Abstract
Deep neural networks (DNNs) are attractive alternatives to more traditional methods for time series anomaly detection thanks to their capacity to automatically learn discriminative features. Despite their demonstrated power, different works have suggested that introducing engineered features in the time series can further improve the performance. In this work, we present a feature engineering strategy to transform univariate time series into a multivariate one by introducing non-local information in the augmented data. In this way, we aim to address an intrinsic limitation of the features learned by DNNs, which is they rely on local information only. We study the performance of our combination compared to each individual method and show that our method achieves better performance without increasing computational time on a set of 250 univariate time series proposed by the University of California, Riverside at the 2021 KDDCup competition.
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
Similar content being viewed by others
References
Aboagye-Sarfo, P., Mai, Q., Sanfilippo, F.M., Preen, D.B., Stewart, L.M., Fatovich, D.M.: A comparison of multivariate and univariate time series approaches to modelling and forecasting emergency department demand in western australia. J. Biomed. Inform. 57, 62–73 (2015)
Audibert, J., Michiardi, P., Guyard, F., Marti, S., Zuluaga, M.A.: USAD: unsupervised anomaly detection on multivariate time series. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2020, pp. 3395–3404. Association for Computing Machinery, New York (2020)
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)
Carta, S., Podda, A.S., Reforgiato Recupero, D.R., Saia, R.: A local feature engineering strategy to improve network anomaly detection. Future Internet 12(10), 177 (2020)
Domingues, R., Filippone, M., Michiardi, P., Zouaoui, J.: A comparative evaluation of outlier detection algorithms: experiments and analyses. Pattern Recogn. 74, 406–421 (2018)
Fan, C., Xiao, F., Zhao, Y., Wang, J.: Analytical investigation of autoencoder-based methods for unsupervised anomaly detection in building energy data. Appl. Energy 211, 1123–1135 (2018)
Fehst, V., La, H.C., Nghiem, T.D., Mayer, B.E., Englert, P., Fiebig, K.H.: Automatic vs. manual feature engineering for anomaly detection of drinking-water quality. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, GECCO 2018, pp. 5–6. Association for Computing Machinery, New York (2018)
Kale, D.C., et al.: An examination of multivariate time series hashing with applications to health care. In: 2014 IEEE International Conference on Data Mining, pp. 260–269 (2014)
Linardi, M., Zhu, Y., Palpanas, T., Keogh, E.J.: Matrix profile goes mad: variable-length motif and discord discovery in data series. Data Min. Knowl. Disc. 34, 1022–1071 (2020)
Makridakis, S., Spiliotis, E., Assimakopoulos, V.: The M4 competition: 100,000 time series and 61 forecasting methods. Int. J. Forecast. 36(1), 54–74 (2020)
Ouyang, Z., Sun, X., Yue, D.: Hierarchical time series feature extraction for power consumption anomaly detection. In: Li, K., Xue, Y., Cui, S., Niu, Q., Yang, Z., Luk, P. (eds.) LSMS/ICSEE -2017. CCIS, vol. 763, pp. 267–275. Springer, Singapore (2017). https://doi.org/10.1007/978-981-10-6364-0_27
Park, D., Hoshi, Y., Kemp, C.C.: A multimodal anomaly detector for robot-assisted feeding using an LSTM-based variational autoencoder. IEEE Robot. Autom. Lett. 3(3), 1544–1551 (2018)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning Internal Representations by Error Propagation, pp. 318–362. MIT Press, Cambridge (1986)
Soni, A.N.: Feature extraction methods for time series functions using machine learning. Int. J. Innov. Res. Sci. Eng. Technol. 7(8), 8661–8665 (2018)
Theodossiou, P.T.: Predicting shifts in the mean of a multivariate time series process: an application in predicting business failures. J. Am. Stat. Assoc. 88(422), 441–449 (1993)
Yeh, C.M., et al.: Matrix profile I: all pairs similarity joins for time series: a unifying view that includes motifs, discords and shapelets. In: 2016 IEEE 16th International Conference on Data Mining (ICDM), pp. 1317–1322 (2016)
Yeh, C.C.M., Kavantzas, N., Keogh, E.: Matrix profile VI: meaningful multidimensional motif discovery. In: 2017 IEEE International Conference on Data Mining (ICDM), pp. 565–574. IEEE (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Audibert, J., Marti, S., Guyard, F., Zuluaga, M.A. (2021). From Univariate to Multivariate Time Series Anomaly Detection with Non-Local Information. In: Lemaire, V., Malinowski, S., Bagnall, A., Guyet, T., Tavenard, R., Ifrim, G. (eds) Advanced Analytics and Learning on Temporal Data. AALTD 2021. Lecture Notes in Computer Science(), vol 13114. Springer, Cham. https://doi.org/10.1007/978-3-030-91445-5_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-91445-5_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91444-8
Online ISBN: 978-3-030-91445-5
eBook Packages: Computer ScienceComputer Science (R0)
