Cross-view location alignment enhanced spatial-topological aware dual transformer for travel time estimation
Accurately estimating route travel time is crucial for intelligent transportation systems. Urban road networks and routes can be viewed from spatial and topological perspectives while existing works typically focus on one view and disregard important information from the other perspective. In this p...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9790 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-10790 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-107902024-12-12T09:00:03Z Cross-view location alignment enhanced spatial-topological aware dual transformer for travel time estimation ZHANG, Hanyuan ZHANG, Xinyu JIANG, Qize LI, Liang ZHENG, Baihua SUN, Weiwei Accurately estimating route travel time is crucial for intelligent transportation systems. Urban road networks and routes can be viewed from spatial and topological perspectives while existing works typically focus on one view and disregard important information from the other perspective. In this paper, we propose, a novel travel time estimation model. It incorporates an alignment-enhanced spatial-topological aware dual transformer model to adaptively incorporate intra-and inter-view features in the route, guided by cross-view location alignment matrices with clear correspondences between locations in two views. Additionally, we propose a sparsity-aware dual-view traffic feature extraction module to effectively capture temporal traffic state changes. Compared to baseline models, demonstrates improved performance on the MAPE and MAE metrics for Chengdu and Shanghai datasets, achieving improvements of 8.32%, 7.03%, 8.06% and 9.51% respectively, validating the effectiveness of in travel time estimation. 2024-10-01T07:00:00Z text https://ink.library.smu.edu.sg/sis_research/9790 info:doi/10.1109/TITS.2024.3463501 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Roads Estimation Transformers Feature extraction Predictive models Accuracy Long short term memory Trajectory Computational modeling Adaptation models Travel time estimation transformer spatial-temporal data mining multi-view learning Databases and Information Systems |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Roads Estimation Transformers Feature extraction Predictive models Accuracy Long short term memory Trajectory Computational modeling Adaptation models Travel time estimation transformer spatial-temporal data mining multi-view learning Databases and Information Systems |
spellingShingle |
Roads Estimation Transformers Feature extraction Predictive models Accuracy Long short term memory Trajectory Computational modeling Adaptation models Travel time estimation transformer spatial-temporal data mining multi-view learning Databases and Information Systems ZHANG, Hanyuan ZHANG, Xinyu JIANG, Qize LI, Liang ZHENG, Baihua SUN, Weiwei Cross-view location alignment enhanced spatial-topological aware dual transformer for travel time estimation |
description |
Accurately estimating route travel time is crucial for intelligent transportation systems. Urban road networks and routes can be viewed from spatial and topological perspectives while existing works typically focus on one view and disregard important information from the other perspective. In this paper, we propose, a novel travel time estimation model. It incorporates an alignment-enhanced spatial-topological aware dual transformer model to adaptively incorporate intra-and inter-view features in the route, guided by cross-view location alignment matrices with clear correspondences between locations in two views. Additionally, we propose a sparsity-aware dual-view traffic feature extraction module to effectively capture temporal traffic state changes. Compared to baseline models, demonstrates improved performance on the MAPE and MAE metrics for Chengdu and Shanghai datasets, achieving improvements of 8.32%, 7.03%, 8.06% and 9.51% respectively, validating the effectiveness of in travel time estimation. |
format |
text |
author |
ZHANG, Hanyuan ZHANG, Xinyu JIANG, Qize LI, Liang ZHENG, Baihua SUN, Weiwei |
author_facet |
ZHANG, Hanyuan ZHANG, Xinyu JIANG, Qize LI, Liang ZHENG, Baihua SUN, Weiwei |
author_sort |
ZHANG, Hanyuan |
title |
Cross-view location alignment enhanced spatial-topological aware dual transformer for travel time estimation |
title_short |
Cross-view location alignment enhanced spatial-topological aware dual transformer for travel time estimation |
title_full |
Cross-view location alignment enhanced spatial-topological aware dual transformer for travel time estimation |
title_fullStr |
Cross-view location alignment enhanced spatial-topological aware dual transformer for travel time estimation |
title_full_unstemmed |
Cross-view location alignment enhanced spatial-topological aware dual transformer for travel time estimation |
title_sort |
cross-view location alignment enhanced spatial-topological aware dual transformer for travel time estimation |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2024 |
url |
https://ink.library.smu.edu.sg/sis_research/9790 |
_version_ |
1819113139658031104 |