TrajRL-TFF: A Trajectory Representation Learning Method Based on Time-domain and Frequency-domain Feature Fusion
Uloženo v:
| Vydáno v: | Computational Urban Science vol. 5, no. 1 (Dec 2025), p. 60 |
|---|---|
| Hlavní autor: | |
| Další autoři: | , , , , , , |
| Vydáno: |
Springer Nature B.V.
|
| Témata: | |
| On-line přístup: | Citation/Abstract Full Text Full Text - PDF |
| Tagy: |
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3267569664 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2730-6852 | ||
| 024 | 7 | |a 10.1007/s43762-025-00219-4 |2 doi | |
| 035 | |a 3267569664 | ||
| 045 | 2 | |b d20251201 |b d20251231 | |
| 100 | 1 | |a Liu, Kang |u Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China (GRID:grid.9227.e) (ISNI:0000000119573309) | |
| 245 | 1 | |a TrajRL-TFF: A Trajectory Representation Learning Method Based on Time-domain and Frequency-domain Feature Fusion | |
| 260 | |b Springer Nature B.V. |c Dec 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Trajectory representation learning transforms raw trajectory data (sequences of spatiotemporal points) into low-dimensional representation vectors to improve downstream tasks such as trajectory similarity computation, prediction, and classification. Existing models primarily adopt self-supervised learning frameworks, often employing models like Recurrent Neural Networks (RNNs) as encoders to capture local dependency in trajectory sequences. However, individual mobility within urban areas exhibits regular and periodic patterns, suggesting the need for a more comprehensive representation from both local and global perspectives. To address this, we propose TrajRL-TFF, a trajectory representation learning method based on time-domain and frequency-domain feature fusion. First, considering the heterogeneous distribution of trajectory data in space, a quadtree is employed for spatial partitioning and coding. Then, each trajectory is converted into a quadtree-code based time series (i.e., time-domain signal), with its corresponding frequency-domain signal derived via Discrete Fourier Transform (DFT). Finally, a trajectory encoder, combining an RNN-based time-domain encoder and a Transformer-based frequency domain encoder, is constructed to capture the trajectory’s local and global features, respectively, and trained by a self-supervised sequence encoding-decoding framework with trajectory perturbation-reconstruction task. Experiments demonstrate that TrajRL-TFF outperforms baselines in downstream tasks including trajectory querying and prediction, confirming that integrating time- and frequency-domain signals enables a more comprehensive representation of human mobility regularities and patterns, which provides valuable guidance for trajectory representation learning and trajectory modeling in future studies. | |
| 653 | |a Fourier transforms | ||
| 653 | |a Self-supervised learning | ||
| 653 | |a Traffic | ||
| 653 | |a Frequency domain analysis | ||
| 653 | |a Recurrent neural networks | ||
| 653 | |a Time domain analysis | ||
| 653 | |a Design | ||
| 653 | |a Learning | ||
| 653 | |a Encoding-Decoding | ||
| 653 | |a Sequences | ||
| 653 | |a Machine learning | ||
| 653 | |a Time series | ||
| 653 | |a Coders | ||
| 653 | |a Urban areas | ||
| 653 | |a Neural networks | ||
| 653 | |a Representations | ||
| 653 | |a Semantics | ||
| 653 | |a Economic | ||
| 700 | 1 | |a Lin, Zhiying |u Southern University of Science and Technology, Shenzhen, China (GRID:grid.263817.9) (ISNI:0000 0004 1773 1790); Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China (GRID:grid.9227.e) (ISNI:0000000119573309) | |
| 700 | 1 | |a Zhu, Kemin |u Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China (GRID:grid.9227.e) (ISNI:0000000119573309) | |
| 700 | 1 | |a Yin, Ling |u Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China (GRID:grid.9227.e) (ISNI:0000000119573309) | |
| 700 | 1 | |a Zheng, Jianze |u Sun Yat-Sen University, Shenzhen, China (GRID:grid.12981.33) (ISNI:0000 0001 2360 039X) | |
| 700 | 1 | |a Feng, Yongheng |u Peking University, College of Urban and Environmental Sciences, Beijing, China (GRID:grid.11135.37) (ISNI:0000 0001 2256 9319) | |
| 700 | 1 | |a Wang, Shaohua |u Aerospace Information Research Institute, Chinese Academy of Sciences, State Key Laboratory of Remote Sensing Science, Beijing, China (GRID:grid.507725.2); University of Chinese Academy of Sciences, Beijing, China (GRID:grid.410726.6) (ISNI:0000 0004 1797 8419) | |
| 700 | 1 | |a Zhang, Yan |u SmartSteps, Beijing, China (GRID:grid.410726.6) | |
| 773 | 0 | |t Computational Urban Science |g vol. 5, no. 1 (Dec 2025), p. 60 | |
| 786 | 0 | |d ProQuest |t Publicly Available Content Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3267569664/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text |u https://www.proquest.com/docview/3267569664/fulltext/embedded/6A8EOT78XXH2IG52?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3267569664/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch |