Abstract
In this paper, we study a challenging problem of mining data generating rules and state transforming rules (i.e., semantics) underneath multiple correlated time series streams. A novel Correlation field-based Semantics Learning Framework (CfSLF) is proposed to learn the semantic. In the framework, we use Hidden Markov Random Field (HMRF) method to model relationship between latent states and observations in multiple correlated time series to learn data generating rules. The transforming rules are learned from corresponding latent state sequence of multiple time series based on Markov chain character. The reusable semantics learned by CfSLF can be fed into various analysis tools, such as prediction or anomaly detection. Moreover, we present two algorithms based on the semantics, which can later be applied to next-n step prediction and anomaly detection. Experiments on real world data sets demonstrate the efficiency and effectiveness of the proposed method.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Zhang, C., Weng, N., Chang, J., Zhou, A.: Detecting Abnormal Trend Evolution over Multiple Data Streams. In: Chen, L., Liu, C., Zhang, X., Wang, S., Strasunskas, D., Tomassen, S.L., Rao, J., Li, W.-S., Candan, K.S., Chiu, D.K.W., Zhuang, Y., Ellis, C.A., Kim, K.-H. (eds.) WCMT 2009. LNCS, vol. 5731, pp. 285–296. Springer, Heidelberg (2009)
Zhang, P., Gao, B.J., Liu, P., Shi, Y., Guo, L.: A framework for application-driven classification of data streams. Neurocomputing 92, 170–182 (2012)
Papadimitriou, S., Sun, J., Faloutsos, C.: Streaming Pattern Discovery in Multiple Time-Series. In: Proceedings of VLDB 2005 (2005)
Chan, P.K., Mahoney, M.V.: Modeling Multiple Time Series for Anomaly Detection. In: Proceedings of ICDM
Hirose, S., Yamanishi, K., Nakata, T., Fujimaki, R.: ]Network Anomaly Detection based on Eigen Equation Compression. In: Proceedings of SIGKDD 2009 (2009)
Qiao, Z., He, J., Cao, J., Huang, G., Zhang, P.: Multiple Time Series Anomaly Detection Based on Compression and Correlation Analysis: A Medical Surveillance Case Study. In: Sheng, Q.Z., Wang, G., Jensen, C.S., Xu, G. (eds.) APWeb 2012. LNCS, vol. 7235, pp. 294–305. Springer, Heidelberg (2012)
Fujimaki, R., Nakata, T., Tsukahara, H., Sato, A., Yamanishi, K.: Mining Abnormal Patterns from Heterogeneous Time-Series with Irrelevant Features for Fault Event Detection. Statistical Analysis and Data Mining 2 (2009)
Zhang, P., Gao, B.J., Zhu, X., Guo, L.: Enabling Fast Lazy Learning for Data Streams. In: Proceedings of ICDM (2011)
Zhang, P., Zhu, X., Shi, Y., Guo, L., Wu, X.: Robust ensemble learning for mining noisy data streams. Decision Support Systems 50(2), 469–479 (2011)
Stock, J.H., Watson, M.W.: Vector Autoregressions. Journal of Economic Perspectives 15(4), 101–115
Yves, N.: Total Least Squares: State-of-the-Art Regression in Numerical Analysis. SIAM Review 36 (2), 258–264
Wang, P., Wang, H., Wang, W.: Finding Semantics in Time Series. In: Proceedings of SIGMOD 2011 (2011)
Duncan, G., Gorr, W., Szczypula, J.: Forecasting Analogous Time Series, pp. 15213–13890. Carnegie Mellon University, Pittsburgh
Pang, C., Zhang, Q., Hansen, D.P., Maeder, A.J.: Unrestricted wavelet synopses under maximum error bound. In: Proceedings of EDBT 2009 (2009)
Keogh, E., Chu, S., Hart, D., Pazzani, M.: An online algorithm for segmenting time series. In: Proceedings of ICDM 2001 (2001)
Wang, Y., Zhou, L.: Mining complex time-series data by learning the temporal structure using bayesian techniques and markovian models. In: Proceedings of ICDM 2006 (2006)
Zhang, P., Li, J., Wang, P., Gao, B., Zhu, X., Guo, L.: Enabling Fast Prediction for Ensemble Models on Data Streams. In: Proceedings of SIGKDD 2011 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Qiao, Z. et al. (2013). Discovering Semantics from Multiple Correlated Time Series Stream. In: Pei, J., Tseng, V.S., Cao, L., Motoda, H., Xu, G. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2013. Lecture Notes in Computer Science(), vol 7819. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37456-2_43
Download citation
DOI: https://doi.org/10.1007/978-3-642-37456-2_43
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37455-5
Online ISBN: 978-3-642-37456-2
eBook Packages: Computer ScienceComputer Science (R0)