Abstract
The ubiquity of positioning devices and wireless networks has been significantly boosting the development of LBS (location-based service) technology and applications. As is widely used in LBS, trajectory top-k query serves as the key operation in a variety of large-scale web services, such as route recommendation, user behavior pattern analysis, etc. Unfortunately, existing top-k methods usually measure the trajectory similarity from a certain perspective, which leads to niche applications, not to mention the high computation complexity causing performance bottlenecks. To enable more types of data mining and analysis for web services, we propose a learning-based approach for multi-scenario trajectory similarity search with the generic metric, named TrajGS. Different from existing trajectory similarity measurements that are calculated by a single principle, TrajGS aims at proposing a generic rule that considers the trajectory correlation from multiple aspects and improves the accuracy of search in any circumstances. Specifically, TrajGS has two innovative modules: 1) a new trajectory representation enabled by a bidirectional LSTM model that can better capture the contextual information of trajectory and overcome the position error caused by outliers. 2) A generic trajectory similarity metric combining multiple distance measures obtains more versatile and accurate top-k results in various scenarios. Extensive experiments conducted on real datasets show that TrajGS achieves both impressive accuracy and adequate training time on trajectory similarity search compared with single-metric solutions. In particular, it achieves 5x–10x speedup and 20%–30% accuracy improvement over Euclidean, Hausdorff, DTW, and EDR measurements.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ma, C., Hua, L., Shou, L., Chen, G.: Ksq: Top-k similarity query on uncertain trajectories. IEEE Trans. Knowl. Data Eng. 25(9), 2049–2062 (2012)
Toohey, K., Duckham, M.: Trajectory similarity measures. Sigspatial Spec. 7(1), 43–50 (2015)
Fang, Z., Du, Y., Chen, L., Hu, Y., Gao, Y., Chen, G.: E2 dtc: an end to end deep trajectory clustering framework via self-training. In: 2021 IEEE 37th International Conference on Data Engineering (ICDE), pp. 696–707. IEEE (2021)
Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673–2681 (1997)
Yi, B.-K., Jagadish, H.V., Faloutsos, C.: Efficient retrieval of similar time sequences under time warping. In: Proceedings 14th International Conference on Data Engineering, pp. 201–208. IEEE (1998)
Sakurai, Y., Yoshikawa, M., Faloutsos, C.: Ftw: fast similarity search under the time warping distance. In: Proceedings of the twenty-fourth ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems, pp. 326–337 (2005)
Rakthanmanon, T., et al. Searching and mining trillions of time series subsequences under dynamic time warping. In: Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 262–270 (2012)
Chen, L., Tamer Özsu, M., Oria, V.: Robust and fast similarity search for moving object trajectories. In: Proceedings of the 2005 ACM SIGMOD International Conference on Management of Data, pp. 491–502 (2005)
Li, X., Zhao, K., Cong, G., Jensen, C.S., Wei, W.: Deep representation learning for trajectory similarity computation. In: 2018 IEEE 34th International Conference on Data Engineering (ICDE), pp. 617–628. IEEE (2018)
Zhang, Y., Liu, A., Liu, G., Li, Z., Li, Q.: Deep representation learning of activity trajectory similarity computation. In: 2019 IEEE International Conference on Web Services (ICWS), pp. 312–319. IEEE (2019)
Yao, D., Cong, G., Zhang, C., Bi, J.: Computing trajectory similarity in linear time: a generic seed-guided neural metric learning approach. In: 2019 IEEE 35th International Conference on Data Engineering (ICDE), pp. 1358–1369. IEEE (2019)
Yao, D., Cong, G., Zhang, C., Meng, X., Duan, R., Bi, J.: A linear time approach to computing time series similarity based on deep metric learning. IEEE Trans. Knowl. Data Eng. (2020)
Liu, Y., Zhao, K., Cong, G.: Efficient similar region search with deep metric learning. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1850–1859 (2018)
Zhang, D., Li, N., Zhou, Z.H., Chen, C., Sun, L., Li, S.: ibat: detecting anomalous taxi trajectories from gps traces. In: Proceedings of the 13th International Conference on Ubiquitous Computing, pp. 99–108 (2011)
Yang, P., Wang, H., Zhang, Y., Qin, L., Zhang, W., Lin, X.: T3s: effective representation learning for trajectory similarity computation. In: 2021 IEEE 37th International Conference on Data Engineering (ICDE), pp. 2183–2188. IEEE (2021)
Siami-Namini, S., Tavakoli, N., Namin, A.S.: The performance of LSTM and BILSTM in forecasting time series. In: 2019 IEEE International Conference on Big Data (Big Data), pp. 3285–3292. IEEE (2019)
Moreira-Matias, L., Gama, J., Ferreira, M., Mendes-Moreira, J., Damas, L.: Time-evolving OD matrix estimation using high-speed GPS data streams. Expert Syst. Appl. 44, 275–288 (2016)
Taghizadeh, S., Elekes, A., Schäler, M., Böhm, K.: How meaningful are similarities in deep trajectory representations? Inf. Syst. 98, 101452 (2021)
Acknowledgment
This work was supported by National Natural Science Foundation of China under grant (No. 61802273, 62102277), Postdoctoral Science Foundation of China (No. 2020M681529), Natural Science Foundation of Jiangsu Province (BK20210703), China Science and Technology Plan Project of Suzhou (No. SYG202139), Postgraduate Research & Practice Innovation Program of Jiangsu Province (SJCX2\(\_\)11342), Extracurricular Academic Research Foundation of Jiangsu Province (KY20220079A), Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Feng, C., Pan, Z., Fang, J., Chao, P., Liu, A., Zhao, L. (2022). A Learning-Based Approach for Multi-scenario Trajectory Similarity Search. In: Chbeir, R., Huang, H., Silvestri, F., Manolopoulos, Y., Zhang, Y. (eds) Web Information Systems Engineering – WISE 2022. WISE 2022. Lecture Notes in Computer Science, vol 13724. Springer, Cham. https://doi.org/10.1007/978-3-031-20891-1_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-20891-1_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20890-4
Online ISBN: 978-3-031-20891-1
eBook Packages: Computer ScienceComputer Science (R0)