets for time series classification, arXiv preprint arXiv:1503.05018. - · arXiv
  14. [25][25] M. Cuturi, A. Doucet, Autoregressive kernels for time series, arXiv preprint arXiv:1101.0673. - · arXiv
  15. [27][27] P. Sch¨ afer, U. Leser, Multivariate time series classification with weasel+ muse, arXiv preprint arXiv:1711.11343. - · arXiv
  16. [28][28] R. Pascanu, C. Gulcehre, K. Cho, Y. Bengio, How to Construct Deep Recurrent Neural Networks, arXiv preprint arXiv:1312.6026. - · arXiv
  17. [30][30] A. Graves, et al., Supervised Sequence Labelling with Recurrent Neural Networks, Vol. 385, Springer, 2012. -
  18. [31][31] D. Bahdanau, K. Cho, Y. Bengio, Neural Machine Translation by Jointly Learning to Align and Translate, arXiv preprint arXiv:1409.0473. - · arXiv
  19. [32][32] J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, arXiv preprint arXiv:1709.01507. - · arXiv
  20. [33][33] F. Karim, S. Majumdar, H. Darabi, S. Chen, Lstm fully convolutional networks for time series classification, IEEE Access (2017) 1-7. -
  21. [34][34] Z. Wang, W. Yan, T. Oates, Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline, in: Neural Networks (IJCNN), 2017 International Joint Conference on, IEEE, 2017, pp. 1578-1585. -
  22. [41][41] B. Williams, M. Toussaint, A. J. Storkey, Modelling motion primitives and their timing in biologically executed movements, in: Advances in neural information processing systems, 2008, pp. 1609-1616. -
  23. [42][42] N. Hammami, M. Bedda, Improved tree model for arabic speech recognition, in: Computer Science and Information Technology (ICCSIT), 2010 3rd IEEE International Conference on, Vol. 5, IEEE, 2010, pp. 521-526. -
  24. [44][44] W. Li, Z. Zhang, Z. Liu, Action recognition based on a bag of 3d points, in: Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 IEEE Computer Society Conference on, IEEE, 2010, pp. 9-14. -
  25. [45][45] J. Wang, Z. Liu, Y. Wu, J. Yuan, Mining actionlet ensemble for action recognition with depth cameras, in: Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, IEEE, 2012, pp. 1290-1297. -
  26. [49][49] P. Nemenyi, Distribution-free multiple comparisons, in: Biometrics, Vol. 18, INTERNATIONAL BIOMETRIC SOC 1441 I ST, NW, SUITE 700, WASHINGTON, DC 20005-2210, 1962, p. 263. -
  27. [50][50] Z. ˇ Sid´ ak, Rectangular confidence regions for the means of multivariate normal distributions, Journal of the American Statistical Association 62 (318) (1967) 626-633.

Cited by

Sorted by citations

Authors
Karim, F., Majumdar, S., Darabi, H., & Harford, S.
Affiliations
University of Illinois Chicago (US)
Corresponding author
Darabi, Houshang
ORCID
Venue
Neural Networks
Publisher
Elsevier BV
Published
2019-08
Volume
116
Pages
237-245
ISSN
0893-6080 (ISSN-L)
DOI
10.1016/j.neunet.2019.04.014
OpenAlex
W2783323081
Cited by
1,138
References
4
Citations by year
2026: 136 · 2025: 204 · 2024: 182 · 2023: 178 · 2022: 156 · 2021: 140 · 2020: 100 · 2019: 38 · 2018: 3 · 2017: 1
FWCI
68.64
Type
journal article
Language
en
Open access
Licence
www.elsevier.com/tdm/userlicense/1.0/ (tdm)
Locations
  • Neural Networks (publishedVersion)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
Keywords
multivariate time series classification, squeeze-and-excitation blocks, fully convolutional network, activity recognition, human action recognition, memory-constrained deployment, model efficiency
MeSH terms
Memory, Short-Term, Multivariate Analysis, Neural Networks, Computer, Memory, Long-Term, Interrupted Time Series Analysis

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review