research-article

Efficient and Effective Similar Subtrajectory Search: A Spatial-aware Comprehension Approach

Authors:

Han SuAuthors Info & Claims

ACM Transactions on Intelligent Systems and Technology (TIST), Volume 13, Issue 3

Article No.: 35, Pages 1 - 22

https://doi.org/10.1145/3456723

Published: 13 April 2022 Publication History

Abstract

Although many applications take subtrajectories as basic units for analysis, there is little research on the similar subtrajectory search problem aiming to return a portion of a trajectory (i.e., subtrajectory), which is the most similar to a query trajectory. We find that in some special cases, when a grid-based metric is used, this problem can be formulated as a reading comprehension problem, which has been studied extensively in the field of natural language processing (NLP). By this formulation, we can obtain faster models with better performance than existing methods. However, due to the difference between natural language and trajectory (e.g., spatial relationship), it is impossible to directly apply NLP models to this problem. Therefore, we propose a Similar Subtrajectory Search with a Graph Neural Networks framework. This framework contains four modules including a spatial-aware grid embedding module, a trajectory embedding module, a query-context trajectory fusion module, and a span prediction module. Specifically, in the spatial-aware grid embedding module, the spatial-based grid adjacency is constructed and delivered to the graph neural network to learn spatial-aware grid embedding. The trajectory embedding module aims to model the sequential information of trajectories. The purpose of the query-context trajectory fusion module is to fuse the information of the query trajectory to each grid of the context trajectories. Finally, the span prediction module aims to predict the start and the end of a subtrajectory for the context trajectory, which is the most similar to the query trajectory. We conduct comprehensive experiments on two real world datasets, where the proposed framework outperforms the state-of-the-art baselines consistently and significantly.

References

[1]

P. Agarwal, K. Fox, K. Munagala, A. Nath, J. Pan, and E. Taylor. 2018. Subtrajectory clustering: Models and algorithms. In SIGMOD/PODS (2018).

[2]

H. Alt and M. Godau. 1995. Computing the Fréchet distance between two polygonal curves. Int. J. Comput. Geom. Appl. 5 (1995), 75–91.

[3]

P. Baldi, S. Brunak, P. Frasconi, G. Soda, and G. Pollastri. 1999. Exploiting the past and the future in protein secondary structure prediction. Bioinformatics 15, 11 (1999), 937–46.

[4]

K. Buchin, M. Buchin, J. Gudmundsson, M. Löffler, and J. Luo. 2011. Detecting commuting patterns by clustering subtrajectories. Int. J. Comput. Geom. Appl. 21 (2011), 253–282.

[5]

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

Digital Library

[6]

L. Chen, M. Özsu, and V. Oria. 2005. Robust and fast similarity search for moving object trajectories. In SIGMOD.

[7]

Y. Cui, L. Deng, Y. Zhao, B. Yao, V. W. Zheng, and K. Zheng. 2019. Hidden POI ranking with spatial crowdsourcing. In SIGKDD. 814–824.

[8]

J. Devlin, M. Chang, K. Lee, and K. Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT.

[9]

R. H. Güting and M. Schneider. 2005. Realm-based spatial data types: The ROSE algebra. Proc. VLDB 4 (2005), 243–286.

Digital Library

[10]

X. He, K. Deng, X. Wang, Y. Li, Y. Zhang, and M. Wang. 2020. LightGCN: Simplifying and powering graph convolution network for recommendation. In SIGIR (2020).

Digital Library

[11]

S. Kanda, K. Takeuchi, K. Fujii, and Y. Tabei. 2020. Succinct trit-array trie for scalable trajectory similarity search. In SIGSPATIAL (2020).

Digital Library

[12]

T. Kipf and M. Welling. 2017. Semi-supervised classification with graph convolutional networks. arXiv: 1609.02907. Retrieved from https://arxiv.org/abs/1609.02907.

[13]

S. Koide, C. Xiao, and Y. Ishikawa. 2020. Fast subtrajectory similarity search in road networks under weighted edit distance constraints. Proc. VLDB 13 (2020), 2188–2201.

Digital Library

[14]

J. Lee, J. Han, and K. Whang. 2007. Trajectory clustering: A partition-and-group framework. In SIGMOD’07.

[15]

L. Li, K. Zheng, S. Wang, W. Hua, and X. Zhou. 2018. Go slow to go fast: Minimal on-road time route scheduling with parking facilities using historical trajectory. VLDB J. 27 (2018), 321–345.

Digital Library

[16]

X. Li, K. Zhao, G. Cong, C. S. Jensen, and W. Wei. 2018. Deep representation learning for trajectory similarity computation. In ICDE. 617–628.

[17]

X. Li, Y. Zhao, J. Guo, and K. Zheng. 2020. Group task assignment with social impact-based preference in spatial crowdsourcing. In DASFAA. 677–693.

[18]

X. Li, Y. Zhao, K. Zheng, and X. Zhou. 2020. Consensus-based group task assignment with social impact in spatial crowdsourcing. Data Sci. Eng. 5, 4 (2020), 375–390.

[19]

G. Liu, Y. Liu, K. Zheng, An Liu, Z. Li, Y. Wang, and X. Zhou. 2018. MCS-GPM: Multi-constrained simulation based graph pattern matching in contextual social graphs. IEEE Trans. Knowl. Data Eng. 30 (2018), 1050–1064.

[20]

G. Liu, Y. Wang, and M. Orgun. 2013. Finding the optimal social trust path for the selection of trustworthy service providers in complex social networks. IEEE Trans. Serv. Comput. 6 (2013), 152–167.

Digital Library

[21]

Y. Liu, K. Zhao, G. Cong, and Z. Bao. 2020. Online anomalous trajectory detection with deep generative sequence modeling. In ICDE. 949–960.

[22]

A. Maheshwari, J. Sack, and C. Scheffer. 2015. Approximating the integral Fréchet distance. ArXiv abs/1512.03359.

[23]

W. Pei, D. Tax, and L. V. D. Maaten. 2016. Modeling time series similarity with siamese recurrent networks. ArXiv abs/1603.04713.

[24]

T. Rakthanmanon, Bilson J. L. Campana, A. Mueen, Gustavo E. A. P. A. Batista, M. Westover, Q. Zhu, J. Zakaria, and E. J. Keogh. 2012. Searching and mining trillions of time series subsequences under dynamic time warping. In KDD, 262–270.

Digital Library

[25]

T. Rakthanmanon, B. J. L. Campana, A. Mueen, G. E. A. P. A. Batista, M. Westover, Q. Zhu, J. Zakaria, and E. J. Keogh. 2013. Addressing big data time series: Mining trillions of time series subsequences under dynamic time warping. ACM Trans. Knowl. Disco. Data 7, 3 (2013).

[26]

S. Ranu, P. Deepak, A. Telang, P. Deshpande, and S. Raghavan. 2015. Indexing and matching trajectories under inconsistent sampling rates. In ICDE. 999–1010.

[27]

Y. Sakurai, C. Faloutsos, and M. Yamamuro. 2007. Stream monitoring under the time warping distance. In ICDE. 1046–1055.

[28]

M. Schuster and K. Paliwal. 1997. Bidirectional recurrent neural networks. IEEE Trans. Sign. Process. 45 (1997), 2673–2681.

Digital Library

[29]

M. Seo, A. Kembhavi, A. Farhadi, and H. Hajishirzi. 2017. Bidirectional attention flow for machine comprehension. arXiv: 1611.01603. Retrieved from https://arxiv.org/abs/1611.01603.

[30]

H. Su, S. Liu, B. Zheng, X. Zhou, and K. Zheng. 2019. A survey of trajectory distance measures and performance evaluation. VLDB J. 29 (2019), 3–32.

Digital Library

[31]

H. Su, K. Zheng, J. Huang, H. Wang, and X. Zhou. 2014. Calibrating trajectory data for spatio-temporal similarity analysis. VLDB J. 24 (2014), 93–116.

Digital Library

[32]

A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin. 2017. Attention is all you need. In NIPS.

Digital Library

[33]

P. Velickovic, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio. 2018. Graph attention networks. arXiv: 1710.10903. Retrieved from https://arxviv.org/abs/1710.10903.

[34]

O. Vinyals, M. Fortunato, and N. Jaitly. 2015. Pointer networks. arXiv: 1506.03134. Retrieved from https://arxiv.org/abs/1506.03134.

[35]

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

[36]

S. Wang and J. Jiang. 2016. Learning natural language inference with LSTM. arXiv: 1512.08849. Retrieved from https://arxiv.org/abs/1512.08849.

[37]

S. Wang and J. Jiang. 2017. Machine comprehension using match-LSTM and answer pointer. arXiv: 1608.07905. Retrieved from https://arxiv.org/abs/1608.07905.

[38]

Z. Wang, C. Long, G. Cong, and Y. Liu. 2020. Efficient and effective similar subtrajectory search with deep reinforcement learning. Proc. VLDB 13 (2020), 2312–2325.

Digital Library

[39]

F. Wu, T. Zhang, A. Souza, C. Fifty, T. Yu, and K. Q. Weinberger. 2019. Simplifying graph convolutional networks. arXiv: 1902.07153. Retrieved from https://arxiv.org/abs/1902.07153.

[40]

J. Xia, Y. Zhao, G. Liu, J. Xu, M. Zhang, and K. Zheng. 2019. Profit-driven task assignment in spatial crowdsourcing. In IJCAI. 1914–1920.

[41]

M. Xie. 2014. EDS: A segment-based distance measure for sub-trajectory similarity search. In SIGMOD (2014).

[42]

C. Xiong, V. Zhong, and R. Socher. 2017. Dynamic coattention networks for question answering. arXiv: 1611.01604. Retrieved from https://arxiv.org/abs/1611.01604.

[43]

Z. Yang, Z. Dai, Y. Yang, J. Carbonell, R. Salakhutdinov, and Quoc V. Le. 2019. XLNet: Generalized autoregressive pretraining for language understanding. In NeurIPS.

[44]

D. Yao, G. Cong, C. Zhang, and J. Bi. 2019. Computing trajectory similarity in linear time: A generic seed-guided neural metric learning approach. In ICDE. 1358–1369.

[45]

B. Yi, H. V. Jagadish, and C. Faloutsos. 1998. Efficient retrieval of similar time sequences under time warping. In ICDE. 201–208.

Digital Library

[46]

A. W. Yu, D. Dohan, M. Luong, R. Zhao, K. Chen, M. Norouzi, and Quoc V. Le. 2018. QANet: Combining local convolution with global self-attention for reading comprehension. ArXiv abs/1804.09541.

[47]

Y. Zhao, Y. Li, Y. Wang, H. Su, and K. Zheng. 2017. Destination-aware task assignment in spatial crowdsourcing. In CIKM. 297–306.

[48]

Y. Zhao, S. Shang, Y. Wang, B. Zheng, Q. V. H. Nguyen, and K. Zheng. 2018. REST: A reference-based framework for spatio-temporal trajectory compression. In SIGKDD. 2797–2806.

[49]

Y. Zhao, J. Xia, G. Liu, H. Su, D. Lian, S. Shang, and K. Zheng. 2019. Preference-aware task assignment in spatial crowdsourcing. In AAAI. 2629–2636.

[50]

Y. Zhao, K. Zheng, Y. Cui, H. Su, F. Zhu, and X. Zhou. 2020. Predictive task assignment in spatial crowdsourcing: A data-driven approach. In ICDE. 13–24.

[51]

Y. Zhao, K. Zheng, J. Guo, B. Yang, T. B. Pedersen, and C. S. Jensen. 2021. Fairness-aware task assignment in spatial crowdsourcing: Game-theoretic approaches. In ICDE.

[52]

Y. Zhao, K. Zheng, Y. Li, H. Su, J. Liu, and X. Zhou. 2019. Destination-aware task assignment in spatial crowdsourcing: A worker decomposition approach. IEEE Trans. Knowl. Data Eng. 32, 12 (2019), 2336–2350.

[53]

K. Zheng, Y. Zhao, D. Lian, B. Zheng, G. Liu, and X. Zhou. 2020. Reference-based framework for spatio-temporal trajectory compression and query processing. IEEE Trans. Knowl. Data Eng. 32 (2020), 2227–2240.

[54]

K. Zheng, Y. Zheng, N. J. Yuan, S. Shang, and X. Zhou. 2014. Online discovery of gathering patterns over trajectories. IEEE Trans. Knowl. Data Eng. 26 (2014), 1974–1988.

Cited By

Musleh MMokbel M(2024)Let's Speak Trajectories: A Vision to Use NLP Models for Trajectory Analysis TasksACM Transactions on Spatial Algorithms and Systems10.1145/365647010:2(1-25)Online publication date: 1-Jul-2024
https://dl.acm.org/doi/10.1145/3656470
Wang KYang SJin JCheng PYang JLin X(2024)Efficient Learning-based Top-k Representative Similar Subtrajectory Query2024 IEEE 40th International Conference on Data Engineering (ICDE)10.1109/ICDE60146.2024.00335(4396-4408)Online publication date: 13-May-2024
https://doi.org/10.1109/ICDE60146.2024.00335
Shang YTing KWang ZWang Y(2024)Distributional Kernel: An Effective and Efficient Means for Trajectory RetrievalAdvances in Knowledge Discovery and Data Mining10.1007/978-981-97-2262-4_22(271-283)Online publication date: 7-May-2024
https://dl.acm.org/doi/10.1007/978-981-97-2262-4_22
Show More Cited By

Index Terms

Efficient and Effective Similar Subtrajectory Search: A Spatial-aware Comprehension Approach
1. Computing methodologies
  1. Machine learning
    1. Learning paradigms
      1. Supervised learning
        Supervised learning by classification
    2. Machine learning approaches
      1. Neural networks

Recommendations

A Graph-based Approach for Trajectory Similarity Computation in Spatial Networks
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining

Trajectory similarity computation is an essential operation in many applications of spatial data analysis. In this paper, we study the problem of trajectory similarity computation over spatial network, where the real distances between objects are ...
Efficient Non-Learning Similar Subtrajectory Search

Similar subtrajectory search is a finer-grained operator that can better capture the similarities between one query trajectory and a portion of a data trajectory than the traditional similar trajectory search, which requires that the two checking ...
Efficient and effective similar subtrajectory search with deep reinforcement learning

Similar trajectory search is a fundamental problem and has been well studied over the past two decades. However, the similar subtrajectory search (SimSub) problem, aiming to return a portion of a trajectory (i.e., a subtrajectory), which is the most ...

Comments

Information & Contributors

Information

Published In

cover image ACM Transactions on Intelligent Systems and Technology

ACM Transactions on Intelligent Systems and Technology Volume 13, Issue 3

June 2022

415 pages

ISSN:2157-6904

EISSN:2157-6912

DOI:10.1145/3508465

Editor:
Huan Liu
Arizona State University, USA

Issue’s Table of Contents

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].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 13 April 2022

Accepted: 01 March 2021

Revised: 01 February 2021

Received: 01 January 2021

Published in TIST Volume 13, Issue 3

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Refereed

Funding Sources

NSFC

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
800
Total Downloads

Downloads (Last 12 months)128
Downloads (Last 6 weeks)5

Reflects downloads up to 19 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Musleh MMokbel M(2024)Let's Speak Trajectories: A Vision to Use NLP Models for Trajectory Analysis TasksACM Transactions on Spatial Algorithms and Systems10.1145/365647010:2(1-25)Online publication date: 1-Jul-2024
https://dl.acm.org/doi/10.1145/3656470
Wang KYang SJin JCheng PYang JLin X(2024)Efficient Learning-based Top-k Representative Similar Subtrajectory Query2024 IEEE 40th International Conference on Data Engineering (ICDE)10.1109/ICDE60146.2024.00335(4396-4408)Online publication date: 13-May-2024
https://doi.org/10.1109/ICDE60146.2024.00335
Shang YTing KWang ZWang Y(2024)Distributional Kernel: An Effective and Efficient Means for Trajectory RetrievalAdvances in Knowledge Discovery and Data Mining10.1007/978-981-97-2262-4_22(271-283)Online publication date: 7-May-2024
https://dl.acm.org/doi/10.1007/978-981-97-2262-4_22
Liu SChen XWu ZDeng LSu HZheng KAl Hasan MXiong L(2022)HeGAProceedings of the 31st ACM International Conference on Information & Knowledge Management10.1145/3511808.3557345(1319-1328)Online publication date: 17-Oct-2022
https://dl.acm.org/doi/10.1145/3511808.3557345

View Options

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.

Full Text

View this article in Full Text.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View full text|Download PDF

View Issue’s Table of Contents