David Alexander Tedjopurnomo
Abstract
Similar trajectory search is a crucial task that facilitates many downstream spatial data analytic applications. Despite its importance, many of the current literature focus solely on the trajectory’s spatial similarity while neglecting the temporal information. Additionally, the few papers that use both the spatial and temporal features based their approach on a traditional point-to-point comparison. These methods model the importance of the spatial and temporal aspect of the data with only a single, pre-defined balancing factor for all trajectories, even though the relative spatial and temporal balance can change from trajectory to trajectory. In this article, we propose the first spatio-temporal, deep-representation-learning-based approach to similar trajectory search. Experiments show that utilizing both features offers significant improvements over existing point-to-point comparison and deep-representation-learning approach. We also show that our deep neural network approach is faster and performs more consistently compared to the point-to-point comparison approaches.
- [1] . 2015. Neural machine translation by jointly learning to align and translate. CoRR abs/1409.0473. https://arxiv.org/abs/1409.0473.Google Scholar
- [2] . 2012. Unsupervised feature learning and deep learning: A review and new perspectives. CoRR abs/1206.5538. https://arxiv.org/abs/1206.5538.Google Scholar
- [3] . 1994. Using dynamic time warping to find patterns in time series. In KDD. 359–370. Google ScholarDigital Library
- [4] . 2010. Large scale online learning of image similarity through ranking. Journal of Machine Learning Research 11 (2010), 1109–1135. Google ScholarDigital Library
- [5] . 2004. On the marriage of Lp-norms and edit distance. In VLDB, Vol. 30. 792–803. Google ScholarDigital Library
- [6] . 2005. Robust and fast similarity search for moving object trajectories. In SIGMOD. 491-502. Google ScholarDigital Library
- [7] . 2010. Searching trajectories by locations: An efficiency study. In SIGMOD. 255–266. Google ScholarDigital Library
- [8] . 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. CoRR abs/1406.1078. https://arxiv.org/abs/1406.1078.Google Scholar
- [9] . 2019. Spatial temporal trajectory similarity join. In APWeb-WAIM, Vol. 11642. 251–259.Google Scholar
- [10] . 2000. Learning to forget: Continual prediction with LSTM. Neural Computation 12 (2000), 2451–2471. Google ScholarDigital Library
- [11] . 1997. Long short-term memory. Neural Computation 9, 8 (1997), 1735–1780. Google ScholarDigital Library
- [12] . 2015. Spatial transformer networks. In NIPS 28. 2017–2025. Google ScholarDigital Library
- [13] . 2015. Adam: A method for stochastic optimization. CoRR abs/1412.6980. https://arxiv.org/abs/1412.6980.Google Scholar
- [14] . 2018. Deep representation learning for trajectory similarity computation. In ICDE 34. 617–628.Google Scholar
- [15] . 2019. Dynamic ridesharing in peak travel periods. IEEE Transactions on Knowledge and Data Engineering 33, 7 (2021), 2888–2902. https://doi.org/10.1109/TKDE.2019.2961341Google Scholar
- [16] . 2013. Efficient estimation of word representations in vector space. arXiv:1301.3781. https://arxiv.org/abs/1301.3781.Google Scholar
- [17] . 2013. Distributed representations of words and phrases and their Compositionality. arXiv:1310.4546. https://arxiv.org/abs/1310.4546. Google ScholarDigital Library
- [18] . 2018. Deep contextualized word representations. arXiv:1802.05365. https://arxiv.org/abs/1802.05365.Google Scholar
- [19] . 2012. Searching and mining trillions of time series subsequences under dynamic time warping. In KDD. 262–270. Google ScholarDigital Library
- [20] . 2015. Indexing and matching trajectories under inconsistent sampling rates. In ICDE. 999–1010.Google Scholar
- [21] . 2014. Personalized trajectory matching in spatial networks. The VLDB Journal 23 (2014), 449–468. Google ScholarDigital Library
- [22] . 2018. DITA: Distributed in-memory trajectory analytics. In SIGMOD. 725–740. Google ScholarDigital Library
- [23] . 2016. Generalizing DTW to the multi-dimensional case requires an adaptive approach. Data Mining and Knowledge Discovery 31 (2016), 1–31. Google ScholarDigital Library
- [24] . 2015. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. https://arxiv.org/abs/1409.1556.Google Scholar
- [25] . 2013. Calibrating trajectory data for similarity-based analysis. In SIGMOD. 833–844. Google ScholarDigital Library
- [26] . 2002. Discovering similar multidimensional trajectories. In ICDE. 673–684. Google ScholarDigital Library
- [27] . 2020. A survey on trajectory data management, analytics, and learning. arXiv:2003.11547. https://arxiv.org/abs/2003.11547. Google ScholarDigital Library
- [28] . 2019. Fast large-scale trajectory clustering. Proceedings of the VLDB Endowment 13, 1 (2019), 29–42. Google ScholarDigital Library
- [29] . 2018. Torch: A search engine for trajectory data. In SIGIR. 535–544. Google ScholarDigital Library
- [30] . 2019. Intelligent traffic analytics: From monitoring to controlling. In WSDM. 778–781. Google ScholarDigital Library
- [31] . 2020. Efficient and effective similar subtrajectory search with deep reinforcement learning. arXiv:2003.02542. https://arxiv.org/abs/2003.02542. Google ScholarDigital Library
- [32] . 2017. Distributed trajectory similarity search. Proceedings of the VLDB Endowment 10, 11 (2017), 1478–1489. Google ScholarDigital Library
- [33] . 2020. Querying recurrent convoys over trajectory data. ACM TIST 11, 5 (2020), 1–24. Google ScholarDigital Library
- [34] . 2019. Computing trajectory similarity in linear time: A generic seed-guided neural metric learning approach. In ICDE. 1358–1369.Google Scholar
- [35] . 2019. Distributed in-memory trajectory similarity search and join on road network. In ICDE. 1262–1273.Google Scholar
- [36] . 2020. Effective travel time estimation: When historical trajectories over road networks matter. In SIGMOD. 2135–2149. Google ScholarDigital Library
- [37] . 2020. SST: Synchronized spatial-temporal trajectory similarity search. GeoInformatica (2020), 1–24.Google Scholar
Index Terms
- Similar Trajectory Search with Spatio-Temporal Deep Representation Learning
Recommendations
Hybrid index for spatio-temporal OLAP operations
ADVIS'06: Proceedings of the 4th international conference on Advances in Information SystemsAccording to increase of spatial data, many decision support systems require the fast spatio-temporal analysis. This paper proposes the improved index for efficient OLAP in a spatial data warehouse. The main idea is to use the hybrid index of the ...
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 network-constrained trajectory queries
SIGSPATIAL '22: Proceedings of the 30th International Conference on Advances in Geographic Information SystemsThe large search companies have very clearly shown that full-text search on very large datasets can be executed efficiently. In this paper, we show how querying spatio-temporal trajectory data can be converted to a full-text search problem. This allows ...
Comments