Unsupervised Retrieval Based Multivariate Time Series Anomaly Detection and Diagnosis with Deep Binary Coding Models

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Sep 4, 2023
Takehiko Mizoguchi Yuji Kobayashi Yasuhiro Ajiro

Abstract

Retrieval based multivariate time series anomaly detection and diagnosis refer to identifying abnormal status in certain time steps and pinpointing the root cause input variables, i.e., sensors, by comparing a current time series segment and its relevant ones that are retrieved from huge amount of historical data. Binary coding with a deep neural network can be applied to reduce the computational cost of the retrieval tasks. However, it is hard to pinpoint the root cause sensors that are responsible for the anomaly, once multivariate time series segments are transformed into binary codes. In this paper, we present an unsupervised retrieval based multivariate time series anomaly detection and diagnosis method with deep binary coding model, to secure both efficiency and explainability. Specifically, we first transform input multivariate time series segments into low dimensional features with a temporal encoder. Subsequently, two hash functions predict two binary codes with different lengths from each feature. The binary codes with two different lengths can contribute to accelerate both anomaly detection and anomaly diagnosis. Experiments performed on datasets from various domains including real optical network, demonstrate the effectiveness and efficiency of the proposed method.

Abstract 228 | PDF Downloads 227

##plugins.themes.bootstrap3.article.details##

Keywords

anomaly detection, fault diagnosis, multivariate time series retrieval, binary coding, deep neural network

References
Chakrabarti, K., Keogh, E., Mehrotra, S., & Pazzani, M. (2002, Jan.). Locally adaptive dimensionality reduction for indexing large time series databases. ACM Trans. Database Systems, 27(2), 188–228.

Chen, X., Li, B., Shamsabardeh, M., Proietti, R., Zhu, Z., & Yoo, S. J. B. (2018). On real-time and self-taught anomaly detection in optical networks using hybrid unsupervised/supervised learning. In Proc. Euro. Conf. Optic. Comm.

Cho, K., Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder–decoder for statistical machine translation. In Proc. Conf. Emp. Meth. Nat. Lang. Process.

Gong, Y., Lazebnik, S., Gordo, A., & Perronnin, F. (2013, Dec.). Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans. Pat. Anal. Mach. Intel., 25(12), 2916– 2928.

Hochreiter, S., & Schmidhuber, J. (1997, Nov.). Long shortterm memory. Neural Computation, 9(8), 1735–1780.

Lai, H., Pan, Y., Liu, Y., & Yan, S. (2015). Simultaneous feature learning and hash coding with deep neural networks. In Proc. IEEE Conf. Comp. Vis. Patt. Recog.

Manevitz, L. M., & Yousef, M. (2002, Mar.). One-class svms for document classification. J. Mach. Learn. Res., 2, 139–154.

N. Kalchbrenner, P. B., E. Grefenstette. (2014). A convolutional neural network for modelling sentences. In Proc. Assoc. Comp. Ling.

Rakthanmanon, T., Campana, B., Mueen, A., Batista, G., Westover, B., Zhu, Q., . . . Keogh, E. (2012). Searching and mining trillions of time series subsequences under dynamic time warping. In Proc. ACM SIGKDD Conf. Knowl. Discov. Data Min.

Reiss, A., & Stricker, D. (2012). Introducing a new benchmarked dataset for activity monitoring. In Proc. Int’l Symp. Wear. Comp.

Schafer, P., Ermshaus, A., & Leser, U. (2021). ClaSP - Time ¨ Series Segmentation. In Proc. Conf. Inf. Knowl. Manage.

Schroff, F., Kalenichenko, D., & Philbin, J. (2015). Facenet: Aunified embedding for face recognition and clustering. In Proc. IEEE Conf. Comp. Vis. Patt. Recog.

Song, D., Xia, N., Cheng, W., Chen, H., & Tao, D. (2018). Deep r-th root of rank supervised joint binary embedding for multivariate time series retrieval. In Proc. ACM SIGKDD Conf. Knowl. Discov. Data Min.

Sprint, G., Cook, D., Weeks, D., Dahmen, J., & Fleur, A. (2017, Oct.). Analyzing sensor-based time series data to track changes in physical activity during inpatient rehabilitation. Sensors, 17(10).

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., . . . Polosukhin, I. (2017). Attention is all you need. In Proc. Neural Inf. Process. Syst.

Yang, H.-F., Lin, K., & Chen, C.-S. (2018, Feb.). Supervised learning of semantics-preserving hash via deep convolutional neural networks. IEEE Trans. Pat. Anal. Mach. Intel., 40(2), 437–451.

Zhu, D., Song, D., Chen, Y., Lumezanu, C., Cheng, W., Zong, B., . . . T. Yang, H. C. (2020). Deep unsupervised binary coding networks for multivariate time series retrieval. In Proc. AAAI Conf. Artif. Intel
Section
Regular Session Papers