Enhanced trajectory reconstruction from sparse and noisy GPS data: A progressive chunked transformer approach
Trajectory reconstruction from sparse and noisy GPS data is critical for applications such as urban mobility analysis, transportation planning, and navigation systems. However, large sampling intervals and the typically long output sequences required to reconstruct coherent travel trajectories signi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Communications in Transportation Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S277242472500040X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839594024940339200 |
|---|---|
| author | Yonghui Liu Qian Li Inhi Kim |
| author_facet | Yonghui Liu Qian Li Inhi Kim |
| author_sort | Yonghui Liu |
| collection | DOAJ |
| description | Trajectory reconstruction from sparse and noisy GPS data is critical for applications such as urban mobility analysis, transportation planning, and navigation systems. However, large sampling intervals and the typically long output sequences required to reconstruct coherent travel trajectories significantly increase computational complexity, particularly in the presence of noise. To address these challenges, we propose a progressive chunked transformer (ProChunkFormer), which is a deep learning method for trajectory reconstruction that employs self-attention mechanisms and chunked processing to balance efficiency with accuracy. ProChunkFormer first generates intermediate trajectories at a semi-high frequency from low-frequency sampled data, and then the remaining trajectory is divided into manageable blocks and reconstructed parallelly in the condition of the semi-high-frequency trajectory. By combining progressive reconstruction with chunk processing, ProChunkFormer not only mitigates the cumulative errors commonly observed in autoregressive models but also alleviates the rapid increase in complexity associated with reconstructing ultralong trajectories. Specifically, our approach achieves quadratic optimization in time and space for attention modules, with cubic time savings compared with autoregressive decoding. A case study using an open-source taxi trajectory dataset confirms the effectiveness of our approach. The performance of ProChunkFormer is comparable to that of autoregressive transformers while offering better running efficiency. It improves the accuracy, F1 score (F1), mean absolute error (MAE), and road network mean absolute error (MAE_RN) by 23.1%, 18.6%, 22.3%, and 25.1%, respectively, for trajectories with a long interval time of up to 240 s. Furthermore, we investigate incorporating heuristic information to guide trajectory reconstruction for each block. The experimental results indicate an improvement in both the overall performance and convergence speed of the model. |
| format | Article |
| id | doaj-art-cffa43f52f5742d39ec43b55b21a80b5 |
| institution | Matheson Library |
| issn | 2772-4247 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Communications in Transportation Research |
| spelling | doaj-art-cffa43f52f5742d39ec43b55b21a80b52025-08-03T04:43:19ZengElsevierCommunications in Transportation Research2772-42472025-12-015100200Enhanced trajectory reconstruction from sparse and noisy GPS data: A progressive chunked transformer approachYonghui Liu0Qian Li1Inhi Kim2Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology, Daejeon, 34051, Republic of KoreaDonghai Laboratory, Zhoushan, 316021, ChinaCho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology, Daejeon, 34051, Republic of Korea; Corresponding author.Trajectory reconstruction from sparse and noisy GPS data is critical for applications such as urban mobility analysis, transportation planning, and navigation systems. However, large sampling intervals and the typically long output sequences required to reconstruct coherent travel trajectories significantly increase computational complexity, particularly in the presence of noise. To address these challenges, we propose a progressive chunked transformer (ProChunkFormer), which is a deep learning method for trajectory reconstruction that employs self-attention mechanisms and chunked processing to balance efficiency with accuracy. ProChunkFormer first generates intermediate trajectories at a semi-high frequency from low-frequency sampled data, and then the remaining trajectory is divided into manageable blocks and reconstructed parallelly in the condition of the semi-high-frequency trajectory. By combining progressive reconstruction with chunk processing, ProChunkFormer not only mitigates the cumulative errors commonly observed in autoregressive models but also alleviates the rapid increase in complexity associated with reconstructing ultralong trajectories. Specifically, our approach achieves quadratic optimization in time and space for attention modules, with cubic time savings compared with autoregressive decoding. A case study using an open-source taxi trajectory dataset confirms the effectiveness of our approach. The performance of ProChunkFormer is comparable to that of autoregressive transformers while offering better running efficiency. It improves the accuracy, F1 score (F1), mean absolute error (MAE), and road network mean absolute error (MAE_RN) by 23.1%, 18.6%, 22.3%, and 25.1%, respectively, for trajectories with a long interval time of up to 240 s. Furthermore, we investigate incorporating heuristic information to guide trajectory reconstruction for each block. The experimental results indicate an improvement in both the overall performance and convergence speed of the model.http://www.sciencedirect.com/science/article/pii/S277242472500040XTrajectory reconstructionTransformerChunked processingHeuristic-informedParallel computing |
| spellingShingle | Yonghui Liu Qian Li Inhi Kim Enhanced trajectory reconstruction from sparse and noisy GPS data: A progressive chunked transformer approach Communications in Transportation Research Trajectory reconstruction Transformer Chunked processing Heuristic-informed Parallel computing |
| title | Enhanced trajectory reconstruction from sparse and noisy GPS data: A progressive chunked transformer approach |
| title_full | Enhanced trajectory reconstruction from sparse and noisy GPS data: A progressive chunked transformer approach |
| title_fullStr | Enhanced trajectory reconstruction from sparse and noisy GPS data: A progressive chunked transformer approach |
| title_full_unstemmed | Enhanced trajectory reconstruction from sparse and noisy GPS data: A progressive chunked transformer approach |
| title_short | Enhanced trajectory reconstruction from sparse and noisy GPS data: A progressive chunked transformer approach |
| title_sort | enhanced trajectory reconstruction from sparse and noisy gps data a progressive chunked transformer approach |
| topic | Trajectory reconstruction Transformer Chunked processing Heuristic-informed Parallel computing |
| url | http://www.sciencedirect.com/science/article/pii/S277242472500040X |
| work_keys_str_mv | AT yonghuiliu enhancedtrajectoryreconstructionfromsparseandnoisygpsdataaprogressivechunkedtransformerapproach AT qianli enhancedtrajectoryreconstructionfromsparseandnoisygpsdataaprogressivechunkedtransformerapproach AT inhikim enhancedtrajectoryreconstructionfromsparseandnoisygpsdataaprogressivechunkedtransformerapproach |