research-article

Deep r -th Root of Rank Supervised Joint Binary Embedding for Multivariate Time Series Retrieval

Authors:

Dacheng TaoAuthors Info & Claims

KDD '18: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining

Pages 2229 - 2238

https://doi.org/10.1145/3219819.3220108

Published: 19 July 2018 Publication History

Abstract

Multivariate time series data are becoming increasingly common in numerous real world applications, e.g., power plant monitoring, health care, wearable devices, automobile, etc. As a result, multivariate time series retrieval, i.e., given the current multivariate time series segment, how to obtain its relevant time series segments in the historical data (or in the database), attracts significant amount of interest in many fields. Building such a system, however, is challenging since it requires a compact representation of the raw time series which can explicitly encode the temporal dynamics as well as the correlations (interactions) between different pairs of time series (sensors). Furthermore, it requires query efficiency and expects a returned ranking list with high precision on the top. Despite the fact that various approaches have been developed, few of them can jointly resolve these two challenges. To cope with this issue, in this paper we propose a Deep r-th root of Rank Supervised Joint Binary Embedding (Deep r-RSJBE) to perform multivariate time series retrieval. Given a raw multivariate time series segment, we employ Long Short-Term Memory (LSTM) units to encode the temporal dynamics and utilize Convolutional Neural Networks (CNNs) to encode the correlations (interactions) between different pairs of time series (sensors). Subsequently, a joint binary embedding is pursued to incorporate both the temporal dynamics and the correlations. Finally, we develop a novel r-th root ranking loss to optimize the precision at the top of a Hamming distance ranking list. Thoroughly empirical studies based upon three publicly available time series datasets demonstrate the effectiveness and the efficiency of Deep r-RSJBE.

Supplementary Material

MP4 File (song_time_series_retrieval.mp4)

Download
332.39 MB

References

[1]

A. Andoni and P. Indyk . 2008. Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. Commun. ACM Vol. 51, 1 (2008), 117--122.

Digital Library

[2]

M. Azzouzi and I.T. Nabney . 1998. Analysing time series structure with Hidden Markov Models Proc. of the IEEE Conference on Neural Networks and Signal Processing. 402--408.

[3]

A. Bagnall, C. Ratanamahatana, E. Keogh, S. Lonardi, and J. Gareth . 2006. "A bit level representation for time series data mining with shape based similarity". Data Mining and Knowledge Discovery Vol. 13, 1 (2006), 11--40.

Digital Library

[4]

D. Berndt and Clifford J. . 1994. Using dynamic time warping to find patterns in time series AAAI-94 Workshop on Knowledge Discovery in Databases. 359--370.

Digital Library

[5]

A. Z. Broder, M. Charikar, A. M. Frieze, and M. Mitzenmacher . 1998. Min-wise independent permutations. In Proc. of ACM Symposium on Theory of Computing.

Digital Library

[6]

Y. Cao, M. Long, J. Wang, Q. Yang, and P. S. Yu . 2016. Deep visual-semantic hashing for cross-modal retrieval KDD. 1445--1454.

Digital Library

[7]

K. Chan and A. W. Fu . 1999. Efficient time series matching by wavelets. In ICDE. 126--133.

Digital Library

[8]

L. Chen and Ng R. . 2004. On the marriage of Lp-norms and edit distance. In VLDB. 792--803.

Digital Library

[9]

L. Chen, M. T. Özsu, and V. Oria . 2005. Robust and fast similarity search for moving object trajectories SIGMOD. 491--502.

Digital Library

[10]

K. Cho, B. Van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio . 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv:1406.1078 (2014).

[11]

H. Ding, G. Trajcevski, P. Scheuermann, X. Wang, and E. Keogh . 2008. Querying and mining of time series data: experimental comparison of representations and distance measures. In VLDB. 1542--1552.

Digital Library

[12]

C. Faloutsos, M. Ranganathan, and Y. Manolopoulos . 1994. Fast subsequence matching in time-Series databases SIGMOD. 419--429.

Digital Library

[13]

E. Fink, K.B. Pratt, and H.S. Gandhi . 2003. Indexing of time series by major minima and maxima Proc. of the IEEE International Conference on Systems, Man, and Cybernetics. 2332--2335.

[14]

H. Gjoreski, M. Ciliberto, F. J. Ordoñez Morales, D. Roggen, S. Mekki, and S. Valentin . 2017. A versatile annotated dataset for multimodal locomotion analytics with mobile devices Proc. ACM Conference on Embedded Networked Sensor Systems.

Digital Library

[15]

Y. Gong, S. Lazebnik, A. Gordo, and F. Perronnin . 2012. Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans. on Pattern Analysis and Machine Intelligence (2012).

Digital Library

[16]

Sepp H. and Jürgen S. . 1997. Long short-term memory. Neural Computation Vol. 9, 8 (1997), 1735--1780.

Digital Library

[17]

D. Hallac, S. Vare, S. Boyd, and J. Leskovec . 2017. Toeplitz inverse covariance-based clustering of multivariate time series data KDD. 215--223.

Digital Library

[18]

K. He, X. Zhang, S. Ren, and J. Sun . 2016. Deep residual learning for image recognition. In CVPR.

[19]

G. Jiang, H. Chen, and Yoshihira K. . 2007. Efficient and scalable algorithms for inferring invariants in distributed system. IEEE Transactions on Knowledge and Data Engineering Vol. 19, 11 (2007), 1508--1523.

Digital Library

[20]

S. S. Jones, R. S. Evans, T. L. Allen, A. Thomas, P. J. Haug, S. J. Welch, and G. L. Snow . 2009. A multivariate time series approach to modeling and forecasting demand in the emergency department. Journal of Biomedical Informatics Vol. 42, 1 (2009), 123--139.

Digital Library

[21]

D. C. Kale, D. Gong, Z. Che, G. Medioni, R. Wetzel, P. Ross, and Y. Liu . 2014. An examination of multivariate time Series hashing with applications to health care ICDM.

Digital Library

[22]

E. Keogh, Chakrabarti, M. K., Pazzani, and S. Mehrotra . 2001. Locally adaptive dimensionality reduction for indexing large time series databases SIGMOD. 151--162.

Digital Library

[23]

E. Keogh, K. Chakrabarti, M. Pazzani, and S. Mehrotra . 2000. "Dimensionality reduction for fast similarity search in large time series Databases". KAIS Vol. 3, 3 (2000), 263--286.

[24]

S.-W. Kim, S. Park, and W. W. Chu . 2001. An index-based approach for similarity search supporting time warping in large sequence databases. In ICDE. 607--614.

Digital Library

[25]

D. Kingma and J. Ba . 2014. Adam: a method for stochastic optimization. arXiv:1412.6980 (2014).

[26]

A. Krizhevsky . 2009. Learning multiple layers of features from tiny images Technical report.

[27]

W.-J. Li, S. Wang, and W.-C. Kang . 2016. Feature learning based deep supervised hashing with pairwise Labels IJCAI.

Digital Library

[28]

W. Liu, J. Wang, R. Ji, Y.-G. Jiang, and S.-F. Chang . 2012. Supervised hashing with kernels. In CVPR.

[29]

C. Luo and A. Shrivastava . 2016. SSH (Sketch, shingle, $&$ hash) for indexing massive-scale time series NIPS 2016 Time Series Workshop. 38--58.

[30]

M. Norouzi, D. J. Fleet, and R. Salakhutdinov . 2012. Hamming distance metric learning. In NIPS.

Digital Library

[31]

J. Parkka, M. Ermes, Korpipaa P., Mantyjarvi J., and Peltola J. . 2006. Activity classification using realistic data from wearable sensors. IEEE Transactions on Information Technology in Biomedicine Vol. 6883 (2006), 119--128.

Digital Library

[32]

P. Prickett, G. Davies, and Grosvenor R. . 2011. A SCADA based power plant monitoring and management system. Knowledge-Based and Intelligent Information and Engineering Systems Vol. 6883 (2011), 433--442.

Digital Library

[33]

Y. Qin, D. Song, H. Chen, W. Cheng, G. Jiang, and G. Cottrell . 2017. A dual-stage attention-based recurrent neural network for time series prediction IJCAI. 2627--2633.

Digital Library

[34]

T. Rakthanmanon, B. Campana, A. Mueen, G. Batista, B. Westover, Q. Zhu, J. Zakaria, and E. Keogh . 2012. Searching and mining trillions of time series subsequences under dynamic time warping KDD. 262--270.

Digital Library

[35]

A. Reiss and D. Stricker . 2012. Introducing a new benchmarked dataset for activity monitoring Proc. of the 16th IEEE International Symposium on Wearable Computers (ISWC).

Digital Library

[36]

F. Shen, C. Shen, W. Liu, and H. T. Shen . 2015. Supervised discrete hashing. In CVPR. 37--45.

[37]

J. Shieh and E. Keogh . 2008. iSAX: indexing and mining terabyte sized time series KDD. 623--631.

Digital Library

[38]

K Simonyan and A. Zisserman . 2015. Very deep convolutional networks for large-scale image recognition ICLR.

[39]

S. W. Smith . 1999. The discrete fourier transform. In The Scientist and Engineer's Guide to Digital Signal Processing (Second ed.). California Technical Publishing, California, Chapter 8.

[40]

D. Song, W. Liu, and D. A. Meyer . 2016. Fast structural binary coding. In IJCAI. 2018--2024.

Digital Library

[41]

D. Song, W. Liu, D. A. Meyer, R. Ji, and J. R. Smith . 2015 a. Top rank supervised binary coding for fast image search ICCV. 1922--1930.

Digital Library

[42]

D. Song, W. Liu, D. A. Meyer, D. Tao, and R. Ji . 2015 b. Rank preserving hashing for rapid image search. In DCC. 353--362.

Digital Library

[43]

D. Song, D. A. Meyer, and D. Tao . 2015 c. Top-k link recommendation in social networks. In ICDM. 389--398.

Digital Library

[44]

I. Sutskever, O. Vinyals, and Q. Le . 2014. Sequence to sequence learning with neural networks NIPS. 3104--3112.

Digital Library

[45]

N. Usunier, D. Buffoni, and P. Gallinari . 2009. Ranking with ordered weighted pairwise classification ICML. 1057--1064.

Digital Library

[46]

M. Vlachos, G. Kollios, and G. Gunopulos . 2002. Discovering similar multidimensional trajectories. In ICDE. 673--684.

Digital Library

[47]

Y. Weiss, A. Torralba, and R. Fergus . 2008. Spectral Hashing. In NIPS.

Digital Library

[48]

J. Weston, S. Bengio, and N. Usunier . 2012. Large scale image annotation: learning to rank with joint world-image embeddings. Machine Learning Vol. 81, 1 (2012), 21--35.

Digital Library

[49]

R. Xia, Y. Pan, Lai H., C. Liu, and S. Yan . 2014. Supervised hashing via image representation learning AAAI.

Digital Library

[50]

B.-K. Yi and C. Faloutsos . 2000. Fast time sequence indexing for arbitrary Lp norms VLDB. 385--394.

Digital Library

[51]

F. Zheng, G. Zhang, and Z. Song . 2001. "Comparison of different implementations of MFCC". Journal of Computer Science $&$ Technology Vol. 16, 6 (2001), 582--589.

Digital Library

Cited By

Le TVu HPonchet-Durupt ABoudaoud NCherfi-Boulanger ZNguyen-Trang T(2024)Unsupervised detecting anomalies in multivariate time series by Robust Convolutional LSTM Encoder–Decoder (RCLED)Neurocomputing10.1016/j.neucom.2024.127791592(127791)Online publication date: Aug-2024
https://doi.org/10.1016/j.neucom.2024.127791
Wang KHe DChen GYuan XWang YYang C(2024)Reordered short-term autocorrelation-driven long-range discriminative convolutional autoencoder for dynamic process monitoringJournal of Process Control10.1016/j.jprocont.2024.103176135(103176)Online publication date: Mar-2024
https://doi.org/10.1016/j.jprocont.2024.103176
Müller NBao KMatthes JHeussen K(2023)CyPhERS: A Cyber-Physical Event Reasoning System providing real-time situational awareness for attack and fault responseSSRN Electronic Journal10.2139/ssrn.4453200Online publication date: 2023
https://doi.org/10.2139/ssrn.4453200
Show More Cited By

Index Terms

Deep r -th Root of Rank Supervised Joint Binary Embedding for Multivariate Time Series Retrieval
1. Information systems
  1. Information retrieval
    1. Retrieval models and ranking
      1. Learning to rank
    2. Search engine architectures and scalability
      1. Search index compression
2. Mathematics of computing
  1. Probability and statistics
    1. Statistical paradigms
      1. Time series analysis

Recommendations

Deep convolutional learning for Content Based Image Retrieval

In this paper we propose a model retraining method for learning more efficient convolutional representations for Content Based Image Retrieval. We employ a deep CNN model to obtain the feature representations from the activations of the convolutional ...
Image Retrieval Using Fused Deep Convolutional Features

This paper proposes an image retrieval using fused deep convolutional features to solve the semantic gap between low-level features and high-level semantic features of traditional contend-based image retrieval method. Firstly, the improved network ...
Content-based image retrieval with compact deep convolutional features

Convolutional neural networks (CNNs) with deep learning have recently achieved a remarkable success with a superior performance in computer vision applications. Most of CNN-based methods extract image features at the last layer using a single CNN ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

KDD '18: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining

July 2018

2925 pages

ISBN:9781450355520

DOI:10.1145/3219819

General Chairs:
Yike Guo
Imperial College London
,
Faisal Farooq
IBM

Copyright © 2018 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 19 July 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

KDD '18

Sponsor:

KDD '18: The 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

August 19 - 23, 2018

London, United Kingdom

Acceptance Rates

KDD '18 Paper Acceptance Rate 107 of 983 submissions, 11%;

Overall Acceptance Rate 1,133 of 8,635 submissions, 13%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

32
Total Citations
View Citations
1,612
Total Downloads

Downloads (Last 12 months)42
Downloads (Last 6 weeks)2

Reflects downloads up to 03 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Le TVu HPonchet-Durupt ABoudaoud NCherfi-Boulanger ZNguyen-Trang T(2024)Unsupervised detecting anomalies in multivariate time series by Robust Convolutional LSTM Encoder–Decoder (RCLED)Neurocomputing10.1016/j.neucom.2024.127791592(127791)Online publication date: Aug-2024
https://doi.org/10.1016/j.neucom.2024.127791
Wang KHe DChen GYuan XWang YYang C(2024)Reordered short-term autocorrelation-driven long-range discriminative convolutional autoencoder for dynamic process monitoringJournal of Process Control10.1016/j.jprocont.2024.103176135(103176)Online publication date: Mar-2024
https://doi.org/10.1016/j.jprocont.2024.103176
Müller NBao KMatthes JHeussen K(2023)CyPhERS: A Cyber-Physical Event Reasoning System providing real-time situational awareness for attack and fault responseSSRN Electronic Journal10.2139/ssrn.4453200Online publication date: 2023
https://doi.org/10.2139/ssrn.4453200
Bamford TColetta AFons EGopalakrishnan SVyetrenko SBalch TVeloso M(2023)Multi-Modal Financial Time-Series Retrieval Through Latent Space ProjectionsProceedings of the Fourth ACM International Conference on AI in Finance10.1145/3604237.3626901(498-506)Online publication date: 27-Nov-2023
https://dl.acm.org/doi/10.1145/3604237.3626901
Yeh CChen HDai XZheng YWang JLai VFan YDer AZhuang ZWang LZhang WPhillips JFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)An Efficient Content-based Time Series Retrieval SystemProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3614655(4909-4915)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3614655
Yu RXiao FWang ZYang JHan DWang ZJin MLi CDong EXia S(2023)Anomaly Detection in Heterogeneous Time Series Data for Server-Monitoring Tasks2023 IEEE Symposium on Computers and Communications (ISCC)10.1109/ISCC58397.2023.10218155(1280-1286)Online publication date: 9-Jul-2023
https://doi.org/10.1109/ISCC58397.2023.10218155
Yeh CChen HDai XZheng YFan YLai VWang JDer AZhuang ZWang LZhang W(2023)Temporal Treasure Hunt: Content-based Time Series Retrieval System for Discovering Insights2023 IEEE International Conference on Big Data (BigData)10.1109/BigData59044.2023.10386668(1994-1997)Online publication date: 15-Dec-2023
https://doi.org/10.1109/BigData59044.2023.10386668
Song YXin RChen PZhang RChen JZhao Z(2023)Identifying performance anomalies in fluctuating cloud environments: A robust correlative-GNN-based explainable approachFuture Generation Computer Systems10.1016/j.future.2023.03.020145(77-86)Online publication date: Aug-2023
https://doi.org/10.1016/j.future.2023.03.020
Müller NBao KMatthes JHeussen K(2023)CyPhERSComputers in Industry10.1016/j.compind.2023.103982151:COnline publication date: 29-Aug-2023
https://dl.acm.org/doi/10.1016/j.compind.2023.103982
Kuo CYing J(2023)An Unsupervised Deep Learning Framework for Anomaly DetectionIntelligent Information and Database Systems10.1007/978-981-99-5834-4_23(284-295)Online publication date: 5-Sep-2023
https://doi.org/10.1007/978-981-99-5834-4_23
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 Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents