Feature Enhanced Spatial–Temporal Trajectory Similarity Computation
Abstract Trajectory similarity computation is a fundamental function in many applications of urban data analysis, such as trajectory clustering, trajectory compression, and route planning. In this paper, we study trajectory similarity computation on the road network. However, existing methods have b...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-08-01
|
| Series: | Data Science and Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s41019-024-00255-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850029725130424320 |
|---|---|
| author | Silin Zhou Chengrui Huang Yuntao Wen Lisi Chen |
| author_facet | Silin Zhou Chengrui Huang Yuntao Wen Lisi Chen |
| author_sort | Silin Zhou |
| collection | DOAJ |
| description | Abstract Trajectory similarity computation is a fundamental function in many applications of urban data analysis, such as trajectory clustering, trajectory compression, and route planning. In this paper, we study trajectory similarity computation on the road network. However, existing methods have been designed primarily for road network trajectories with spatial information, while ignoring the important temporal information in the real world. To solve this problem, we propose a Feature Enhanced Spatial–Temporal trajectory similarity computation framework FEST, which is a graph neural network (GNN) and sequence model pipeline. We first use the GNN model to capture global information on the road network. In particular, we enhance the process with multi-graph to learn multiple signals from the road network on different aspects. In addition to the original road network topology signal, we also take into account the content signal to learn spatial–temporal features from trajectory traffic, as well as the adaptive similarity signal of the road network to learn hidden features. From these three signals, we construct a multi-graph and use GCN to learn road intersection embedding jointly. Next, we propose a feature-enhanced Transformer with spatial–temporal information to learn correlation within the trajectory, and we further use mean-pooling to get the final trajectory embedding. We compare FEST with six trajectory similarity computation methods on two real-world datasets. The results show that FEST consistently outperforms all baselines and can improve the accuracy of the best-performing baseline. |
| format | Article |
| id | doaj-art-a1fa46ae6fa04decb8cb32c7efdfe8ad |
| institution | DOAJ |
| issn | 2364-1185 2364-1541 |
| language | English |
| publishDate | 2024-08-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Data Science and Engineering |
| spelling | doaj-art-a1fa46ae6fa04decb8cb32c7efdfe8ad2025-08-20T02:59:28ZengSpringerOpenData Science and Engineering2364-11852364-15412024-08-0110111110.1007/s41019-024-00255-wFeature Enhanced Spatial–Temporal Trajectory Similarity ComputationSilin Zhou0Chengrui Huang1Yuntao Wen2Lisi Chen3University of Electronic Science and Technology of ChinaUniversity of Electronic Science and Technology of ChinaUniversity of Electronic Science and Technology of ChinaUniversity of Electronic Science and Technology of ChinaAbstract Trajectory similarity computation is a fundamental function in many applications of urban data analysis, such as trajectory clustering, trajectory compression, and route planning. In this paper, we study trajectory similarity computation on the road network. However, existing methods have been designed primarily for road network trajectories with spatial information, while ignoring the important temporal information in the real world. To solve this problem, we propose a Feature Enhanced Spatial–Temporal trajectory similarity computation framework FEST, which is a graph neural network (GNN) and sequence model pipeline. We first use the GNN model to capture global information on the road network. In particular, we enhance the process with multi-graph to learn multiple signals from the road network on different aspects. In addition to the original road network topology signal, we also take into account the content signal to learn spatial–temporal features from trajectory traffic, as well as the adaptive similarity signal of the road network to learn hidden features. From these three signals, we construct a multi-graph and use GCN to learn road intersection embedding jointly. Next, we propose a feature-enhanced Transformer with spatial–temporal information to learn correlation within the trajectory, and we further use mean-pooling to get the final trajectory embedding. We compare FEST with six trajectory similarity computation methods on two real-world datasets. The results show that FEST consistently outperforms all baselines and can improve the accuracy of the best-performing baseline.https://doi.org/10.1007/s41019-024-00255-wTrajectory similarity computationSpatial–temporalRoad network |
| spellingShingle | Silin Zhou Chengrui Huang Yuntao Wen Lisi Chen Feature Enhanced Spatial–Temporal Trajectory Similarity Computation Data Science and Engineering Trajectory similarity computation Spatial–temporal Road network |
| title | Feature Enhanced Spatial–Temporal Trajectory Similarity Computation |
| title_full | Feature Enhanced Spatial–Temporal Trajectory Similarity Computation |
| title_fullStr | Feature Enhanced Spatial–Temporal Trajectory Similarity Computation |
| title_full_unstemmed | Feature Enhanced Spatial–Temporal Trajectory Similarity Computation |
| title_short | Feature Enhanced Spatial–Temporal Trajectory Similarity Computation |
| title_sort | feature enhanced spatial temporal trajectory similarity computation |
| topic | Trajectory similarity computation Spatial–temporal Road network |
| url | https://doi.org/10.1007/s41019-024-00255-w |
| work_keys_str_mv | AT silinzhou featureenhancedspatialtemporaltrajectorysimilaritycomputation AT chengruihuang featureenhancedspatialtemporaltrajectorysimilaritycomputation AT yuntaowen featureenhancedspatialtemporaltrajectorysimilaritycomputation AT lisichen featureenhancedspatialtemporaltrajectorysimilaritycomputation |