GMTP: Enhanced Travel Time Prediction with Graph Attention Network and BERT Integration

(1) Background: Existing Vehicle travel time prediction applications face challenges in modeling complex road network and handling irregular spatiotemporal traffic state propagation. (2) Methods: To address these issues, we propose a Graph Attention-based Multi-Spatiotemporal Features for Travel Tim...

Full description

Saved in:
Bibliographic Details
Main Authors: Ting Liu, Yuan Liu
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:AI
Subjects:
Online Access:https://www.mdpi.com/2673-2688/5/4/141
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850036458927161344
author Ting Liu
Yuan Liu
author_facet Ting Liu
Yuan Liu
author_sort Ting Liu
collection DOAJ
description (1) Background: Existing Vehicle travel time prediction applications face challenges in modeling complex road network and handling irregular spatiotemporal traffic state propagation. (2) Methods: To address these issues, we propose a Graph Attention-based Multi-Spatiotemporal Features for Travel Time Prediction (GMTP) model, which integrates an enhanced graph attention network (GATv2) and Bidirectional Encoder Representations from Transformers (BERT) to analyze dynamic correlations across spatial and temporal dimensions. The pre-training process consists of two blocks: the Road Segment Interaction Pattern to Enhance GATv2, which generates road segment representation vectors, and a traffic congestion-aware trajectory encoder by incorporating a shared attention mechanism for high computational efficiency. Additionally, two self-supervised tasks are designed for improved model accuracy and robustness. (3) Results: The fine-tuned model had comparatively optimal performance metrics with significant reductions in Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Squared Error (RMSE). (4) Conclusions: Ultimately, the integration of this model into travel time prediction, based on two large-scale real-world trajectory datasets, demonstrates enhanced performance and computational efficiency.
format Article
id doaj-art-5e84ee65fe7f408091f2258fc37aba99
institution DOAJ
issn 2673-2688
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series AI
spelling doaj-art-5e84ee65fe7f408091f2258fc37aba992025-08-20T02:57:08ZengMDPI AGAI2673-26882024-12-01542926294410.3390/ai5040141GMTP: Enhanced Travel Time Prediction with Graph Attention Network and BERT IntegrationTing Liu0Yuan Liu1School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 102206, ChinaSchool of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 102206, China(1) Background: Existing Vehicle travel time prediction applications face challenges in modeling complex road network and handling irregular spatiotemporal traffic state propagation. (2) Methods: To address these issues, we propose a Graph Attention-based Multi-Spatiotemporal Features for Travel Time Prediction (GMTP) model, which integrates an enhanced graph attention network (GATv2) and Bidirectional Encoder Representations from Transformers (BERT) to analyze dynamic correlations across spatial and temporal dimensions. The pre-training process consists of two blocks: the Road Segment Interaction Pattern to Enhance GATv2, which generates road segment representation vectors, and a traffic congestion-aware trajectory encoder by incorporating a shared attention mechanism for high computational efficiency. Additionally, two self-supervised tasks are designed for improved model accuracy and robustness. (3) Results: The fine-tuned model had comparatively optimal performance metrics with significant reductions in Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Squared Error (RMSE). (4) Conclusions: Ultimately, the integration of this model into travel time prediction, based on two large-scale real-world trajectory datasets, demonstrates enhanced performance and computational efficiency.https://www.mdpi.com/2673-2688/5/4/141road networkGATv2BERTtravel time preditction
spellingShingle Ting Liu
Yuan Liu
GMTP: Enhanced Travel Time Prediction with Graph Attention Network and BERT Integration
AI
road network
GATv2
BERT
travel time preditction
title GMTP: Enhanced Travel Time Prediction with Graph Attention Network and BERT Integration
title_full GMTP: Enhanced Travel Time Prediction with Graph Attention Network and BERT Integration
title_fullStr GMTP: Enhanced Travel Time Prediction with Graph Attention Network and BERT Integration
title_full_unstemmed GMTP: Enhanced Travel Time Prediction with Graph Attention Network and BERT Integration
title_short GMTP: Enhanced Travel Time Prediction with Graph Attention Network and BERT Integration
title_sort gmtp enhanced travel time prediction with graph attention network and bert integration
topic road network
GATv2
BERT
travel time preditction
url https://www.mdpi.com/2673-2688/5/4/141
work_keys_str_mv AT tingliu gmtpenhancedtraveltimepredictionwithgraphattentionnetworkandbertintegration
AT yuanliu gmtpenhancedtraveltimepredictionwithgraphattentionnetworkandbertintegration