Abstract
Representation learning of time series is common in tasks like data mining and improves performance in downstream tasks. However, existing methods aren’t appropriate for streaming time series due to two main limitations: first, The efficiency of representation learning methods can be a concern when dealing with streaming time series. Secondly, most of representation learning are designed for timestamp-level representation. They cannot reveal the semantic information in time series, which further reduces the efficiency and effectiveness of representation learning of streaming time series. This study introduces an unsupervised method tailored for streaming time series, considering semantic information. Specifically, it integrates recursive covariance estimation into a simplified transformer structure, PoolFormer, to enhance efficiency and reveal real-time semantic information. In addition, a novel unsupervised method is designed to learning the representation of streaming time series. The experiments show that this method outperforms other representation methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lawi, A., Mesra, H., Amir, S.: Implementation of long short-term memory and gated recurrent units on grouped time-series data to predict stock prices accurately. J. Big Data 9, 1–19 (2022)
Tseng, K., Li, J., Tang, Y., Yang, C., Lin, F.: Healthcare knowledge of relationship between time series electrocardiogram and cigarette smoking using clinical records. BMC Med. Inform. Decis. Mak. 20, 1–11 (2020)
Imani, S., Keogh, E.: Matrix profile XIX: time series semantic motifs: a new primitive for finding higher-level structure in time series. In: 2019 IEEE International Conference on Data Mining (ICDM), pp. 329–338 (2019)
Ye, C., Ma, Q.: GP-HLS: Gaussian process-based unsupervised high-level semantics representation learning of multivariate time series. In: Wang, X., et al. (eds.) DASFAA 2023. LNCS, vol. 13943, pp. 221–236. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-30637-2_15
Lehman, E., Krishnan, R., Zhao, X., Mark, R., Li-Wei, H.: Representation learning approaches to detect false arrhythmia alarms from ECG dynamics. In: Machine Learning for Healthcare Conference, pp. 571–586 (2018)
Sun, Y., Li, J., Liu, J., Sun, B., Chow, C.: An improvement of symbolic aggregate approximation distance measure for time series. Neurocomputing 138, 189–198 (2014)
Kitaev, N., Kaiser, Ł., Levskaya, A.: Reformer: the efficient Transformer. arXiv Preprint arXiv:2001.04451 (2020)
Choromanski, K., et al.: Rethinking attention with performers. arXiv Preprint arXiv:2009.14794 (2020)
Yu, W., et al.: Metaformer is actually what you need for vision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10819–10829 (2022)
Li, G., Choi, B., Xu, J., Bhowmick, S., Chun, K., Wong, G.: Shapenet: a shapelet-neural network approach for multivariate time series classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 8375–8383 (2021)
Hallac, D., Nystrup, P., Boyd, S.: Greedy Gaussian segmentation of multivariate time series. Adv. Data Anal. Classif. 13, 727–751 (2019)
Chen, Y., Fang, W., Dai, S., Lu, C.: Skeleton moving pose-based human fall detection with sparse coding and temporal pyramid pooling. In: 2021 7th International Conference on Applied System Innovation (ICASI), pp. 91–96 (2021)
Zeiler, M., Fergus, R.: Stochastic pooling for regularization of deep convolutional neural networks. arXiv Preprint arXiv:1301.3557 (2013)
Bifet, A., Maniu, S., Qian, J., Tian, G., He, C., Fan, W.: Streamdm: advanced data mining in spark streaming. In: 2015 IEEE International Conference on Data Mining Workshop (ICDMW), pp. 1608–1611 (2015)
Bagnall, A., et al.: The UEA multivariate time series classification archive, 2018. arXiv Preprint arXiv:1811.00075 (2018)
Oregi, I., Pérez, A., Del Ser, J., Lozano, J.: An active adaptation strategy for streaming time series classification based on elastic similarity measures. Neural Comput. Appl. 34, 13237–13252 (2022)
Oregi, I., Pérez, A., Del Ser, J., Lozano, J.A.: On-line dynamic time warping for streaming time series. In: Ceci, M., Hollmén, J., Todorovski, L., Vens, C., Džeroski, S. (eds.) ECML PKDD 2017. LNCS (LNAI), vol. 10535, pp. 591–605. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-71246-8_36
Chen, Y., Hu, B., Keogh, E., Batista, G.: DTW-D: time series semi-supervised learning from a single example. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 383–391 (2013)
Yue, Z., et al.: Ts2Vec: towards universal representation of time series. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 8980–8987 (2022)
Ding, Y., Luo, W., Zhao, Y., Li, Z., Zhan, P., Li, X.: A novel similarity search approach for streaming time series. J. Phys: Conf. Ser. 1302, 022084 (2019)
Lian, X., Chen, L., Yu, J., Wang, G., Yu, G.: Similarity match over high speed time-series streams. In: 2007 IEEE 23rd International Conference on Data Engineering, pp. 1086–1095 (2006)
Luo, W., et al.: Multi-resolution representation for streaming time series retrieval. Int. J. Pattern Recognit. Artif. Intell. 35, 2150019 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ye, C., Ma, Q. (2023). Unsupervised Representation Learning with Semantic of Streaming Time Series. In: Zhang, F., Wang, H., Barhamgi, M., Chen, L., Zhou, R. (eds) Web Information Systems Engineering – WISE 2023. WISE 2023. Lecture Notes in Computer Science, vol 14306. Springer, Singapore. https://doi.org/10.1007/978-981-99-7254-8_64
Download citation
DOI: https://doi.org/10.1007/978-981-99-7254-8_64
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7253-1
Online ISBN: 978-981-99-7254-8
eBook Packages: Computer ScienceComputer Science (R0)