research-article

Series2Graph: graph-based subsequence anomaly detection for time series

Authors:

Themis PalpanasAuthors Info & Claims

Proceedings of the VLDB Endowment, Volume 13, Issue 12

Pages 1821 - 1834

https://doi.org/10.14778/3407790.3407792

Published: 01 July 2020 Publication History

Abstract

Subsequence anomaly detection in long sequences is an important problem with applications in a wide range of domains. However, the approaches that have been proposed so far in the literature have severe limitations: they either require prior domain knowledge that is used to design the anomaly discovery algorithms, or become cumbersome and expensive to use in situations with recurrent anomalies of the same type. In this work, we address these problems, and propose an unsupervised method suitable for domain agnostic subsequence anomaly detection. Our method, Series2Graph, is based on a graph representation of a novel low-dimensionality embedding of subsequences. Series2Graph needs neither labeled instances (like supervised techniques), nor anomaly-free data (like zero-positive learning techniques), and identifies anomalies of varying lengths. The experimental results, on the largest set of synthetic and real datasets used to date, demonstrate that the proposed approach correctly identifies single and recurrent anomalies without any prior knowledge of their characteristics, outperforming by a large margin several competing approaches in accuracy, while being up to orders of magnitude faster.

References

[1]

Series2Graph Webpage. http://helios.mi.parisdescartes.fr/~themisp/series2graph/, 2020.

[2]

D. Abboud, M. Elbadaoui, W. Smith, and R. Randall. Advanced bearing diagnostics: A comparative study of two powerful approaches. MSSP, 114, 2019.

[3]

A. Abdul-Aziz, M. R. Woike, N. C. Oza, B. L. Matthews, and J. D. lekki. Rotor health monitoring combining spin tests and data-driven anomaly detection methods. Structural Health Monitoring, 2012.

[4]

M. Ali Abdul-Aziz, N. Woike, B. Oza, Matthews, and G. Baakilini. Propulsion health monitoring of a turbine engine disk using spin test data, 2010.

[5]

J. Antoni and P. Borghesani. A statistical methodology for the design of condition indicators. Mechanical Systems and Signal Processing, 2019.

[6]

A. J. Bagnall, R. L. Cole, T. Palpanas, and K. Zoumpatianos. Data series management (dagstuhl seminar 19282). Dagstuhl Reports, 9(7), 2019.

[7]

S. Bahaadini, V. Noroozi, N. Rohani, S. Coughlin, M. Zevin, J. Smith, V. Kalogera, and A. Katsaggelos. Machine learning for gravity spy: Glitch classification and dataset. Information Sciences, 444:172--186, 5 2018.

[8]

V. Barnet and T. Lewis. Outliers in Statistical Data. John Wiley and Sons, Inc., 1994.

[9]

P. Boniol, M. Linardi, F. Roncallo, and T. Palpanas. Automated anomaly detection in large sequences. In ICDE, 2020.

[10]

P. Boniol, M. Linardi, F. Roncallo, and T. Palpanas. SAD: an unsupervised system for subsequence anomaly detection. In ICDE, 2020.

[11]

P. Boniol, T. Palpanas, M. Meftah, and E. Remy. Graphan: Graph-based subsequence anomaly detection. PVLDB, 13(11), 2020.

Digital Library

[12]

L. Bontemps, V. L. Cao, J. McDermott, and N. LeKhac. Collective anomaly detection based on long short term memory recurrent neural network. CoRR, abs/1703.09752, 2017.

[13]

E. Bradley and H. Kantz. Nonlinear time-series analysis revisited. Chaos: An Interdisciplinary Journal of Nonlinear Science, 2015.

[14]

M. M. Breunig, H.-P. Kriegel, R. T. Ng, and J. Sander. Lof: Identifying density-based local outliers. In SIGMOD, 2000.

Digital Library

[15]

Y. Bu, O. T. Leung, A. W. Fu, E. J. Keogh, J. Pei, and S. Meshkin. WAT: finding top-k discords in time series database. In SIAM, 2007.

[16]

B. Y. Chiu, E. J. Keogh, and S. Lonardi. Probabilistic discovery of time series motifs. In SIGKDD 2003, pages 493--498, 2003.

Digital Library

[17]

N. Daouayry, A. Mechouche, P.-L. Maisonneuve, V.-M. Scuturici, and J.-M. Petit. Data-centric helicopter failure anticipation: The mgb oil pressure virtual sensor case. IEEE BigData, 2019.

[18]

K. Echihabi, K. Zoumpatianos, and T. Palpanas. Scalable Machine Learning on High-Dimensional Vectors: From Data Series to Deep Network Embeddings. In WIMS, 2020.

Digital Library

[19]

K. Echihabi, K. Zoumpatianos, T. Palpanas, and H. Benbrahim. The lernaean hydra of data series similarity search: An experimental evaluation of the state of the art. PVLDB, 2019.

Digital Library

[20]

K. Echihabi, K. Zoumpatianos, T. Palpanas, and H. Benbrahim. Return of the Lernaean Hydra: Experimental Evaluation of Data Series Approximate Similarity Search. PVLDB, 2019.

Digital Library

[21]

G. et al. Physiobank, physiotoolkit, and physionet. Circulation.

[22]

Y. Z. et al. Matrix profile II: exploiting a novel algorithm and gpus to break the one hundred million barrier for time series motifs and joins. In ICDM 2016.

[23]

A. W. Fu, O. T. Leung, E. J. Keogh, and J. Lin. Finding time series discords based on haar transform. In ADMA, 2006.

Digital Library

[24]

Z.-K. Gao and N. Jin. Complex network from time series based on phase space reconstruction. Chaos (Woodbury, N. Y.), 19:033137, 09 2009.

[25]

Z.-K. Gao, M. Small, and J. Kurths. Complex network analysis of time series. EPL (Europhysics Letters), 116(5):50001, dec 2016.

[26]

A. Gogolou, T. Tsandilas, K. Echihabi, A. Bezerianos, and T. Palpanas. Data Series Progressive Similarity Search with Probabilistic Quality Guarantees. In SIGMOD, 2020.

Digital Library

[27]

M. Hadjem, F. Naït-Abdesselam, and A. A. Khokhar. St-segment and t-wave anomalies prediction in an ECG data using rusboost. In Healthcom, 2016.

[28]

N. Halko, P. G. Martinsson, and J. A. Tropp. Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions. SIAM Review, 2011.

Digital Library

[29]

S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural Comput., 9(8):1735--1780, Nov. 1997.

Digital Library

[30]

H. Kantz and T. Schreiber. Nonlinear Time Series Analysis. Cambridge University Press, New York, NY, USA, 2003.

Digital Library

[31]

E. Keogh, S. Lonardi, and C. A. Ratanamahatana. Towards parameter-free data mining. In Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '04, pages 206--215, New York, NY, USA, 2004. ACM.

Digital Library

[32]

E. Keogh, S. Lonardi, C. A. Ratanamahatana, L. Wei, S.-H. Lee, and J. Handley. Compression-based data mining of sequential data. Data Mining and Knowledge Discovery, 2007.

Digital Library

[33]

E. J. Keogh, J. Lin, and A. W. Fu. HOT SAX: efficiently finding the most unusual time series subsequence. In ICDM, 2005.

Digital Library

[34]

L. Lacasa, B. Luque, F. Ballesteros, J. Luque, and J. C. Nuno. From time series to complex networks: The visibility graph. Proceedings of the National Academy of Sciences, 105(13):4972--4975, 2008.

[35]

T. Lee, J. Gottschlich, N. Tatbul, E. Metcalf, and S. Zdonik. Greenhouse: A zero-positive machine learning system for time-series anomaly detection. CoRR, abs/1801.03168, 2018.

[36]

M. Linardi, Y. Zhu, T. Palpanas, and E. J. Keogh. Matrix Profile Goes MAD: Variable-Length Motif And Discord Discovery in Data Series. In DAMI, 2020.

[37]

F. T. Liu, K. M. Ting, and Z.-H. Zhou. Isolation forest. In ICDM, ICDM, 2008.

Digital Library

[38]

Y. Liu, X. Chen, and F. Wang. Efficient Detection of Discords for Time Series Stream. Advances in Data and Web Management, pages 629--634, 2009.

Digital Library

[39]

W. Luo and M. Gallagher. Faster and parameter-free discord search in quasi-periodic time series. In J. Z. Huang, L. Cao, and J. Srivastava, editors, Advances in Knowledge Discovery and Data Mining, 2011.

Digital Library

[40]

P. Malhotra, L. Vig, G. Shroff, and P. Agarwal. Long short term memory networks for anomaly detection in time series. 2015.

[41]

K. Mirylenka, A. Marascu, T. Palpanas, M. Fehr, S. Jank, G. Welde, and D. Groeber. Envelope-based anomaly detection for high-speed manufacturing processes. European Advanced Process Control and Manufacturing Conference, 2013.

[42]

G. B. Moody and R. G. Mark. The impact of the mit-bih arrhythmia database. IEEE Engineering in Medicine and Biology Magazine, 2001.

[43]

A. Mueen, E. J. Keogh, Q. Zhu, S. Cash, and M. B. Westover. Exact discovery of time series motifs. In SDM 2009.

[44]

T. Palpanas. Data series management: The road to big sequence analytics. SIGMOD Rec., 44(2):47--52, Aug. 2015.

Digital Library

[45]

T. Palpanas. Evolution of a Data Series Index. CCIS, 1197, 2020.

[46]

T. Palpanas and V. Beckmann. Report on the First and Second Interdisciplinary Time Series Analysis Workshop (ITISA). ACM SIGMOD Record, 48(3), 2019.

Digital Library

[47]

T. Pelkonen, S. Franklin, P. Cavallaro, Q. Huang, J. Meza, J. Teller, and K. Veeraraghavan. Gorilla: A fast, scalable, in-memory time series database. PVLDB, 8(12):1816--1827, 2015.

Digital Library

[48]

B. Peng, P. Fatourou, and T. Palpanas. MESSI: In-Memory Data Series Indexing. In ICDE, 2020.

[49]

B. Peng, T. Palpanas, and P. Fatourou. Paris+: Data series indexing on multi-core architectures. TKDE, 2020.

[50]

D. W. Scott. Multivariate Density Estimation. Theory, Practice, and Visualization. Wiley, 1992.

[51]

P. Senin, J. Lin, X. Wang, T. Oates, S. Gandhi, A. P. Boedihardjo, C. Chen, and S. Frankenstein. Time series anomaly discovery with grammar-based compression. In EDBT, 2015.

[52]

P. Senin, J. Lin, X. Wang, T. Oates, S. Gandhi, A. P. Boedihardjo, C. Chen, and S. Frankenstein. Grammarviz 3.0: Interactive discovery of variable-length time series patterns. TKDD, 2018.

Digital Library

[53]

S. Subramaniam, T. Palpanas, D. Papadopoulos, V. Kalogeraki, and D. Gunopulos. Online outlier detection in sensor data using non-parametric models. In VLDB 2006, pages 187--198, 2006.

Digital Library

[54]

J. Wang, A. Balasubramanian, L. M. de la Vega, J. Green, A. Samal, and B. Prabhakaran. Word recognition from continuous articulatory movement time-series data using symbolic representations. In SLPAT.

[55]

L. Wei, E. J. Keogh, and X. Xi. Saxually explicit images: Finding unusual shapes. In Proceedings of the 6th IEEE International Conference on Data Mining (ICDM 2006), 18--22 December 2006, Hong Kong, China, pages 711--720, 2006.

Digital Library

[56]

C. Whitney, D. Gottlieb, S. Redline, R. Norman, R. Dodge, E. Shahar, S. Surovec, and F. Nieto. Reliability of scoring respiratory disturbance indices and sleep staging. Sleep, November 1998.

[57]

D. Yankov, E. J. Keogh, J. Medina, B. Y. Chiu, and V. B. Zordan. Detecting time series motifs under uniform scaling. In ACM.

[58]

D. Yankov, E. J. Keogh, and U. Rebbapragada. Disk aware discord discovery: Finding unusual time series in terabyte sized datasets. In ICDM, 2007.

Digital Library

[59]

D. Yankov, E. J. Keogh, and U. Rebbapragada. Disk aware discord discovery: finding unusual time series in terabyte sized datasets. Knowl. Inf. Syst., 17(2):241--262, 2008.

Digital Library

[60]

C. M. Yeh, Y. Zhu, L. Ulanova, N. Begum, Y. Ding, H. A. Dau, D. F. Silva, A. Mueen, and E. J. Keogh. Matrix profile I: all pairs similarity joins for time series: A unifying view that includes motifs, discords and shapelets. In ICDM, pages 1317--1322, 2016.

Cited By

Chen HEldardiry H(2024)Graph Time-series Modeling in Deep Learning: A SurveyACM Transactions on Knowledge Discovery from Data10.1145/363853418:5(1-35)Online publication date: 28-Feb-2024
https://dl.acm.org/doi/10.1145/3638534
Liu WMa MWang P(2023)Multi-QueryingInformatica10.15388/23-INFOR51934:3(557-576)Online publication date: 28-Jun-2023
https://dl.acm.org/doi/10.15388/23-INFOR519
Sylligardos EBoniol PPaparrizos JTrahanias PPalpanas T(2023)Choose Wisely: An Extensive Evaluation of Model Selection for Anomaly Detection in Time SeriesProceedings of the VLDB Endowment10.14778/3611479.361153616:11(3418-3432)Online publication date: 24-Aug-2023
https://dl.acm.org/doi/10.14778/3611479.3611536
Show More Cited By

Recommendations

GraphAn: graph-based subsequence anomaly detection

Subsequence anomaly detection in long sequences is an important problem with applications in a wide range of domains. However, the state-of-the-art approaches have severe limitations: they either require prior domain knowledge, or become cumbersome and ...
Unsupervised and scalable subsequence anomaly detection in large data series
Abstract
Subsequence anomaly (or outlier) detection in long sequences is an important problem with applications in a wide range of domains. However, the approaches that have been proposed so far in the literature have severe limitations: they either ...
Multi-scale Anomaly Detection with Wavelets
BDIOT '17: Proceedings of the International Conference on Big Data and Internet of Thing

We present a novel system for the detection of anomalies in streaming timeseries data, particularly that found in server and application monitoring, as well as "Internet of Things" (IoT) sensor monitoring and applications. By using the Discrete Wavelet ...

Comments

Information & Contributors

Information

Published In

cover image Proceedings of the VLDB Endowment

Proceedings of the VLDB Endowment Volume 13, Issue 12

August 2020

1710 pages

ISSN:2150-8097

Editors:
Magdalena Balazinska
University of Washington
,
Xiaofang Zhou
University of Queensland, Australia

Issue’s Table of Contents

Publisher

VLDB Endowment

Publication History

Published: 01 July 2020

Published in PVLDB Volume 13, Issue 12

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

23
Total Citations
View Citations
1,360
Total Downloads

Downloads (Last 12 months)88
Downloads (Last 6 weeks)3

Reflects downloads up to 30 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

Chen HEldardiry H(2024)Graph Time-series Modeling in Deep Learning: A SurveyACM Transactions on Knowledge Discovery from Data10.1145/363853418:5(1-35)Online publication date: 28-Feb-2024
https://dl.acm.org/doi/10.1145/3638534
Liu WMa MWang P(2023)Multi-QueryingInformatica10.15388/23-INFOR51934:3(557-576)Online publication date: 28-Jun-2023
https://dl.acm.org/doi/10.15388/23-INFOR519
Sylligardos EBoniol PPaparrizos JTrahanias PPalpanas T(2023)Choose Wisely: An Extensive Evaluation of Model Selection for Anomaly Detection in Time SeriesProceedings of the VLDB Endowment10.14778/3611479.361153616:11(3418-3432)Online publication date: 24-Aug-2023
https://dl.acm.org/doi/10.14778/3611479.3611536
Paparrizos JWu KElmore AFaloutsos CFranklin M(2023)Accelerating Similarity Search for Elastic Measures: A Study and New Generalization of Lower Bounding DistancesProceedings of the VLDB Endowment10.14778/3594512.359453016:8(2019-2032)Online publication date: 22-Jun-2023
https://dl.acm.org/doi/10.14778/3594512.3594530
Azizi IEchihabi KPalpanas T(2023)ELPIS: Graph-Based Similarity Search for Scalable Data ScienceProceedings of the VLDB Endowment10.14778/3583140.358316616:6(1548-1559)Online publication date: 1-Feb-2023
https://dl.acm.org/doi/10.14778/3583140.3583166
Chatzakis MFatourou PKosmas EPalpanas TPeng B(2023)Odyssey: A Journey in the Land of Distributed Data Series Similarity SearchProceedings of the VLDB Endowment10.14778/3579075.357908716:5(1140-1153)Online publication date: 1-Jan-2023
https://dl.acm.org/doi/10.14778/3579075.3579087
Campos DZhang MYang BKieu TGuo CJensen C(2023)LightTS: Lightweight Time Series Classification with Adaptive Ensemble DistillationProceedings of the ACM on Management of Data10.1145/35893161:2(1-27)Online publication date: 20-Jun-2023
https://dl.acm.org/doi/10.1145/3589316
Wang ZWang QWang PPalpanas TWang W(2023)Dumpy: A Compact and Adaptive Index for Large Data Series CollectionsProceedings of the ACM on Management of Data10.1145/35889651:1(1-27)Online publication date: 30-May-2023
https://dl.acm.org/doi/10.1145/3588965
Yang YZhang CZhou TWen QSun LSingh ASun YAkoglu LGunopulos DYan XKumar ROzcan FYe J(2023)DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly DetectionProceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining10.1145/3580305.3599295(3033-3045)Online publication date: 6-Aug-2023
https://dl.acm.org/doi/10.1145/3580305.3599295
Zhao YChen GJia Z(2022)TODProceedings of the VLDB Endowment10.14778/3570690.357070316:3(546-560)Online publication date: 1-Nov-2022
https://dl.acm.org/doi/10.14778/3570690.3570703
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Issue’s Table of Contents