Abstract
Time series is a necessary data type in both industrial scenarios and data analysis. In this era of explosive data growth, the significant development of sensors has made it possible to obtain massive amounts of time series data. However, the performance of different algorithms for different types of time series data varies greatly. So how to automatically choose an optimal algorithm for different data becomes the key to improving efficiency and saving resources. However, existing cloud services or open-source frameworks are not easy to use for users with little experience in time series analysis, and the user needs to rely on continuous experimentation to choose an algorithm that best suits his scenario. This significantly reduces the efficiency of data analysis. Thus to address this phenomenon, in this paper we propose an automated time series analysis system Auto-TSA. The biggest advantage over existing methods is that we have designed “Automation mode” so that even first-time users can easily use it. Users can automatically obtain the best-performing algorithm and hyperparameter configuration by entering only their own data. The whole process of automatic algorithm selection and hyperparameter optimization is efficient by introducing historical experience. In addition, we also design “Customization mode” for time series analysis experts, which makes it easier to use and more functional through the excellent and simple interface design. We will describe the framework and workflow of the system in detail, and show some samples to guide users to use it quickly.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Change history
28 September 2023
A correction has been published.
References
Bhatnagar, A., et al.: Merlion: a machine learning library for time series. ar**v preprint ar**v:2109.09265 (2021)
Blázquez-García, A., Conde, A., Mori, U., Lozano, J.A.: A review on outlier/anomaly detection in time series data. ACM Comput. Surv. (CSUR) 54(3), 1–33 (2021)
Christ, M., Braun, N., Neuffer, J., Kempa-Liehr, A.W.: Time series feature extraction on basis of scalable hypothesis tests (tsfresh-a python package). Neurocomputing 307, 72–77 (2018)
Dau, H.A., et al.: The UCR time series archive. IEEE/CAA J. Automatica Sinica 6(6), 1293–1305 (2019)
Dempster, A., Petitjean, F., Webb, G.I.: Rocket: exceptionally fast and accurate time series classification using random convolutional kernels. Data Min. Knowl. Disc. 34(5), 1454–1495 (2020)
Esling, P., Agon, C.: Time-series data mining. ACM Comput. Surv. (CSUR) 45(1), 1–34 (2012)
Hamilton, J.D.: Time Series Analysis. Princeton University Press, Princeton (2020)
Hutter, F., Kotthoff, L., Vanschoren, J.: Automated Machine Learning. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-05318-5
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., Muller, P.A.: Deep learning for time series classification: a review. Data Min. Knowl. Disc. 33(4), 917–963 (2019)
Ismail Fawaz, H., et al.: Inceptiontime: finding alexnet for time series classification. Data Min. Knowl. Disc. 34(6), 1936–1962 (2020)
Kieu, T., Yang, B., Jensen, C.S.: Outlier detection for multidimensional time series using deep neural networks. In: 2018 19th IEEE International Conference on Mobile Data Management (MDM), pp. 125–134. IEEE (2018)
Lim, B., Zohren, S.: Time-series forecasting with deep learning: a survey. Phil. Trans. R. Soc. A 379(2194), 20200209 (2021)
Lines, J., Bagnall, A.: Time series classification with ensembles of elastic distance measures. Data Min. Knowl. Disc. 29(3), 565–592 (2015)
Löning, M., Bagnall, A., Ganesh, S., Kazakov, V., Lines, J., Király, F.J.: sktime: a unified interface for machine learning with time series. ar**v preprint ar**v:1909.07872 (2019)
Lucas, B., et al.: Proximity forest: an effective and scalable distance-based classifier for time series. Data Min. Knowl. Disc. 33(3), 607–635 (2019)
Mu, T., Wang, H., Zheng, S., Zhang, S., Liang, C., Tang, H.: Assassin: an automatic classification system based on algorithm selection. Proc. VLDB Endowment 14(12), 2751–2754 (2021)
Peng, Y., Flach, P.A., Soares, C., Brazdil, P.: Improved dataset characterisation for meta-learning. In: Lange, S., Satoh, K., Smith, C.H. (eds.) DS 2002. LNCS, vol. 2534, pp. 141–152. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-36182-0_14
Pinto, F., Soares, C., Mendes-Moreira, J.: Towards automatic generation of metafeatures. In: Bailey, J., Khan, L., Washio, T., Dobbie, G., Huang, J.Z., Wang, R. (eds.) PAKDD 2016. LNCS (LNAI), vol. 9651, pp. 215–226. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-31753-3_18
Ren, H., et al.: Time-series anomaly detection service at Microsoft. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3009–3017 (2019)
Schaffer, C.: Cross-validation, stacking and bi-level stacking: Meta-methods for classification learning. In: Cheeseman, P., Oldford, R.W. (eds.) Selecting Models from Data, pp. 51–59. Springer, New York (1994). https://doi.org/10.1007/978-1-4612-2660-4_6
Shen, Z., Zhang, Y., Lu, J., Xu, J., **ao, G.: A novel time series forecasting model with deep learning. Neurocomputing 396, 302–313 (2020)
Susto, G.A., Cenedese, A., Terzi, M.: Time-series classification methods: review and applications to power systems data. Big Data Appl. Power Syst. 2018, 179–220 (2018)
Ye, L., Keogh, E.: Time series shapelets: a new primitive for data mining. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 947–956 (2009)
Acknowledgement
This paper was supported by NSFC grant (62232005, 62202126, U1866602) and Sichuan Science and Technology Program (2020YFSY0069). This work was done by the first author during his internship at Hangzhou Huawei Cloud Computing Technologies Co., Ltd. We thank the anonymous reviewers for their valuable review comments.
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 Switzerland AG
About this paper
Cite this paper
Mu, T., Sheng, Z., Zhou, L., Wang, H. (2023). Auto-TSA: An Automatic Time Series Analysis System Based on Meta-learning. In: El Abbadi, A., et al. Database Systems for Advanced Applications. DASFAA 2023 International Workshops. DASFAA 2023. Lecture Notes in Computer Science, vol 13922. Springer, Cham. https://doi.org/10.1007/978-3-031-35415-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-35415-1_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35414-4
Online ISBN: 978-3-031-35415-1
eBook Packages: Computer ScienceComputer Science (R0)